system

Abstract

We provide the system. [Solution] A means of storing profile data for collecting information based on user interests, A means of collecting data in real time from multiple sources and indexing it based on specific classifications, A means for filtering and prioritizing collected data by referring to stored profile data, A means for generating text and multimedia content based on filtered and prioritized data, A means of delivering the generated content to the user's device, A means of receiving feedback from users and updating the algorithm based on that feedback, 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] In modern society, it is difficult for people to efficiently obtain important and relevant information for themselves from a vast amount of information. In particular, in the busy daily life, it is required to efficiently acquire and view news and information that match one's interests within limited time. However, existing information collection means have difficulty fully corresponding to the individual interests of users, and there is also a problem that the amount of information is too large and it takes time to find the necessary news.

Means for Solving the Problems

[0005] This invention provides a system that efficiently delivers information tailored to users by storing profile data based on users' interests and preferences, and filtering and classifying data collected from multiple sources. Specifically, it prioritizes information by referring to the stored profile data and generates text and multimedia content in a format viewable within a time frame specified by the user. This system has a function to continuously collect user feedback and update the algorithm, improving the accuracy and relevance of information collection. Furthermore, by utilizing machine learning models, it is possible to automatically adjust news to match the user's preferences.

[0006] "Profile data" refers to information accumulated based on users' interests, preferences, and viewing history, and the system uses this information to select individual news articles.

[0007] "Information sources" refer to external data providers from which news and related content are obtained, such as websites and APIs.

[0008] "Filtering" refers to the process of selecting highly relevant data from collected information based on specific criteria.

[0009] "Prioritization" refers to the process of placing information that is deemed most important or relevant to the user at the top of a large amount of information.

[0010] "Text and multimedia content" refers to data in media formats such as text, audio, images, and video, including news and information provided to users.

[0011] "Feedback" refers to the opinions and evaluations received from users, and this information is used to adjust the algorithm.

[0012] A "machine learning model" refers to a part of a system that includes algorithms and methods that learn from data and improve prediction and classification in specific tasks. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units 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.

[0017] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, a numbered storage 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, etc.

[0019] 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).

[0020] 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."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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".

[0034] This invention is a system that enables users to obtain information based on their individual interests and preferences. The system operates primarily through interaction between a server, a terminal, and the user. In one example of this embodiment, the user uses a terminal to input their preferred news genres and desired viewing time.

[0035] The terminal sends user input to the server, which then creates a user profile based on this input. The server periodically collects news data from multiple sources, classifies the collected data by genre, and indexes it.

[0036] Based on the user's profile, the server selects relevant news articles and prioritizes them based on their importance and relevance. This makes it possible to select specific news articles that meet the user's needs.

[0037] The server then generates text and multimedia content based on the selected news. This generation step simultaneously utilizes speech synthesis technology and video clips to create visually and aurally effective content.

[0038] The generated content is edited to a length suitable for the time frame specified by the user. This allows users to efficiently obtain summaries of news they are interested in at their desired time. During delivery, the device provides the content to the user in either streaming or download format.

[0039] After a user views content, their device sends feedback to the server. This feedback evaluates how much the user enjoyed the news and whether it was relevant. The server analyzes this feedback and uses it as data to improve its information selection algorithm.

[0040] For example, if a user requests to watch "health" and "sports" news for 15 minutes at 8 AM, the server will collect relevant news articles based on this request, generate content, and deliver it at the specified time. This allows users to efficiently obtain the latest news. Through continuous use, this system will continue to evolve to better suit user preferences.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The user enters their preferred news genres and viewing times via their device. The device then sends this information to the server.

[0044] Step 2:

[0045] The server creates user profiles based on information received from users and stores them in a database. This makes it possible to manage the interests and needs of individual users.

[0046] Step 3:

[0047] The server periodically collects news data from multiple sources. This news data is obtained via APIs and web scraping, formatted, and then stored in a temporary data store.

[0048] Step 4:

[0049] The server analyzes the collected news data using natural language processing technology, classifying and indexing it based on pre-defined genres. This enables rapid searching and access.

[0050] Step 5:

[0051] The server references the user profile and filters news by genre. Furthermore, it prioritizes news based on its importance and recency.

[0052] Step 6:

[0053] The server uses prioritized news to generate text and multimedia content using text synthesis and video editing software. This creates content in a format that is easy for users to view.

[0054] Step 7:

[0055] The generated content is edited to fit the time frame specified by the user and prepared for distribution. The server saves the content to system storage.

[0056] Step 8:

[0057] When the device reaches the specified time, it retrieves video content from the server and provides it to the user in streaming or download format.

[0058] Step 9:

[0059] Users view content using their devices and then provide feedback on what they have been given.

[0060] Step 10:

[0061] The device sends the collected feedback information to the server. The server uses this feedback to improve the news selection algorithm and incorporate it into future content delivery.

[0062] (Example 1)

[0063] 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."

[0064] In today's information society, it is difficult for users to quickly and efficiently gather information relevant to their interests from a vast amount of data. Furthermore, filtering and selecting necessary information from this vast amount of data requires considerable time and effort. In addition, as users' interests change, there are few information provision systems that can adapt to these changes, resulting in challenges in providing effective information.

[0065] 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.

[0066] In this invention, the server includes means for generating and storing profile information based on the user's interests, means for acquiring the latest data from multiple sources and classifying and organizing it into different categories, and means for selecting the acquired data based on the accumulated profile information and ordering it according to its importance. This makes it possible to efficiently and quickly provide necessary information while adapting to the user's changing interests.

[0067] "Profile information" refers to a collection of data generated and stored based on a user's interests, preferences, viewing history, and other factors.

[0068] A "source of information" refers to an external repository or system that provides news, articles, and other knowledge.

[0069] A "category" is a framework for organizing and classifying collected information by genre or type.

[0070] "Selection" refers to the process of selecting information from the collected data that is highly relevant to the user's profile.

[0071] "Ordering" refers to the process of assigning ranks to selected information based on its importance or relevance.

[0072] A "text" is a collection of sentences used to convey information or messages in text format.

[0073] "Multimedia content" refers to informational representations that combine different media such as text, images, audio, and video.

[0074] "Time management means" refers to functions and technologies for adjusting generated content to fit a time range specified by the user.

[0075] A "machine learning mechanism" is an algorithm or system that learns from past data and experience to improve the accuracy of information selection and delivery.

[0076] This invention is a system that efficiently provides information based on user interests. The system operates primarily through interaction between a server, a terminal, and the user. Specific embodiments of this system are described below.

[0077] The server receives news genres and desired viewing times entered by the user via their terminal, and uses this information to generate and store the user's profile information. This profile information is used to filter data according to the user's interests.

[0078] The server uses API access and web scraping techniques to collect the latest news data from multiple sources, including news delivery services and publicly available databases. The collected data is then categorized into genres such as "health" and "sports" using machine learning.

[0079] The terminal is responsible for delivering optimized content from the server to the user. The content length is adjusted to fit the user's desired time slot and delivered to the user in a viewable state. Users can efficiently obtain news and information of interest according to their specified viewing time.

[0080] For example, if a user wants to watch 15 minutes of news on "health" and "sports" at 8 AM, the server will select relevant news, generate content, and deliver it through the device at the specified time. This allows users to quickly access the latest news tailored to their interests.

[0081] An example of a prompt message is: "Generate a 15-minute news content piece based on the following news genre and time slot. The genres are 'Health' and 'Sports', and the time slot is 8:00 AM daily."

[0082] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0083] Step 1:

[0084] The user enters the news genre and desired viewing time into the device. The device formats the input data and sends it to the server. The input data is processed into JSON format, which includes the keys "news genre" and "viewing time".

[0085] Step 2:

[0086] The server generates user profile information from the data it receives. Based on the input data, the server analyzes the user's interests and updates or registers new profiles in the profile database. This profile information includes past viewing history and preferred genres.

[0087] Step 3:

[0088] The server collects news data from multiple sources. This is done using APIs and web scraping, and data is retrieved in real time. The input is the URL or API key of the configured information source, and the output is raw news data.

[0089] Step 4:

[0090] The server classifies and indexes the collected news data by category. Machine learning techniques are used to analyze the news content and classify it into categories such as "health" and "sports." The input is raw news data, and the output is a classified dataset.

[0091] Step 5:

[0092] The server selects and prioritizes appropriate news based on the user profile. The algorithm evaluates the relevance between the profile and categories and generates a list of selected news as output.

[0093] Step 6:

[0094] Based on the selected news, the server uses a generative AI model to create text and multimedia content. The input is a list of selected news articles, and the output is the generated content, which may include speech synthesis or video clips.

[0095] Step 7:

[0096] The server edits the generated content to fit the user-specified time frame. It adjusts the length and order of the content to suit the viewing time. The input is the generated content, and the output is the edited content.

[0097] Step 8:

[0098] The terminal receives the edited content and provides it to the user's device. The user can view it via streaming or download, with the input being the content data from the server and the output being the delivery to the user.

[0099] Step 9:

[0100] After a user views content, the device retrieves feedback and sends it to the server. This feedback includes ratings of satisfaction and relevance. The input is user feedback data, and the output is the registration of this feedback information to the server.

[0101] Step 10:

[0102] The server analyzes the feedback and updates the information selection algorithm. The feedback data is used to improve the selection accuracy in subsequent iterations and enhance overall system performance. The input is the feedback information, and the output is the updated selection algorithm.

[0103] (Application Example 1)

[0104] 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."

[0105] In modern society, users face the challenge of efficiently obtaining information relevant to their individual interests from a vast amount of news content. Furthermore, timely and flexible information provision is desirable for users to consume news at their own pace and according to their lifestyle.

[0106] 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.

[0107] In this invention, the server includes means for holding profile data for collecting information based on the user's interests, means for collecting data in real time from multiple information sources and indexing it based on a specific classification, means for filtering and prioritizing the collected data by referring to the stored profile data, means for creating text and multimedia content based on the filtered and prioritized data, means for distributing the generated content to the user's information processing device and converting it into audio format using speech synthesis technology, and means for receiving feedback from the user and improving the selection algorithm based on that feedback. This makes it possible for users to flexibly receive content that matches their interests as audio or video within a specified time frame.

[0108] "Profile data" refers to data that records a user's interests and preferences, and is used as a basis for information gathering.

[0109] "Information sources" refer to data providers who offer news and related information, and who provide the material necessary for indexing.

[0110] "Indexing" is the process of organizing collected data based on specific classifications to facilitate searching and filtering.

[0111] "Filtering" is the process of selecting highly relevant data from collected information based on profile data.

[0112] Prioritization is the process of determining the order in which filtered data is displayed or presented based on its importance and relevance.

[0113] "Text and multimedia content" refers to information in various forms, such as text, audio, and video, that is generated for the purpose of providing it to users.

[0114] An "information processing device" is an electronic device used to receive and play content, and generally refers to smartphones and computers.

[0115] "Speech synthesis technology" is a type of technology used to convert text data into a speech format.

[0116] "Feedback" refers to data on users' evaluations and impressions of the content provided, and is information that can be used to improve the system.

[0117] A "selection algorithm" is a computational method used to select the information that best suits the user's profile from the collected data.

[0118] To implement this invention, a server, a user terminal, and a network environment for communication between them are used. The server stores user profile data, collects data from multiple sources in real time, and indexes it based on specific classifications. Specifically, the server uses Python and Flask to build the backend logic and manage user profiles and collect news data.

[0119] The user's device has an application developed using React Native installed, which accepts user input and sends necessary data to the server. By using React Native, a user interface that can be comfortably operated on a smartphone is realized.

[0120] Furthermore, the server uses the Google® Cloud Text-to-Speech API to convert text data into speech based on filtered and prioritized data. This enables the generation of multimedia content in audio format, which is then temporarily stored in AWS® S3.

[0121] The distributed multimedia content utilizes speech synthesis technology to deliver audio content to the user's device within a specified time frame, either via streaming or download. This allows users to view news tailored to their interests and lifestyle.

[0122] For example, if a user specifies that they want to receive news in the "technology" and "health" categories every morning at 8:00 AM, the server will generate relevant content based on that request and deliver it at the specified time. Furthermore, user feedback after viewing the content is sent to the server, contributing to improvements in the selection algorithm.

[0123] As an example of a prompt, it's possible to provide input such as, "Please select a news genre, for example, politics, health, technology, etc. Please also specify your preferred delivery time. The AI ​​will customize and deliver news tailored to your preferences."

[0124] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0125] Step 1:

[0126] The user uses a device to input news genres of interest and desired delivery times. The device sends the user input data to the server. The server receives the news genres and desired times as input and records them as a user profile.

[0127] Step 2:

[0128] The server collects news data from multiple sources in real time based on the received user profile. The collected data is indexed based on the specified classification. This process retrieves RSS feeds from news feed URLs and filters their content by keywords.

[0129] Step 3:

[0130] The server filters indexed news data based on the user's profile and prioritizes it according to importance and relevance. The filtering and prioritization process refers to stored profile data to select articles related to specific genres.

[0131] Step 4:

[0132] The server uses filtered and prioritized news data to generate multimedia content in audio format from text. It uses the Google Cloud Text-to-Speech API to convert selected text articles into audio data. The generated audio data is stored in AWS S3.

[0133] Step 5:

[0134] At the specified delivery time, the server delivers the generated multimedia content to the device via streaming or download. The device then plays the received audio data and provides it to the user. In this step, the content delivery service is triggered by a time specified by the user.

[0135] Step 6:

[0136] After a user views content, the device sends feedback to the server. This feedback includes information about the user's satisfaction level and relevance of the news they viewed. The server analyzes this feedback and uses it to improve the algorithm. This process improves the generative AI model.

[0137] 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.

[0138] This invention is a system for providing personalized information tailored to a user's interests, concerns, and emotional state. The system operates with a server, a terminal, and an emotion engine working in conjunction. The user inputs their preferred news genres and desired viewing time via the terminal, which transmits this information to the server and collects data to analyze the user's emotional state.

[0139] The server creates a profile based on the information received from the user and stores it in a database. This profile includes not only the user's interests and relevant information, but also their emotional state analyzed by the emotion engine.

[0140] The server collects news data from multiple sources, analyzes it using natural language processing techniques, and classifies and indexes it by genre. The collected news data is filtered based on user profiles and then prioritized, taking into account the results of analysis by a sentiment engine.

[0141] For example, if a user is typically interested in "health" or "technology," they will be provided with selected news. However, if the emotion engine analyzes the user's current emotional state as "stressed," the server has the capability to prioritize delivering positive news or relaxation-related content.

[0142] The generated text and multimedia content are optimized by the server based on the user's emotional state. Text-to-speech technology and video editing software are used to create content that is easy for the user to view.

[0143] At a specified time, the device delivers content received from the server to the user via streaming or download. After viewing, the user enters feedback on the content into the device, which then sends this feedback to the server.

[0144] The server continuously improves its algorithms using feedback and analysis results from the sentiment engine. This process ensures that subsequent content deliveries are better tailored to the user's preferences and emotional state. In this way, the present invention makes it possible to provide users with a richer and more personalized news viewing experience.

[0145] The following describes the processing flow.

[0146] Step 1:

[0147] The user inputs news genres and desired viewing times through their device, which then sends this information to a server. The device also collects inputs to understand the user's emotional state (e.g., facial expressions and tone of voice).

[0148] Step 2:

[0149] The emotional data collected by the device is analyzed by an emotion engine, which evaluates the user's emotional state and sends the results to the server.

[0150] Step 3:

[0151] The server creates a user profile, which includes data about the user's interests, concerns, and emotional state. This profile is stored in a database and used for future processing.

[0152] Step 4:

[0153] The server collects news data from multiple sources. The collected data is classified using natural language processing techniques and indexed by related genre.

[0154] Step 5:

[0155] The server refers to user profiles and filters the collected news data. This filtering takes into account not only the user's interests but also the results of the sentiment engine's analysis.

[0156] Step 6:

[0157] Filtered news is prioritized on the server based on importance and relevance. Depending on the user's emotional state, news that evokes positive emotions may also be prioritized.

[0158] Step 7:

[0159] The server generates text and multimedia content based on prioritized news, utilizing speech synthesis technology and video editing software. The content is optimized for the user's emotional state.

[0160] Step 8:

[0161] The generated content is edited to fit the time frame specified by the user and sent from the server to the device. The device then makes the received content available for streaming or download to the user.

[0162] Step 9:

[0163] After viewing content on their device, users enter feedback such as their impressions and ratings. This feedback is sent from the device to the server.

[0164] Step 10:

[0165] The server uses feedback and analysis results from the sentiment engine to continuously improve news selection and content generation algorithms, and utilizes this information for future deliveries. This makes it possible to provide users with even more relevant content.

[0166] (Example 2)

[0167] 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".

[0168] While modern information distribution systems have achieved some success in providing content based on users' interests and preferences, there remain unresolved challenges in providing personalized information that takes into account users' emotional states. Furthermore, the lack of dynamic learning capabilities to continuously improve the accuracy and relevance of collected data makes it difficult to optimize the user experience.

[0169] 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.

[0170] In this invention, the server includes information storage means for recording data based on the user's interests and emotional state; means for collecting data in real time from multiple information sources and classifying and indexing it based on specific categories using natural language processing technology; and means for filtering and prioritizing the collected data by referring to the stored data records and the results of sentiment analysis. This enables the provision of personalized information according to the user's emotional state.

[0171] "Information storage means" refers to a means of recording data based on the user's interests and emotional state, and is a function that uses storage devices and databases to retain information.

[0172] "Natural language processing technology" refers to techniques for processing and analyzing human language using computers, and is a method used for data classification, analysis, and indexing.

[0173] A "filtering method" is a function that selects collected data based on specific criteria, and plays a role in extracting only the necessary information according to the user's profile and emotional state.

[0174] A "prioritization method" is a function that ranks filtered data based on importance and relevance, and is used to provide users with the most relevant information.

[0175] A "generative AI model" is an artificial intelligence model that learns from data and generates or predicts new data, and is used to improve algorithms.

[0176] A "machine learning structure" is a framework or system for learning patterns from data and using them to make predictions or classifications, with the aim of improving the accuracy and relevance of information gathering.

[0177] A "time adjustment mechanism" is a function that configures content to be viewable within a time frame specified by the user, and is used to control the timing of content delivery.

[0178] The system in this invention involves a server, a terminal, and an emotion analysis engine working together to provide personalized information based on the user's interests and emotional state.

[0179] The server stores data on user interests, desired viewing times, and emotional states received from users via their devices into a dedicated database. User information is analyzed by an emotion analysis engine, and the results are also stored as profile data. The server uses natural language processing (NLP) techniques to collect news data from multiple internet sources, classifying and indexing it into specific categories. This process utilizes software such as Python NLP libraries.

[0180] In the filtering and prioritization process, the server takes into account stored user profiles and emotional states to select the most relevant content from the collected information. The selected content is optimized for the user's emotional state and generated in an optimal visual and auditory format using speech synthesis technology (e.g., text-to-speech engine) and video editing software (e.g., video editing program).

[0181] The device provides optimized content from the server in streaming or download format, based on the specified viewing time. The user views the content and then enters feedback into the device. This feedback information is sent to the server, where a generative AI model uses it to improve the content delivery algorithm.

[0182] For example, if a user requests news in the "health" category and is experiencing stress, the system will prioritize providing relaxing health information and positive articles. An example of a prompt would be, "Please suggest news suitable for a user who is stressed," which asks the AI ​​model to suggest content that takes the user's emotional state into consideration.

[0183] In this way, the invention enables personalized news delivery based on emotional factors, providing users with a richer and more customized information experience.

[0184] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0185] Step 1:

[0186] The user uses a device to input their preferred news genres and desired viewing time. The device receives this information and collects emotional state data by sensing the user's speech and facial expressions. The input information includes news genres, desired viewing time, and emotional state data, and this data is sent to the next step.

[0187] Step 2:

[0188] The terminal sends the collected data to the server. The server stores the received data in a database and generates a profile using an information storage system. This profile includes the user's interests, preferred time, and emotional state. The profile information is output through data processing.

[0189] Step 3:

[0190] The server collects news data from multiple sources using an API. The input data is raw data obtained from each source. The server analyzes this data using natural language processing techniques and classifies and indexes it based on news genre. This process outputs genre-classified news data.

[0191] Step 4:

[0192] The server filters and prioritizes news data based on the user's profile and sentiment analysis results. At this stage, profile data and categorized news data are input. The filtering process selects the news content most relevant to the user.

[0193] Step 5:

[0194] The server optimizes prioritized news content based on the user's emotional state. Speech synthesis technology and video editing software are used to convert the content to speech and edit its visuals. This step outputs optimized text and multimedia content.

[0195] Step 6:

[0196] The device delivers content received from the server to the user via streaming or download at a specified time. Optimized content is used as input data, and the delivery result to the user is output.

[0197] Step 7:

[0198] After viewing the content, users enter feedback about it into their device. This feedback includes information about their satisfaction level and relevance of the content. This process generates feedback data.

[0199] Step 8:

[0200] The device sends the collected feedback to the server. The server uses a generative AI model to analyze the feedback and sentiment analysis results, and uses this information to improve the content delivery algorithm. In this step, the feedback data becomes the input, and the improved algorithm is output.

[0201] (Application Example 2)

[0202] 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".

[0203] In today's information society, users are often overwhelmed by the sheer volume of content provided by various sources. Furthermore, the lack of personalized information tailored to users' interests and emotional states leads to a problem where information is not properly utilized. There is also a need for methods to effectively leverage user feedback and emotional data to optimize future information delivery.

[0204] 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.

[0205] In this invention, the server includes means for storing profile data for collecting information based on the user's interests and emotional state; means for collecting data in real time from multiple sources and indexing it based on specific classifications using natural language processing technology; and means for filtering and prioritizing the collected data by referring to the stored profile data and the emotional state analyzed by the emotion analysis engine. This makes it possible to provide information optimized for the user's interests and emotions.

[0206] "Profile data" refers to data stored to collect information based on the user's interests and emotional state.

[0207] An "emotion analysis engine" is a system or program that analyzes a user's emotional state and reflects the analysis results in profile data.

[0208] "Natural language processing technology" is a technique for processing and analyzing human language using computers, and is a means of indexing information based on specific classifications.

[0209] "Filtering" is the process of selecting collected data based on the user's profile data and removing unnecessary information.

[0210] Prioritization is the process of evaluating the importance of information based on the user's interests and emotional state, and determining the order in which that information is presented.

[0211] "Speech synthesis technology" is a technology for converting text information into speech, and is a means of conveying the generated content to users.

[0212] "Video editing methods" refer to the technologies and tools used to process and edit multimedia content into a format that is easy for users to view.

[0213] "Streaming" is a technology that delivers generated content in real time, allowing users to watch it while downloading the data.

[0214] "Feedback" refers to the process by which users return their evaluations and opinions about content to the system, and this information is used to improve future information provision.

[0215] A "machine learning model" is an algorithm or technique used to improve the accuracy and relevance of information collection based on profile data and feedback data.

[0216] The system for realizing this invention mainly consists of a server, a terminal, and an emotion analysis engine.

[0217] The server stores profile data to collect information based on the user's interests and emotional state. The device processes the user's preferred genres and viewing time settings and sends this data to the server. During this process, the device collects the user's emotional data in real time using an emotion analysis engine.

[0218] The server collects data in real time from multiple sources and uses natural language processing techniques to categorize and index that information. The technologies used include natural language processing and speech synthesis engines. The collected data is filtered and prioritized based on stored profile data and emotional states analyzed by an emotion analysis engine. Following this process, text and multimedia content optimized to the user's emotions is generated.

[0219] The generated content is delivered to the device via streaming or download at a specified time. For example, if a user asks, "What news content can I find relaxing?", the system will prioritize delivering content that reduces stress. This allows for information delivery optimized to the user's state of mind.

[0220] Furthermore, user feedback is sent to the server via the device, and the algorithm is improved using machine learning models. This increases the accuracy and relevance of the information, making future information provision more appropriate.

[0221] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0222] Step 1:

[0223] The user uses a device to input their preferred genres of interest and desired viewing time. The device collects the user's current emotional data through sensors such as the camera and microphone. The input includes the user's genres of interest and emotional data, which is sent to the server. As output, this information is added to a profile database.

[0224] Step 2:

[0225] The server collects relevant news data from multiple sources based on the received interest genres and sentiment data. Natural language processing techniques are used to classify and index the data by theme. The input is news data obtained from numerous sources, and the output is classified news data.

[0226] Step 3:

[0227] The server filters and prioritizes collected news data based on profile data and sentiment analysis results. Inputs are stored profile data and sentiment states, while output prioritizes news with a relaxing effect and news from genres preferred by the user.

[0228] Step 4:

[0229] Using speech synthesis technology and video editing techniques, prioritized news data is generated as text and multimedia content. The input is filtered and prioritized news data, and the output is visually and aurally user-friendly content.

[0230] Step 5:

[0231] Based on the specified viewing time, the server delivers the generated content to the device via streaming or download. Here, the content is provided at the time reserved by the user. The input is the generated content and schedule information, and the output is the content available for viewing on the device.

[0232] Step 6:

[0233] Users enter feedback on their devices after viewing. This feedback is sent to the server. The input consists of user ratings and opinions, and the output is feedback data that helps in the continuous improvement of the algorithm.

[0234] Step 7:

[0235] The server updates its algorithm using a machine learning model based on feedback and sentiment data. This ensures that subsequent requests are better tailored to the user's preferences and emotional state. The input is feedback data and emotional state, and the output is an improved information delivery algorithm.

[0236] 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.

[0237] 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.

[0238] 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.

[0239] [Second Embodiment]

[0240] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0241] 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.

[0242] 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).

[0243] 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.

[0244] 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.

[0245] 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).

[0246] 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.

[0247] 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.

[0248] 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.

[0249] 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.

[0250] 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.

[0251] 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".

[0252] This invention is a system that enables users to obtain information based on their individual interests and preferences. The system operates primarily through interaction between a server, a terminal, and the user. In one example of this embodiment, the user uses a terminal to input their preferred news genres and desired viewing time.

[0253] The terminal sends user input to the server, which then creates a user profile based on this input. The server periodically collects news data from multiple sources, classifies the collected data by genre, and indexes it.

[0254] Based on the user's profile, the server selects relevant news articles and prioritizes them based on their importance and relevance. This makes it possible to select specific news articles that meet the user's needs.

[0255] The server then generates text and multimedia content based on the selected news. This generation step simultaneously utilizes speech synthesis technology and video clips to create visually and aurally effective content.

[0256] The generated content is edited to a length suitable for the time frame specified by the user. This allows users to efficiently obtain summaries of news they are interested in at their desired time. During delivery, the device provides the content to the user in either streaming or download format.

[0257] After a user views content, their device sends feedback to the server. This feedback evaluates how much the user enjoyed the news and whether it was relevant. The server analyzes this feedback and uses it as data to improve its information selection algorithm.

[0258] For example, if a user requests to watch "health" and "sports" news for 15 minutes at 8 AM, the server will collect relevant news articles based on this request, generate content, and deliver it at the specified time. This allows users to efficiently obtain the latest news. Through continuous use, this system will continue to evolve to better suit user preferences.

[0259] The following describes the processing flow.

[0260] Step 1:

[0261] The user enters their preferred news genres and viewing times via their device. The device then sends this information to the server.

[0262] Step 2:

[0263] The server creates user profiles based on information received from users and stores them in a database. This makes it possible to manage the interests and needs of individual users.

[0264] Step 3:

[0265] The server periodically collects news data from multiple sources. This news data is obtained via APIs and web scraping, formatted, and then stored in a temporary data store.

[0266] Step 4:

[0267] The server analyzes the collected news data using natural language processing technology, classifying and indexing it based on pre-defined genres. This enables rapid searching and access.

[0268] Step 5:

[0269] The server references the user profile and filters news by genre. Furthermore, it prioritizes news based on its importance and recency.

[0270] Step 6:

[0271] The server uses prioritized news to generate text and multimedia content using text synthesis and video editing software. This creates content in a format that is easy for users to view.

[0272] Step 7:

[0273] The generated content is edited to fit the time frame specified by the user and prepared for distribution. The server saves the content to system storage.

[0274] Step 8:

[0275] When the device reaches the specified time, it retrieves video content from the server and provides it to the user in streaming or download format.

[0276] Step 9:

[0277] Users view content using their devices and then provide feedback on what they have been given.

[0278] Step 10:

[0279] The device sends the collected feedback information to the server. The server uses this feedback to improve the news selection algorithm and incorporate it into future content delivery.

[0280] (Example 1)

[0281] 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."

[0282] In today's information society, it is difficult for users to quickly and efficiently gather information relevant to their interests from a vast amount of data. Furthermore, filtering and selecting necessary information from this vast amount of data requires considerable time and effort. In addition, as users' interests change, there are few information provision systems that can adapt to these changes, resulting in challenges in providing effective information.

[0283] 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.

[0284] In this invention, the server includes means for generating and storing profile information based on the interests of users, means for obtaining the latest data from multiple information sources, classifying and organizing it into different categories, and means for screening the obtained data based on the stored profile information and ranking it according to importance. This makes it possible to efficiently and quickly provide the necessary information while adapting to the changing interests of users.

[0285] "Profile information" is a collection of data generated and stored based on users' interests, concerns, viewing history, etc.

[0286] "Information source" is an external repository or system that provides news, articles, and other knowledge.

[0287] "Category" is a framework for organizing and classifying the collected information by genre or type.

[0288] "Screening" is the act of selecting the information highly relevant to the user's profile from the collected information.

[0289] "Ranking" refers to ranking the selected information according to importance or relevance.

[0290] "Article" is a collection of sentences for conveying information or messages in text form.

[0291] "Composite media content" is an information representation that combines different media such as text, images, audio, and video.

[0292] "Time management means" is a function or technology for adjusting the generated content to fit within the time range specified by the user.

[0293] "Machine learning mechanism" is an algorithm or system that learns from past data and experience to improve the accuracy of information selection and provision.

[0294] This invention is a system that efficiently provides information based on user interests. The system operates primarily through interaction between a server, a terminal, and the user. Specific embodiments of this system are described below.

[0295] The server receives news genres and desired viewing times entered by the user via their terminal, and uses this information to generate and store the user's profile information. This profile information is used to filter data according to the user's interests.

[0296] The server uses API access and web scraping techniques to collect the latest news data from multiple sources, including news delivery services and publicly available databases. The collected data is then categorized into genres such as "health" and "sports" using machine learning.

[0297] The terminal is responsible for delivering optimized content from the server to the user. The content length is adjusted to fit the user's desired time slot and delivered to the user in a viewable state. Users can efficiently obtain news and information of interest according to their specified viewing time.

[0298] For example, if a user wants to watch 15 minutes of news on "health" and "sports" at 8 AM, the server will select relevant news, generate content, and deliver it through the device at the specified time. This allows users to quickly access the latest news tailored to their interests.

[0299] An example of a prompt message is: "Generate a 15-minute news content piece based on the following news genre and time slot. The genres are 'Health' and 'Sports', and the time slot is 8:00 AM daily."

[0300] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0301] Step 1:

[0302] The user inputs the news genre and the desired viewing time into the terminal. The terminal formats the input data and sends it to the server. The input data is processed into JSON format containing keys such as "news genre" and "viewing time".

[0303] Step 2:

[0304] The server generates the user's profile information from the received data. Based on the input data, the server analyzes the user's interests and updates or newly registers them in the profile database. The profile information also includes past viewing history and preferred genres.

[0305] Step 3:

[0306] The server collects news data from multiple information sources. API and web scraping are used for this, and real-time data acquisition is performed. The input is the URL or API key of the set information source, and the output is raw news data.

[0307] Step 4:

[0308] The server classifies and indexes the collected news data by category. Using machine learning techniques, the content of the news is analyzed and classified into "health", "sports", etc. The input is raw news data, and the output is a classified dataset.

[0309] Step 5:

[0310] The server selects appropriate news based on the user profile and assigns priorities. The algorithm evaluates the relevance between the profile and the category and generates a list of selected news as output.

[0311] Step 6:

[0312] Based on the selected news, the server uses a generative AI model to create text and multimedia content. The input is a list of selected news articles, and the output is the generated content, which may include speech synthesis or video clips.

[0313] Step 7:

[0314] The server edits the generated content to fit the user-specified time frame. It adjusts the length and order of the content to suit the viewing time. The input is the generated content, and the output is the edited content.

[0315] Step 8:

[0316] The terminal receives the edited content and provides it to the user's device. The user can view it via streaming or download, with the input being the content data from the server and the output being the delivery to the user.

[0317] Step 9:

[0318] After a user views content, the device retrieves feedback and sends it to the server. This feedback includes ratings of satisfaction and relevance. The input is user feedback data, and the output is the registration of this feedback information to the server.

[0319] Step 10:

[0320] The server analyzes the feedback and updates the information selection algorithm. The feedback data is used to improve the selection accuracy in subsequent iterations and enhance overall system performance. The input is the feedback information, and the output is the updated selection algorithm.

[0321] (Application Example 1)

[0322] 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."

[0323] In modern society, users face the challenge of efficiently obtaining information relevant to their individual interests from a vast amount of news content. Furthermore, timely and flexible information provision is desirable for users to consume news at their own pace and according to their lifestyle.

[0324] 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.

[0325] In this invention, the server includes means for holding profile data for collecting information based on the user's interests, means for collecting data in real time from multiple information sources and indexing it based on a specific classification, means for filtering and prioritizing the collected data by referring to the stored profile data, means for creating text and multimedia content based on the filtered and prioritized data, means for distributing the generated content to the user's information processing device and converting it into audio format using speech synthesis technology, and means for receiving feedback from the user and improving the selection algorithm based on that feedback. This makes it possible for users to flexibly receive content that matches their interests as audio or video within a specified time frame.

[0326] "Profile data" refers to data that records a user's interests and preferences, and is used as a basis for information gathering.

[0327] "Information sources" refer to data providers who offer news and related information, and who provide the material necessary for indexing.

[0328] "Indexing" is the process of organizing collected data based on specific classifications to facilitate searching and filtering.

[0329] "Filtering" is the process of selecting highly relevant data from collected information based on profile data.

[0330] Prioritization is the process of determining the order in which filtered data is displayed or presented based on its importance and relevance.

[0331] "Text and multimedia content" refers to information in various forms, such as text, audio, and video, that is generated for the purpose of providing it to users.

[0332] An "information processing device" is an electronic device used to receive and play content, and generally refers to smartphones and computers.

[0333] "Speech synthesis technology" is a type of technology used to convert text data into a speech format.

[0334] "Feedback" refers to data on users' evaluations and impressions of the content provided, and is information that can be used to improve the system.

[0335] A "selection algorithm" is a computational method used to select the information that best suits the user's profile from the collected data.

[0336] To implement this invention, a server, a user terminal, and a network environment for communication between them are used. The server stores user profile data, collects data from multiple sources in real time, and indexes it based on specific classifications. Specifically, the server uses Python and Flask to build the backend logic and manage user profiles and collect news data.

[0337] The user's device has an application developed using React Native installed, which accepts user input and sends necessary data to the server. By using React Native, a user interface that can be comfortably operated on a smartphone is realized.

[0338] Furthermore, the server uses the Google Cloud Text-to-Speech API to convert text data into speech based on filtered and prioritized data. This enables the generation of multimedia content in audio format, which is then temporarily stored in AWS S3.

[0339] The distributed multimedia content utilizes speech synthesis technology to deliver audio content to the user's device within a specified time frame, either via streaming or download. This allows users to view news tailored to their interests and lifestyle.

[0340] For example, if a user specifies that they want to receive news in the "technology" and "health" categories every morning at 8:00 AM, the server will generate relevant content based on that request and deliver it at the specified time. Furthermore, user feedback after viewing the content is sent to the server, contributing to improvements in the selection algorithm.

[0341] As an example of a prompt, it's possible to provide input such as, "Please select a news genre, for example, politics, health, technology, etc. Please also specify your preferred delivery time. The AI ​​will customize and deliver news tailored to your preferences."

[0342] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0343] Step 1:

[0344] The user uses a device to input news genres of interest and desired delivery times. The device sends the user input data to the server. The server receives the news genres and desired times as input and records them as a user profile.

[0345] Step 2:

[0346] The server collects news data from multiple sources in real time based on the received user profile. The collected data is indexed based on the specified classification. This process retrieves RSS feeds from news feed URLs and filters their content by keywords.

[0347] Step 3:

[0348] The server filters indexed news data based on the user's profile and prioritizes it according to importance and relevance. The filtering and prioritization process refers to stored profile data to select articles related to specific genres.

[0349] Step 4:

[0350] The server uses filtered and prioritized news data to generate multimedia content in audio format from text. It uses the Google Cloud Text-to-Speech API to convert selected text articles into audio data. The generated audio data is stored in AWS S3.

[0351] Step 5:

[0352] At the specified delivery time, the server delivers the generated multimedia content to the device via streaming or download. The device then plays the received audio data and provides it to the user. In this step, the content delivery service is triggered by a time specified by the user.

[0353] Step 6:

[0354] After a user views content, the device sends feedback to the server. This feedback includes information about the user's satisfaction level and relevance of the news they viewed. The server analyzes this feedback and uses it to improve the algorithm. This process improves the generative AI model.

[0355] 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.

[0356] This invention is a system for providing personalized information tailored to a user's interests, concerns, and emotional state. The system operates with a server, a terminal, and an emotion engine working in conjunction. The user inputs their preferred news genres and desired viewing time via the terminal, which transmits this information to the server and collects data to analyze the user's emotional state.

[0357] The server creates a profile based on the information received from the user and stores it in a database. This profile includes not only the user's interests and relevant information, but also their emotional state analyzed by the emotion engine.

[0358] The server collects news data from multiple sources, analyzes it using natural language processing techniques, and classifies and indexes it by genre. The collected news data is filtered based on user profiles and then prioritized, taking into account the results of analysis by a sentiment engine.

[0359] For example, if a user is typically interested in "health" or "technology," they will be provided with selected news. However, if the emotion engine analyzes the user's current emotional state as "stressed," the server has the capability to prioritize delivering positive news or relaxation-related content.

[0360] The generated text and multimedia content are optimized by the server based on the user's emotional state. Text-to-speech technology and video editing software are used to create content that is easy for the user to view.

[0361] At a specified time, the device delivers content received from the server to the user via streaming or download. After viewing, the user enters feedback on the content into the device, which then sends this feedback to the server.

[0362] The server continuously improves its algorithms using feedback and analysis results from the sentiment engine. This process ensures that subsequent content deliveries are better tailored to the user's preferences and emotional state. In this way, the present invention makes it possible to provide users with a richer and more personalized news viewing experience.

[0363] The following describes the processing flow.

[0364] Step 1:

[0365] The user inputs news genres and desired viewing times through their device, which then sends this information to a server. The device also collects inputs to understand the user's emotional state (e.g., facial expressions and tone of voice).

[0366] Step 2:

[0367] The emotional data collected by the device is analyzed by an emotion engine, which evaluates the user's emotional state and sends the results to the server.

[0368] Step 3:

[0369] The server creates a user profile, which includes data about the user's interests, concerns, and emotional state. This profile is stored in a database and used for future processing.

[0370] Step 4:

[0371] The server collects news data from multiple sources. The collected data is classified using natural language processing techniques and indexed by related genre.

[0372] Step 5:

[0373] The server refers to user profiles and filters the collected news data. This filtering takes into account not only the user's interests but also the results of the sentiment engine's analysis.

[0374] Step 6:

[0375] Filtered news is prioritized on the server based on importance and relevance. Depending on the user's emotional state, news that evokes positive emotions may also be prioritized.

[0376] Step 7:

[0377] The server generates text and multimedia content based on prioritized news, utilizing speech synthesis technology and video editing software. The content is optimized for the user's emotional state.

[0378] Step 8:

[0379] The generated content is edited to fit the time frame specified by the user and sent from the server to the device. The device then makes the received content available for streaming or download to the user.

[0380] Step 9:

[0381] After viewing content on their device, users enter feedback such as their impressions and ratings. This feedback is sent from the device to the server.

[0382] Step 10:

[0383] The server uses feedback and analysis results from the sentiment engine to continuously improve news selection and content generation algorithms, and utilizes this information for future deliveries. This makes it possible to provide users with even more relevant content.

[0384] (Example 2)

[0385] 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".

[0386] While modern information distribution systems have achieved some success in providing content based on users' interests and preferences, there remain unresolved challenges in providing personalized information that takes into account users' emotional states. Furthermore, the lack of dynamic learning capabilities to continuously improve the accuracy and relevance of collected data makes it difficult to optimize the user experience.

[0387] 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.

[0388] In this invention, the server includes information storage means for recording data based on the user's interests and emotional state; means for collecting data in real time from multiple information sources and classifying and indexing it based on specific categories using natural language processing technology; and means for filtering and prioritizing the collected data by referring to the stored data records and the results of sentiment analysis. This enables the provision of personalized information according to the user's emotional state.

[0389] "Information storage means" refers to a means of recording data based on the user's interests and emotional state, and is a function that uses storage devices and databases to retain information.

[0390] "Natural language processing technology" refers to techniques for processing and analyzing human language using computers, and is a method used for data classification, analysis, and indexing.

[0391] A "filtering method" is a function that selects collected data based on specific criteria, and plays a role in extracting only the necessary information according to the user's profile and emotional state.

[0392] A "prioritization method" is a function that ranks filtered data based on importance and relevance, and is used to provide users with the most relevant information.

[0393] A "generative AI model" is an artificial intelligence model that learns from data and generates or predicts new data, and is used to improve algorithms.

[0394] A "machine learning structure" is a framework or system for learning patterns from data and using them to make predictions or classifications, with the aim of improving the accuracy and relevance of information gathering.

[0395] A "time adjustment mechanism" is a function that configures content to be viewable within a time frame specified by the user, and is used to control the timing of content delivery.

[0396] The system in this invention involves a server, a terminal, and an emotion analysis engine working together to provide personalized information based on the user's interests and emotional state.

[0397] The server stores data on user interests, desired viewing times, and emotional states received from users via their devices into a dedicated database. User information is analyzed by an emotion analysis engine, and the results are also stored as profile data. The server uses natural language processing (NLP) techniques to collect news data from multiple internet sources, classifying and indexing it into specific categories. This process utilizes software such as Python NLP libraries.

[0398] In the filtering and prioritization process, the server takes into account stored user profiles and emotional states to select the most relevant content from the collected information. The selected content is optimized for the user's emotional state and generated in an optimal visual and auditory format using speech synthesis technology (e.g., text-to-speech engine) and video editing software (e.g., video editing program).

[0399] The device provides optimized content from the server in streaming or download format, based on the specified viewing time. The user views the content and then enters feedback into the device. This feedback information is sent to the server, where a generative AI model uses it to improve the content delivery algorithm.

[0400] For example, if a user requests news in the "health" category and is experiencing stress, the system will prioritize providing relaxing health information and positive articles. An example of a prompt would be, "Please suggest news suitable for a user who is stressed," which asks the AI ​​model to suggest content that takes the user's emotional state into consideration.

[0401] In this way, the invention enables personalized news delivery based on emotional factors, providing users with a richer and more customized information experience.

[0402] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0403] Step 1:

[0404] The user uses a device to input their preferred news genres and desired viewing time. The device receives this information and collects emotional state data by sensing the user's speech and facial expressions. The input information includes news genres, desired viewing time, and emotional state data, and this data is sent to the next step.

[0405] Step 2:

[0406] The terminal sends the collected data to the server. The server stores the received data in a database and generates a profile using an information storage system. This profile includes the user's interests, preferred time, and emotional state. The profile information is output through data processing.

[0407] Step 3:

[0408] The server collects news data from multiple sources using an API. The input data is raw data obtained from each source. The server analyzes this data using natural language processing techniques and classifies and indexes it based on news genre. This process outputs genre-classified news data.

[0409] Step 4:

[0410] The server filters and prioritizes news data based on the user's profile and sentiment analysis results. At this stage, profile data and categorized news data are input. The filtering process selects the news content most relevant to the user.

[0411] Step 5:

[0412] The server optimizes prioritized news content based on the user's emotional state. Speech synthesis technology and video editing software are used to convert the content to speech and edit its visuals. This step outputs optimized text and multimedia content.

[0413] Step 6:

[0414] The device delivers content received from the server to the user via streaming or download at a specified time. Optimized content is used as input data, and the delivery result to the user is output.

[0415] Step 7:

[0416] After viewing the content, users enter feedback about it into their device. This feedback includes information about their satisfaction level and relevance of the content. This process generates feedback data.

[0417] Step 8:

[0418] The device sends the collected feedback to the server. The server uses a generative AI model to analyze the feedback and sentiment analysis results, and uses this information to improve the content delivery algorithm. In this step, the feedback data becomes the input, and the improved algorithm is output.

[0419] (Application Example 2)

[0420] 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."

[0421] In today's information society, users are often overwhelmed by the sheer volume of content provided by various sources. Furthermore, the lack of personalized information tailored to users' interests and emotional states leads to a problem where information is not properly utilized. There is also a need for methods to effectively leverage user feedback and emotional data to optimize future information delivery.

[0422] 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.

[0423] In this invention, the server includes means for storing profile data for collecting information based on the user's interests and emotional state; means for collecting data in real time from multiple sources and indexing it based on specific classifications using natural language processing technology; and means for filtering and prioritizing the collected data by referring to the stored profile data and the emotional state analyzed by the emotion analysis engine. This makes it possible to provide information optimized for the user's interests and emotions.

[0424] "Profile data" refers to data stored to collect information based on the user's interests and emotional state.

[0425] An "emotion analysis engine" is a system or program that analyzes a user's emotional state and reflects the analysis results in profile data.

[0426] "Natural language processing technology" is a technique for processing and analyzing human language using computers, and is a means of indexing information based on specific classifications.

[0427] "Filtering" is the process of selecting collected data based on the user's profile data and removing unnecessary information.

[0428] Prioritization is the process of evaluating the importance of information based on the user's interests and emotional state, and determining the order in which that information is presented.

[0429] "Speech synthesis technology" is a technology for converting text information into speech, and is a means of conveying the generated content to users.

[0430] "Video editing methods" refer to the technologies and tools used to process and edit multimedia content into a format that is easy for users to view.

[0431] "Streaming" is a technology that delivers generated content in real time, allowing users to watch it while downloading the data.

[0432] "Feedback" refers to the process by which users return their evaluations and opinions about content to the system, and this information is used to improve future information provision.

[0433] A "machine learning model" is an algorithm or technique used to improve the accuracy and relevance of information collection based on profile data and feedback data.

[0434] The system for realizing this invention mainly consists of a server, a terminal, and an emotion analysis engine.

[0435] The server stores profile data to collect information based on the user's interests and emotional state. The device processes the user's preferred genres and viewing time settings and sends this data to the server. During this process, the device collects the user's emotional data in real time using an emotion analysis engine.

[0436] The server collects data in real time from multiple sources and uses natural language processing techniques to categorize and index that information. The technologies used include natural language processing and speech synthesis engines. The collected data is filtered and prioritized based on stored profile data and emotional states analyzed by an emotion analysis engine. Following this process, text and multimedia content optimized to the user's emotions is generated.

[0437] The generated content is delivered to the device via streaming or download at a specified time. For example, if a user asks, "What news content can I find relaxing?", the system will prioritize delivering content that reduces stress. This allows for information delivery optimized to the user's state of mind.

[0438] Furthermore, user feedback is sent to the server via the device, and the algorithm is improved using machine learning models. This increases the accuracy and relevance of the information, making future information provision more appropriate.

[0439] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0440] Step 1:

[0441] The user uses a device to input their preferred genres of interest and desired viewing time. The device collects the user's current emotional data through sensors such as the camera and microphone. The input includes the user's genres of interest and emotional data, which is sent to the server. As output, this information is added to a profile database.

[0442] Step 2:

[0443] The server collects relevant news data from multiple sources based on the received interest genres and sentiment data. Natural language processing techniques are used to classify and index the data by theme. The input is news data obtained from numerous sources, and the output is classified news data.

[0444] Step 3:

[0445] The server filters and prioritizes collected news data based on profile data and sentiment analysis results. Inputs are stored profile data and sentiment states, while output prioritizes news with a relaxing effect and news from genres preferred by the user.

[0446] Step 4:

[0447] Using speech synthesis technology and video editing techniques, prioritized news data is generated as text and multimedia content. The input is filtered and prioritized news data, and the output is visually and aurally user-friendly content.

[0448] Step 5:

[0449] Based on the specified viewing time, the server delivers the generated content to the device via streaming or download. Here, the content is provided at the time reserved by the user. The input is the generated content and schedule information, and the output is the content available for viewing on the device.

[0450] Step 6:

[0451] Users enter feedback on their devices after viewing. This feedback is sent to the server. The input consists of user ratings and opinions, and the output is feedback data that helps in the continuous improvement of the algorithm.

[0452] Step 7:

[0453] The server updates its algorithm using a machine learning model based on feedback and sentiment data. This ensures that subsequent requests are better tailored to the user's preferences and emotional state. The input is feedback data and emotional state, and the output is an improved information delivery algorithm.

[0454] 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.

[0455] 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.

[0456] 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.

[0457] [Third Embodiment]

[0458] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0459] 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.

[0460] 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).

[0461] 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.

[0462] 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.

[0463] 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).

[0464] 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.

[0465] 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.

[0466] 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.

[0467] 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.

[0468] 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.

[0469] 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".

[0470] This invention is a system that enables users to obtain information based on their individual interests and preferences. The system operates primarily through interaction between a server, a terminal, and the user. In one example of this embodiment, the user uses a terminal to input their preferred news genres and desired viewing time.

[0471] The terminal sends user input to the server, which then creates a user profile based on this input. The server periodically collects news data from multiple sources, classifies the collected data by genre, and indexes it.

[0472] Based on the user's profile, the server selects relevant news articles and prioritizes them based on their importance and relevance. This makes it possible to select specific news articles that meet the user's needs.

[0473] The server then generates text and multimedia content based on the selected news. This generation step simultaneously utilizes speech synthesis technology and video clips to create visually and aurally effective content.

[0474] The generated content is edited to a length suitable for the time frame specified by the user. This allows users to efficiently obtain summaries of news they are interested in at their desired time. During delivery, the device provides the content to the user in either streaming or download format.

[0475] After a user views content, their device sends feedback to the server. This feedback evaluates how much the user enjoyed the news and whether it was relevant. The server analyzes this feedback and uses it as data to improve its information selection algorithm.

[0476] For example, if a user requests to watch "health" and "sports" news for 15 minutes at 8 AM, the server will collect relevant news articles based on this request, generate content, and deliver it at the specified time. This allows users to efficiently obtain the latest news. Through continuous use, this system will continue to evolve to better suit user preferences.

[0477] The following describes the processing flow.

[0478] Step 1:

[0479] The user enters their preferred news genres and viewing times via their device. The device then sends this information to the server.

[0480] Step 2:

[0481] The server creates user profiles based on information received from users and stores them in a database. This makes it possible to manage the interests and needs of individual users.

[0482] Step 3:

[0483] The server periodically collects news data from multiple sources. This news data is obtained via APIs and web scraping, formatted, and then stored in a temporary data store.

[0484] Step 4:

[0485] The server analyzes the collected news data using natural language processing technology, classifying and indexing it based on pre-defined genres. This enables rapid searching and access.

[0486] Step 5:

[0487] The server references the user profile and filters news by genre. Furthermore, it prioritizes news based on its importance and recency.

[0488] Step 6:

[0489] The server uses prioritized news to generate text and multimedia content using text synthesis and video editing software. This creates content in a format that is easy for users to view.

[0490] Step 7:

[0491] The generated content is edited to fit the time frame specified by the user and prepared for distribution. The server saves the content to system storage.

[0492] Step 8:

[0493] When the device reaches the specified time, it retrieves video content from the server and provides it to the user in streaming or download format.

[0494] Step 9:

[0495] Users view content using their devices and then provide feedback on what they have been given.

[0496] Step 10:

[0497] The device sends the collected feedback information to the server. The server uses this feedback to improve the news selection algorithm and incorporate it into future content delivery.

[0498] (Example 1)

[0499] 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."

[0500] In today's information society, it is difficult for users to quickly and efficiently gather information relevant to their interests from a vast amount of data. Furthermore, filtering and selecting necessary information from this vast amount of data requires considerable time and effort. In addition, as users' interests change, there are few information provision systems that can adapt to these changes, resulting in challenges in providing effective information.

[0501] 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.

[0502] In this invention, the server includes means for generating and storing profile information based on the user's interests, means for acquiring the latest data from multiple sources and classifying and organizing it into different categories, and means for selecting the acquired data based on the accumulated profile information and ordering it according to its importance. This makes it possible to efficiently and quickly provide necessary information while adapting to the user's changing interests.

[0503] "Profile information" refers to a collection of data generated and stored based on a user's interests, preferences, viewing history, and other factors.

[0504] A "source of information" refers to an external repository or system that provides news, articles, and other knowledge.

[0505] A "category" is a framework for organizing and classifying collected information by genre or type.

[0506] "Selection" refers to the process of selecting information from the collected data that is highly relevant to the user's profile.

[0507] "Ordering" refers to the process of assigning ranks to selected information based on its importance or relevance.

[0508] A "text" is a collection of sentences used to convey information or messages in text format.

[0509] "Multimedia content" refers to informational representations that combine different media such as text, images, audio, and video.

[0510] "Time management means" refers to functions and technologies for adjusting generated content to fit a time range specified by the user.

[0511] A "machine learning mechanism" is an algorithm or system that learns from past data and experience to improve the accuracy of information selection and delivery.

[0512] This invention is a system that efficiently provides information based on user interests. The system operates primarily through interaction between a server, a terminal, and the user. Specific embodiments of this system are described below.

[0513] The server receives news genres and desired viewing times entered by the user via their terminal, and uses this information to generate and store the user's profile information. This profile information is used to filter data according to the user's interests.

[0514] The server uses API access and web scraping techniques to collect the latest news data from multiple sources, including news delivery services and publicly available databases. The collected data is then categorized into genres such as "health" and "sports" using machine learning.

[0515] The terminal is responsible for delivering optimized content from the server to the user. The content length is adjusted to fit the user's desired time slot and delivered to the user in a viewable state. Users can efficiently obtain news and information of interest according to their specified viewing time.

[0516] For example, if a user wants to watch 15 minutes of news on "health" and "sports" at 8 AM, the server will select relevant news, generate content, and deliver it through the device at the specified time. This allows users to quickly access the latest news tailored to their interests.

[0517] An example of a prompt message is: "Generate a 15-minute news content piece based on the following news genre and time slot. The genres are 'Health' and 'Sports', and the time slot is 8:00 AM daily."

[0518] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0519] Step 1:

[0520] The user enters the news genre and desired viewing time into the device. The device formats the input data and sends it to the server. The input data is processed into JSON format, which includes the keys "news genre" and "viewing time".

[0521] Step 2:

[0522] The server generates user profile information from the data it receives. Based on the input data, the server analyzes the user's interests and updates or registers new profiles in the profile database. This profile information includes past viewing history and preferred genres.

[0523] Step 3:

[0524] The server collects news data from multiple sources. This is done using APIs and web scraping, and data is retrieved in real time. The input is the URL or API key of the configured information source, and the output is raw news data.

[0525] Step 4:

[0526] The server classifies and indexes the collected news data by category. Machine learning techniques are used to analyze the news content and classify it into categories such as "health" and "sports." The input is raw news data, and the output is a classified dataset.

[0527] Step 5:

[0528] The server selects and prioritizes appropriate news based on the user profile. The algorithm evaluates the relevance between the profile and categories and generates a list of selected news as output.

[0529] Step 6:

[0530] Based on the selected news, the server uses a generative AI model to create text and multimedia content. The input is a list of selected news articles, and the output is the generated content, which may include speech synthesis or video clips.

[0531] Step 7:

[0532] The server edits the generated content to fit the user-specified time frame. It adjusts the length and order of the content to suit the viewing time. The input is the generated content, and the output is the edited content.

[0533] Step 8:

[0534] The terminal receives the edited content and provides it to the user's device. The user can view it via streaming or download, with the input being the content data from the server and the output being the delivery to the user.

[0535] Step 9:

[0536] After a user views content, the device retrieves feedback and sends it to the server. This feedback includes ratings of satisfaction and relevance. The input is user feedback data, and the output is the registration of this feedback information to the server.

[0537] Step 10:

[0538] The server analyzes the feedback and updates the information selection algorithm. The feedback data is used to improve the selection accuracy in subsequent iterations and enhance overall system performance. The input is the feedback information, and the output is the updated selection algorithm.

[0539] (Application Example 1)

[0540] 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."

[0541] In modern society, users face the challenge of efficiently obtaining information relevant to their individual interests from a vast amount of news content. Furthermore, timely and flexible information provision is desirable for users to consume news at their own pace and according to their lifestyle.

[0542] 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.

[0543] In this invention, the server includes means for holding profile data for collecting information based on the user's interests, means for collecting data in real time from multiple information sources and indexing it based on a specific classification, means for filtering and prioritizing the collected data by referring to the stored profile data, means for creating text and multimedia content based on the filtered and prioritized data, means for distributing the generated content to the user's information processing device and converting it into audio format using speech synthesis technology, and means for receiving feedback from the user and improving the selection algorithm based on that feedback. This makes it possible for users to flexibly receive content that matches their interests as audio or video within a specified time frame.

[0544] "Profile data" refers to data that records a user's interests and preferences, and is used as a basis for information gathering.

[0545] "Information sources" refer to data providers who offer news and related information, and who provide the material necessary for indexing.

[0546] "Indexing" is the process of organizing collected data based on specific classifications to facilitate searching and filtering.

[0547] "Filtering" is the process of selecting highly relevant data from collected information based on profile data.

[0548] Prioritization is the process of determining the order in which filtered data is displayed or presented based on its importance and relevance.

[0549] "Text and multimedia content" refers to information in various forms, such as text, audio, and video, that is generated for the purpose of providing it to users.

[0550] An "information processing device" is an electronic device used to receive and play content, and generally refers to smartphones and computers.

[0551] "Speech synthesis technology" is a type of technology used to convert text data into a speech format.

[0552] "Feedback" refers to data on users' evaluations and impressions of the content provided, and is information that can be used to improve the system.

[0553] A "selection algorithm" is a computational method used to select the information that best suits the user's profile from the collected data.

[0554] To implement this invention, a server, a user terminal, and a network environment for communication between them are used. The server stores user profile data, collects data from multiple sources in real time, and indexes it based on specific classifications. Specifically, the server uses Python and Flask to build the backend logic and manage user profiles and collect news data.

[0555] The user's device has an application developed using React Native installed, which accepts user input and sends necessary data to the server. By using React Native, a user interface that can be comfortably operated on a smartphone is realized.

[0556] Furthermore, the server uses the Google Cloud Text-to-Speech API to convert text data into speech based on filtered and prioritized data. This enables the generation of multimedia content in audio format, which is then temporarily stored in AWS S3.

[0557] The distributed multimedia content utilizes speech synthesis technology to deliver audio content to the user's device within a specified time frame, either via streaming or download. This allows users to view news tailored to their interests and lifestyle.

[0558] For example, if a user specifies that they want to receive news in the "technology" and "health" categories every morning at 8:00 AM, the server will generate relevant content based on that request and deliver it at the specified time. Furthermore, user feedback after viewing the content is sent to the server, contributing to improvements in the selection algorithm.

[0559] As an example of a prompt, it's possible to provide input such as, "Please select a news genre, for example, politics, health, technology, etc. Please also specify your preferred delivery time. The AI ​​will customize and deliver news tailored to your preferences."

[0560] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0561] Step 1:

[0562] The user uses a device to input news genres of interest and desired delivery times. The device sends the user input data to the server. The server receives the news genres and desired times as input and records them as a user profile.

[0563] Step 2:

[0564] The server collects news data from multiple sources in real time based on the received user profile. The collected data is indexed based on the specified classification. This process retrieves RSS feeds from news feed URLs and filters their content by keywords.

[0565] Step 3:

[0566] The server filters indexed news data based on the user's profile and prioritizes it according to importance and relevance. The filtering and prioritization process refers to stored profile data to select articles related to specific genres.

[0567] Step 4:

[0568] The server uses filtered and prioritized news data to generate multimedia content in audio format from text. It uses the Google Cloud Text-to-Speech API to convert selected text articles into audio data. The generated audio data is stored in AWS S3.

[0569] Step 5:

[0570] At the specified delivery time, the server delivers the generated multimedia content to the device via streaming or download. The device then plays the received audio data and provides it to the user. In this step, the content delivery service is triggered by a time specified by the user.

[0571] Step 6:

[0572] After a user views content, the device sends feedback to the server. This feedback includes information about the user's satisfaction level and relevance of the news they viewed. The server analyzes this feedback and uses it to improve the algorithm. This process improves the generative AI model.

[0573] 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.

[0574] This invention is a system for providing personalized information tailored to a user's interests, concerns, and emotional state. The system operates with a server, a terminal, and an emotion engine working in conjunction. The user inputs their preferred news genres and desired viewing time via the terminal, which transmits this information to the server and collects data to analyze the user's emotional state.

[0575] The server creates a profile based on the information received from the user and stores it in a database. This profile includes not only the user's interests and relevant information, but also their emotional state analyzed by the emotion engine.

[0576] The server collects news data from multiple sources, analyzes it using natural language processing techniques, and classifies and indexes it by genre. The collected news data is filtered based on user profiles and then prioritized, taking into account the results of analysis by a sentiment engine.

[0577] For example, if a user is typically interested in "health" or "technology," they will be provided with selected news. However, if the emotion engine analyzes the user's current emotional state as "stressed," the server has the capability to prioritize delivering positive news or relaxation-related content.

[0578] The generated text and multimedia content are optimized by the server based on the user's emotional state. Text-to-speech technology and video editing software are used to create content that is easy for the user to view.

[0579] At a specified time, the device delivers content received from the server to the user via streaming or download. After viewing, the user enters feedback on the content into the device, which then sends this feedback to the server.

[0580] The server continuously improves its algorithms using feedback and analysis results from the sentiment engine. This process ensures that subsequent content deliveries are better tailored to the user's preferences and emotional state. In this way, the present invention makes it possible to provide users with a richer and more personalized news viewing experience.

[0581] The following describes the processing flow.

[0582] Step 1:

[0583] The user inputs news genres and desired viewing times through their device, which then sends this information to a server. The device also collects inputs to understand the user's emotional state (e.g., facial expressions and tone of voice).

[0584] Step 2:

[0585] The emotional data collected by the device is analyzed by an emotion engine, which evaluates the user's emotional state and sends the results to the server.

[0586] Step 3:

[0587] The server creates a user profile, which includes data about the user's interests, concerns, and emotional state. This profile is stored in a database and used for future processing.

[0588] Step 4:

[0589] The server collects news data from multiple sources. The collected data is classified using natural language processing techniques and indexed by related genre.

[0590] Step 5:

[0591] The server refers to user profiles and filters the collected news data. This filtering takes into account not only the user's interests but also the results of the sentiment engine's analysis.

[0592] Step 6:

[0593] Filtered news is prioritized on the server based on importance and relevance. Depending on the user's emotional state, news that evokes positive emotions may also be prioritized.

[0594] Step 7:

[0595] The server generates text and multimedia content based on prioritized news, utilizing speech synthesis technology and video editing software. The content is optimized for the user's emotional state.

[0596] Step 8:

[0597] The generated content is edited to fit the time frame specified by the user and sent from the server to the device. The device then makes the received content available for streaming or download to the user.

[0598] Step 9:

[0599] After viewing content on their device, users enter feedback such as their impressions and ratings. This feedback is sent from the device to the server.

[0600] Step 10:

[0601] The server uses feedback and analysis results from the sentiment engine to continuously improve news selection and content generation algorithms, and utilizes this information for future deliveries. This makes it possible to provide users with even more relevant content.

[0602] (Example 2)

[0603] 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."

[0604] While modern information distribution systems have achieved some success in providing content based on users' interests and preferences, there remain unresolved challenges in providing personalized information that takes into account users' emotional states. Furthermore, the lack of dynamic learning capabilities to continuously improve the accuracy and relevance of collected data makes it difficult to optimize the user experience.

[0605] 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.

[0606] In this invention, the server includes information storage means for recording data based on the user's interests and emotional state; means for collecting data in real time from multiple information sources and classifying and indexing it based on specific categories using natural language processing technology; and means for filtering and prioritizing the collected data by referring to the stored data records and the results of sentiment analysis. This enables the provision of personalized information according to the user's emotional state.

[0607] "Information storage means" refers to a means of recording data based on the user's interests and emotional state, and is a function that uses storage devices and databases to retain information.

[0608] "Natural language processing technology" refers to techniques for processing and analyzing human language using computers, and is a method used for data classification, analysis, and indexing.

[0609] A "filtering method" is a function that selects collected data based on specific criteria, and plays a role in extracting only the necessary information according to the user's profile and emotional state.

[0610] A "prioritization method" is a function that ranks filtered data based on importance and relevance, and is used to provide users with the most relevant information.

[0611] A "generative AI model" is an artificial intelligence model that learns from data and generates or predicts new data, and is used to improve algorithms.

[0612] A "machine learning structure" is a framework or system for learning patterns from data and using them to make predictions or classifications, with the aim of improving the accuracy and relevance of information gathering.

[0613] A "time adjustment mechanism" is a function that configures content to be viewable within a time frame specified by the user, and is used to control the timing of content delivery.

[0614] The system in this invention involves a server, a terminal, and an emotion analysis engine working together to provide personalized information based on the user's interests and emotional state.

[0615] The server stores data on user interests, desired viewing times, and emotional states received from users via their devices into a dedicated database. User information is analyzed by an emotion analysis engine, and the results are also stored as profile data. The server uses natural language processing (NLP) techniques to collect news data from multiple internet sources, classifying and indexing it into specific categories. This process utilizes software such as Python NLP libraries.

[0616] In the filtering and prioritization process, the server takes into account stored user profiles and emotional states to select the most relevant content from the collected information. The selected content is optimized for the user's emotional state and generated in an optimal visual and auditory format using speech synthesis technology (e.g., text-to-speech engine) and video editing software (e.g., video editing program).

[0617] The device provides optimized content from the server in streaming or download format, based on the specified viewing time. The user views the content and then enters feedback into the device. This feedback information is sent to the server, where a generative AI model uses it to improve the content delivery algorithm.

[0618] For example, if a user requests news in the "health" category and is experiencing stress, the system will prioritize providing relaxing health information and positive articles. An example of a prompt would be, "Please suggest news suitable for a user who is stressed," which asks the AI ​​model to suggest content that takes the user's emotional state into consideration.

[0619] In this way, the invention enables personalized news delivery based on emotional factors, providing users with a richer and more customized information experience.

[0620] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0621] Step 1:

[0622] The user uses a device to input their preferred news genres and desired viewing time. The device receives this information and collects emotional state data by sensing the user's speech and facial expressions. The input information includes news genres, desired viewing time, and emotional state data, and this data is sent to the next step.

[0623] Step 2:

[0624] The terminal sends the collected data to the server. The server stores the received data in a database and generates a profile using an information storage system. This profile includes the user's interests, preferred time, and emotional state. The profile information is output through data processing.

[0625] Step 3:

[0626] The server collects news data from multiple sources using an API. The input data is raw data obtained from each source. The server analyzes this data using natural language processing techniques and classifies and indexes it based on news genre. This process outputs genre-classified news data.

[0627] Step 4:

[0628] The server filters and prioritizes news data based on the user's profile and sentiment analysis results. At this stage, profile data and categorized news data are input. The filtering process selects the news content most relevant to the user.

[0629] Step 5:

[0630] The server optimizes prioritized news content based on the user's emotional state. Speech synthesis technology and video editing software are used to convert the content to speech and edit its visuals. This step outputs optimized text and multimedia content.

[0631] Step 6:

[0632] The device delivers content received from the server to the user via streaming or download at a specified time. Optimized content is used as input data, and the delivery result to the user is output.

[0633] Step 7:

[0634] After viewing the content, users enter feedback about it into their device. This feedback includes information about their satisfaction level and relevance of the content. This process generates feedback data.

[0635] Step 8:

[0636] The device sends the collected feedback to the server. The server uses a generative AI model to analyze the feedback and sentiment analysis results, and uses this information to improve the content delivery algorithm. In this step, the feedback data becomes the input, and the improved algorithm is output.

[0637] (Application Example 2)

[0638] 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."

[0639] In today's information society, users are often overwhelmed by the sheer volume of content provided by various sources. Furthermore, the lack of personalized information tailored to users' interests and emotional states leads to a problem where information is not properly utilized. There is also a need for methods to effectively leverage user feedback and emotional data to optimize future information delivery.

[0640] 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.

[0641] In this invention, the server includes means for storing profile data for collecting information based on the user's interests and emotional state; means for collecting data in real time from multiple sources and indexing it based on specific classifications using natural language processing technology; and means for filtering and prioritizing the collected data by referring to the stored profile data and the emotional state analyzed by the emotion analysis engine. This makes it possible to provide information optimized for the user's interests and emotions.

[0642] "Profile data" refers to data stored to collect information based on the user's interests and emotional state.

[0643] An "emotion analysis engine" is a system or program that analyzes a user's emotional state and reflects the analysis results in profile data.

[0644] "Natural language processing technology" is a technique for processing and analyzing human language using computers, and is a means of indexing information based on specific classifications.

[0645] "Filtering" is the process of selecting collected data based on the user's profile data and removing unnecessary information.

[0646] Prioritization is the process of evaluating the importance of information based on the user's interests and emotional state, and determining the order in which that information is presented.

[0647] "Speech synthesis technology" is a technology for converting text information into speech, and is a means of conveying the generated content to users.

[0648] "Video editing methods" refer to the technologies and tools used to process and edit multimedia content into a format that is easy for users to view.

[0649] "Streaming" is a technology that delivers generated content in real time, allowing users to watch it while downloading the data.

[0650] "Feedback" refers to the process by which users return their evaluations and opinions about content to the system, and this information is used to improve future information provision.

[0651] A "machine learning model" is an algorithm or technique used to improve the accuracy and relevance of information collection based on profile data and feedback data.

[0652] The system for realizing this invention mainly consists of a server, a terminal, and an emotion analysis engine.

[0653] The server stores profile data to collect information based on the user's interests and emotional state. The device processes the user's preferred genres and viewing time settings and sends this data to the server. During this process, the device collects the user's emotional data in real time using an emotion analysis engine.

[0654] The server collects data in real time from multiple sources and uses natural language processing techniques to categorize and index that information. The technologies used include natural language processing and speech synthesis engines. The collected data is filtered and prioritized based on stored profile data and emotional states analyzed by an emotion analysis engine. Following this process, text and multimedia content optimized to the user's emotions is generated.

[0655] The generated content is delivered to the device via streaming or download at a specified time. For example, if a user asks, "What news content can I find relaxing?", the system will prioritize delivering content that reduces stress. This allows for information delivery optimized to the user's state of mind.

[0656] Furthermore, user feedback is sent to the server via the device, and the algorithm is improved using machine learning models. This increases the accuracy and relevance of the information, making future information provision more appropriate.

[0657] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0658] Step 1:

[0659] The user uses a device to input their preferred genres of interest and desired viewing time. The device collects the user's current emotional data through sensors such as the camera and microphone. The input includes the user's genres of interest and emotional data, which is sent to the server. As output, this information is added to a profile database.

[0660] Step 2:

[0661] The server collects relevant news data from multiple sources based on the received interest genres and sentiment data. Natural language processing techniques are used to classify and index the data by theme. The input is news data obtained from numerous sources, and the output is classified news data.

[0662] Step 3:

[0663] The server filters and prioritizes collected news data based on profile data and sentiment analysis results. Inputs are stored profile data and sentiment states, while output prioritizes news with a relaxing effect and news from genres preferred by the user.

[0664] Step 4:

[0665] Using speech synthesis technology and video editing techniques, prioritized news data is generated as text and multimedia content. The input is filtered and prioritized news data, and the output is visually and aurally user-friendly content.

[0666] Step 5:

[0667] Based on the specified viewing time, the server delivers the generated content to the device via streaming or download. Here, the content is provided at the time reserved by the user. The input is the generated content and schedule information, and the output is the content available for viewing on the device.

[0668] Step 6:

[0669] Users enter feedback on their devices after viewing. This feedback is sent to the server. The input consists of user ratings and opinions, and the output is feedback data that helps in the continuous improvement of the algorithm.

[0670] Step 7:

[0671] The server updates its algorithm using a machine learning model based on feedback and sentiment data. This ensures that subsequent requests are better tailored to the user's preferences and emotional state. The input is feedback data and emotional state, and the output is an improved information delivery algorithm.

[0672] 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.

[0673] 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.

[0674] 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.

[0675] [Fourth Embodiment]

[0676] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0677] 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.

[0678] 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).

[0679] 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.

[0680] 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.

[0681] 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).

[0682] 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.

[0683] 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.

[0684] 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.

[0685] 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.

[0686] 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.

[0687] 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.

[0688] 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".

[0689] This invention is a system that enables users to obtain information based on their individual interests and preferences. The system operates primarily through interaction between a server, a terminal, and the user. In one example of this embodiment, the user uses a terminal to input their preferred news genres and desired viewing time.

[0690] The terminal sends user input to the server, which then creates a user profile based on this input. The server periodically collects news data from multiple sources, classifies the collected data by genre, and indexes it.

[0691] Based on the user's profile, the server selects relevant news articles and prioritizes them based on their importance and relevance. This makes it possible to select specific news articles that meet the user's needs.

[0692] The server then generates text and multimedia content based on the selected news. This generation step simultaneously utilizes speech synthesis technology and video clips to create visually and aurally effective content.

[0693] The generated content is edited to a length suitable for the time frame specified by the user. This allows users to efficiently obtain summaries of news they are interested in at their desired time. During delivery, the device provides the content to the user in either streaming or download format.

[0694] After a user views content, their device sends feedback to the server. This feedback evaluates how much the user enjoyed the news and whether it was relevant. The server analyzes this feedback and uses it as data to improve its information selection algorithm.

[0695] For example, if a user requests to watch "health" and "sports" news for 15 minutes at 8 AM, the server will collect relevant news articles based on this request, generate content, and deliver it at the specified time. This allows users to efficiently obtain the latest news. Through continuous use, this system will continue to evolve to better suit user preferences.

[0696] The following describes the processing flow.

[0697] Step 1:

[0698] The user enters their preferred news genres and viewing times via their device. The device then sends this information to the server.

[0699] Step 2:

[0700] The server creates user profiles based on information received from users and stores them in a database. This makes it possible to manage the interests and needs of individual users.

[0701] Step 3:

[0702] The server periodically collects news data from multiple sources. This news data is obtained via APIs and web scraping, formatted, and then stored in a temporary data store.

[0703] Step 4:

[0704] The server analyzes the collected news data using natural language processing technology, classifying and indexing it based on pre-defined genres. This enables rapid searching and access.

[0705] Step 5:

[0706] The server references the user profile and filters news by genre. Furthermore, it prioritizes news based on its importance and recency.

[0707] Step 6:

[0708] The server uses prioritized news to generate text and multimedia content using text synthesis and video editing software. This creates content in a format that is easy for users to view.

[0709] Step 7:

[0710] The generated content is edited to fit the time frame specified by the user and prepared for distribution. The server saves the content to system storage.

[0711] Step 8:

[0712] When the device reaches the specified time, it retrieves video content from the server and provides it to the user in streaming or download format.

[0713] Step 9:

[0714] Users view content using their devices and then provide feedback on what they have been given.

[0715] Step 10:

[0716] The device sends the collected feedback information to the server. The server uses this feedback to improve the news selection algorithm and incorporate it into future content delivery.

[0717] (Example 1)

[0718] 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".

[0719] In today's information society, it is difficult for users to quickly and efficiently gather information relevant to their interests from a vast amount of data. Furthermore, filtering and selecting necessary information from this vast amount of data requires considerable time and effort. In addition, as users' interests change, there are few information provision systems that can adapt to these changes, resulting in challenges in providing effective information.

[0720] 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.

[0721] In this invention, the server includes means for generating and storing profile information based on the user's interests, means for acquiring the latest data from multiple sources and classifying and organizing it into different categories, and means for selecting the acquired data based on the accumulated profile information and ordering it according to its importance. This makes it possible to efficiently and quickly provide necessary information while adapting to the user's changing interests.

[0722] "Profile information" refers to a collection of data generated and stored based on a user's interests, preferences, viewing history, and other factors.

[0723] A "source of information" refers to an external repository or system that provides news, articles, and other knowledge.

[0724] A "category" is a framework for organizing and classifying collected information by genre or type.

[0725] "Selection" refers to the process of selecting information from the collected data that is highly relevant to the user's profile.

[0726] "Ordering" refers to the process of assigning ranks to selected information based on its importance or relevance.

[0727] A "text" is a collection of sentences used to convey information or messages in text format.

[0728] "Multimedia content" refers to informational representations that combine different media such as text, images, audio, and video.

[0729] "Time management means" refers to functions and technologies for adjusting generated content to fit a time range specified by the user.

[0730] A "machine learning mechanism" is an algorithm or system that learns from past data and experience to improve the accuracy of information selection and delivery.

[0731] This invention is a system that efficiently provides information based on user interests. The system operates primarily through interaction between a server, a terminal, and the user. Specific embodiments of this system are described below.

[0732] The server receives news genres and desired viewing times entered by the user via their terminal, and uses this information to generate and store the user's profile information. This profile information is used to filter data according to the user's interests.

[0733] The server uses API access and web scraping techniques to collect the latest news data from multiple sources, including news delivery services and publicly available databases. The collected data is then categorized into genres such as "health" and "sports" using machine learning.

[0734] The terminal is responsible for delivering optimized content from the server to the user. The content length is adjusted to fit the user's desired time slot and delivered to the user in a viewable state. Users can efficiently obtain news and information of interest according to their specified viewing time.

[0735] For example, if a user wants to watch 15 minutes of news on "health" and "sports" at 8 AM, the server will select relevant news, generate content, and deliver it through the device at the specified time. This allows users to quickly access the latest news tailored to their interests.

[0736] An example of a prompt message is: "Generate a 15-minute news content piece based on the following news genre and time slot. The genres are 'Health' and 'Sports', and the time slot is 8:00 AM daily."

[0737] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0738] Step 1:

[0739] The user enters the news genre and desired viewing time into the device. The device formats the input data and sends it to the server. The input data is processed into JSON format, which includes the keys "news genre" and "viewing time".

[0740] Step 2:

[0741] The server generates user profile information from the data it receives. Based on the input data, the server analyzes the user's interests and updates or registers new profiles in the profile database. This profile information includes past viewing history and preferred genres.

[0742] Step 3:

[0743] The server collects news data from multiple sources. This is done using APIs and web scraping, and data is retrieved in real time. The input is the URL or API key of the configured information source, and the output is raw news data.

[0744] Step 4:

[0745] The server classifies and indexes the collected news data by category. Machine learning techniques are used to analyze the news content and classify it into categories such as "health" and "sports." The input is raw news data, and the output is a classified dataset.

[0746] Step 5:

[0747] The server selects and prioritizes appropriate news based on the user profile. The algorithm evaluates the relevance between the profile and categories and generates a list of selected news as output.

[0748] Step 6:

[0749] Based on the selected news, the server uses a generative AI model to create text and multimedia content. The input is a list of selected news articles, and the output is the generated content, which may include speech synthesis or video clips.

[0750] Step 7:

[0751] The server edits the generated content to fit the user-specified time frame. It adjusts the length and order of the content to suit the viewing time. The input is the generated content, and the output is the edited content.

[0752] Step 8:

[0753] The terminal receives the edited content and provides it to the user's device. The user can view it via streaming or download, with the input being the content data from the server and the output being the delivery to the user.

[0754] Step 9:

[0755] After a user views content, the device retrieves feedback and sends it to the server. This feedback includes ratings of satisfaction and relevance. The input is user feedback data, and the output is the registration of this feedback information to the server.

[0756] Step 10:

[0757] The server analyzes the feedback and updates the information selection algorithm. The feedback data is used to improve the selection accuracy in subsequent iterations and enhance overall system performance. The input is the feedback information, and the output is the updated selection algorithm.

[0758] (Application Example 1)

[0759] 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".

[0760] In modern society, users face the challenge of efficiently obtaining information relevant to their individual interests from a vast amount of news content. Furthermore, timely and flexible information provision is desirable for users to consume news at their own pace and according to their lifestyle.

[0761] 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.

[0762] In this invention, the server includes means for holding profile data for collecting information based on the user's interests, means for collecting data in real time from multiple information sources and indexing it based on a specific classification, means for filtering and prioritizing the collected data by referring to the stored profile data, means for creating text and multimedia content based on the filtered and prioritized data, means for distributing the generated content to the user's information processing device and converting it into audio format using speech synthesis technology, and means for receiving feedback from the user and improving the selection algorithm based on that feedback. This makes it possible for users to flexibly receive content that matches their interests as audio or video within a specified time frame.

[0763] "Profile data" refers to data that records a user's interests and preferences, and is used as a basis for information gathering.

[0764] "Information sources" refer to data providers who offer news and related information, and who provide the material necessary for indexing.

[0765] "Indexing" is the process of organizing collected data based on specific classifications to facilitate searching and filtering.

[0766] "Filtering" is the process of selecting highly relevant data from collected information based on profile data.

[0767] Prioritization is the process of determining the order in which filtered data is displayed or presented based on its importance and relevance.

[0768] "Text and multimedia content" refers to information in various forms, such as text, audio, and video, that is generated for the purpose of providing it to users.

[0769] An "information processing device" is an electronic device used to receive and play content, and generally refers to smartphones and computers.

[0770] "Speech synthesis technology" is a type of technology used to convert text data into a speech format.

[0771] "Feedback" refers to data on users' evaluations and impressions of the content provided, and is information that can be used to improve the system.

[0772] A "selection algorithm" is a computational method used to select the information that best suits the user's profile from the collected data.

[0773] To implement this invention, a server, a user terminal, and a network environment for communication between them are used. The server stores user profile data, collects data from multiple sources in real time, and indexes it based on specific classifications. Specifically, the server uses Python and Flask to build the backend logic and manage user profiles and collect news data.

[0774] The user's device has an application developed using React Native installed, which accepts user input and sends necessary data to the server. By using React Native, a user interface that can be comfortably operated on a smartphone is realized.

[0775] Furthermore, the server uses the Google Cloud Text-to-Speech API to convert text data into speech based on filtered and prioritized data. This enables the generation of multimedia content in audio format, which is then temporarily stored in AWS S3.

[0776] The distributed multimedia content utilizes speech synthesis technology to deliver audio content to the user's device within a specified time frame, either via streaming or download. This allows users to view news tailored to their interests and lifestyle.

[0777] For example, if a user specifies that they want to receive news in the "technology" and "health" categories every morning at 8:00 AM, the server will generate relevant content based on that request and deliver it at the specified time. Furthermore, user feedback after viewing the content is sent to the server, contributing to improvements in the selection algorithm.

[0778] As an example of a prompt, it's possible to provide input such as, "Please select a news genre, for example, politics, health, technology, etc. Please also specify your preferred delivery time. The AI ​​will customize and deliver news tailored to your preferences."

[0779] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0780] Step 1:

[0781] The user uses a device to input news genres of interest and desired delivery times. The device sends the user input data to the server. The server receives the news genres and desired times as input and records them as a user profile.

[0782] Step 2:

[0783] The server collects news data from multiple sources in real time based on the received user profile. The collected data is indexed based on the specified classification. This process retrieves RSS feeds from news feed URLs and filters their content by keywords.

[0784] Step 3:

[0785] The server filters indexed news data based on the user's profile and prioritizes it according to importance and relevance. The filtering and prioritization process refers to stored profile data to select articles related to specific genres.

[0786] Step 4:

[0787] The server uses filtered and prioritized news data to generate multimedia content in audio format from text. It uses the Google Cloud Text-to-Speech API to convert selected text articles into audio data. The generated audio data is stored in AWS S3.

[0788] Step 5:

[0789] At the specified delivery time, the server delivers the generated multimedia content to the device via streaming or download. The device then plays the received audio data and provides it to the user. In this step, the content delivery service is triggered by a time specified by the user.

[0790] Step 6:

[0791] After a user views content, the device sends feedback to the server. This feedback includes information about the user's satisfaction level and relevance of the news they viewed. The server analyzes this feedback and uses it to improve the algorithm. This process improves the generative AI model.

[0792] 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.

[0793] This invention is a system for providing personalized information tailored to a user's interests, concerns, and emotional state. The system operates with a server, a terminal, and an emotion engine working in conjunction. The user inputs their preferred news genres and desired viewing time via the terminal, which transmits this information to the server and collects data to analyze the user's emotional state.

[0794] The server creates a profile based on the information received from the user and stores it in a database. This profile includes not only the user's interests and relevant information, but also their emotional state analyzed by the emotion engine.

[0795] The server collects news data from multiple sources, analyzes it using natural language processing techniques, and classifies and indexes it by genre. The collected news data is filtered based on user profiles and then prioritized, taking into account the results of analysis by a sentiment engine.

[0796] For example, if a user is typically interested in "health" or "technology," they will be provided with selected news. However, if the emotion engine analyzes the user's current emotional state as "stressed," the server has the capability to prioritize delivering positive news or relaxation-related content.

[0797] The generated text and multimedia content are optimized by the server based on the user's emotional state. Text-to-speech technology and video editing software are used to create content that is easy for the user to view.

[0798] At a specified time, the device delivers content received from the server to the user via streaming or download. After viewing, the user enters feedback on the content into the device, which then sends this feedback to the server.

[0799] The server continuously improves its algorithms using feedback and analysis results from the sentiment engine. This process ensures that subsequent content deliveries are better tailored to the user's preferences and emotional state. In this way, the present invention makes it possible to provide users with a richer and more personalized news viewing experience.

[0800] The following describes the processing flow.

[0801] Step 1:

[0802] The user inputs news genres and desired viewing times through their device, which then sends this information to a server. The device also collects inputs to understand the user's emotional state (e.g., facial expressions and tone of voice).

[0803] Step 2:

[0804] The emotional data collected by the device is analyzed by an emotion engine, which evaluates the user's emotional state and sends the results to the server.

[0805] Step 3:

[0806] The server creates a user profile, which includes data about the user's interests, concerns, and emotional state. This profile is stored in a database and used for future processing.

[0807] Step 4:

[0808] The server collects news data from multiple sources. The collected data is classified using natural language processing techniques and indexed by related genre.

[0809] Step 5:

[0810] The server refers to user profiles and filters the collected news data. This filtering takes into account not only the user's interests but also the results of the sentiment engine's analysis.

[0811] Step 6:

[0812] Filtered news is prioritized on the server based on importance and relevance. Depending on the user's emotional state, news that evokes positive emotions may also be prioritized.

[0813] Step 7:

[0814] The server generates text and multimedia content based on prioritized news, utilizing speech synthesis technology and video editing software. The content is optimized for the user's emotional state.

[0815] Step 8:

[0816] The generated content is edited to fit the time frame specified by the user and sent from the server to the device. The device then makes the received content available for streaming or download to the user.

[0817] Step 9:

[0818] After viewing content on their device, users enter feedback such as their impressions and ratings. This feedback is sent from the device to the server.

[0819] Step 10:

[0820] The server uses feedback and analysis results from the sentiment engine to continuously improve news selection and content generation algorithms, and utilizes this information for future deliveries. This makes it possible to provide users with even more relevant content.

[0821] (Example 2)

[0822] 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".

[0823] While modern information distribution systems have achieved some success in providing content based on users' interests and preferences, there remain unresolved challenges in providing personalized information that takes into account users' emotional states. Furthermore, the lack of dynamic learning capabilities to continuously improve the accuracy and relevance of collected data makes it difficult to optimize the user experience.

[0824] 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.

[0825] In this invention, the server includes information storage means for recording data based on the user's interests and emotional state; means for collecting data in real time from multiple information sources and classifying and indexing it based on specific categories using natural language processing technology; and means for filtering and prioritizing the collected data by referring to the stored data records and the results of sentiment analysis. This enables the provision of personalized information according to the user's emotional state.

[0826] "Information storage means" refers to a means of recording data based on the user's interests and emotional state, and is a function that uses storage devices and databases to retain information.

[0827] "Natural language processing technology" refers to techniques for processing and analyzing human language using computers, and is a method used for data classification, analysis, and indexing.

[0828] A "filtering method" is a function that selects collected data based on specific criteria, and plays a role in extracting only the necessary information according to the user's profile and emotional state.

[0829] A "prioritization method" is a function that ranks filtered data based on importance and relevance, and is used to provide users with the most relevant information.

[0830] A "generative AI model" is an artificial intelligence model that learns from data and generates or predicts new data, and is used to improve algorithms.

[0831] A "machine learning structure" is a framework or system for learning patterns from data and using them to make predictions or classifications, with the aim of improving the accuracy and relevance of information gathering.

[0832] A "time adjustment mechanism" is a function that configures content to be viewable within a time frame specified by the user, and is used to control the timing of content delivery.

[0833] The system in this invention involves a server, a terminal, and an emotion analysis engine working together to provide personalized information based on the user's interests and emotional state.

[0834] The server stores data on user interests, desired viewing times, and emotional states received from users via their devices into a dedicated database. User information is analyzed by an emotion analysis engine, and the results are also stored as profile data. The server uses natural language processing (NLP) techniques to collect news data from multiple internet sources, classifying and indexing it into specific categories. This process utilizes software such as Python NLP libraries.

[0835] In the filtering and prioritization process, the server takes into account stored user profiles and emotional states to select the most relevant content from the collected information. The selected content is optimized for the user's emotional state and generated in an optimal visual and auditory format using speech synthesis technology (e.g., text-to-speech engine) and video editing software (e.g., video editing program).

[0836] The device provides optimized content from the server in streaming or download format, based on the specified viewing time. The user views the content and then enters feedback into the device. This feedback information is sent to the server, where a generative AI model uses it to improve the content delivery algorithm.

[0837] For example, if a user requests news in the "health" category and is experiencing stress, the system will prioritize providing relaxing health information and positive articles. An example of a prompt would be, "Please suggest news suitable for a user who is stressed," which asks the AI ​​model to suggest content that takes the user's emotional state into consideration.

[0838] In this way, the invention enables personalized news delivery based on emotional factors, providing users with a richer and more customized information experience.

[0839] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0840] Step 1:

[0841] The user uses a device to input their preferred news genres and desired viewing time. The device receives this information and collects emotional state data by sensing the user's speech and facial expressions. The input information includes news genres, desired viewing time, and emotional state data, and this data is sent to the next step.

[0842] Step 2:

[0843] The terminal sends the collected data to the server. The server stores the received data in a database and generates a profile using an information storage system. This profile includes the user's interests, preferred time, and emotional state. The profile information is output through data processing.

[0844] Step 3:

[0845] The server collects news data from multiple sources using an API. The input data is raw data obtained from each source. The server analyzes this data using natural language processing techniques and classifies and indexes it based on news genre. This process outputs genre-classified news data.

[0846] Step 4:

[0847] The server filters and prioritizes news data based on the user's profile and sentiment analysis results. At this stage, profile data and categorized news data are input. The filtering process selects the news content most relevant to the user.

[0848] Step 5:

[0849] The server optimizes prioritized news content based on the user's emotional state. Speech synthesis technology and video editing software are used to convert the content to speech and edit its visuals. This step outputs optimized text and multimedia content.

[0850] Step 6:

[0851] The device delivers content received from the server to the user via streaming or download at a specified time. Optimized content is used as input data, and the delivery result to the user is output.

[0852] Step 7:

[0853] After viewing the content, users enter feedback about it into their device. This feedback includes information about their satisfaction level and relevance of the content. This process generates feedback data.

[0854] Step 8:

[0855] The device sends the collected feedback to the server. The server uses a generative AI model to analyze the feedback and sentiment analysis results, and uses this information to improve the content delivery algorithm. In this step, the feedback data becomes the input, and the improved algorithm is output.

[0856] (Application Example 2)

[0857] 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".

[0858] In today's information society, users are often overwhelmed by the sheer volume of content provided by various sources. Furthermore, the lack of personalized information tailored to users' interests and emotional states leads to a problem where information is not properly utilized. There is also a need for methods to effectively leverage user feedback and emotional data to optimize future information delivery.

[0859] 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.

[0860] In this invention, the server includes means for storing profile data for collecting information based on the user's interests and emotional state; means for collecting data in real time from multiple sources and indexing it based on specific classifications using natural language processing technology; and means for filtering and prioritizing the collected data by referring to the stored profile data and the emotional state analyzed by the emotion analysis engine. This makes it possible to provide information optimized for the user's interests and emotions.

[0861] "Profile data" refers to data stored to collect information based on the user's interests and emotional state.

[0862] An "emotion analysis engine" is a system or program that analyzes a user's emotional state and reflects the analysis results in profile data.

[0863] "Natural language processing technology" is a technique for processing and analyzing human language using computers, and is a means of indexing information based on specific classifications.

[0864] "Filtering" is the process of selecting collected data based on the user's profile data and removing unnecessary information.

[0865] Prioritization is the process of evaluating the importance of information based on the user's interests and emotional state, and determining the order in which that information is presented.

[0866] "Speech synthesis technology" is a technology for converting text information into speech, and is a means of conveying the generated content to users.

[0867] "Video editing methods" refer to the technologies and tools used to process and edit multimedia content into a format that is easy for users to view.

[0868] "Streaming" is a technology that delivers generated content in real time, allowing users to watch it while downloading the data.

[0869] "Feedback" refers to the process by which users return their evaluations and opinions about content to the system, and this information is used to improve future information provision.

[0870] A "machine learning model" is an algorithm or technique used to improve the accuracy and relevance of information collection based on profile data and feedback data.

[0871] The system for realizing this invention mainly consists of a server, a terminal, and an emotion analysis engine.

[0872] The server stores profile data to collect information based on the user's interests and emotional state. The device processes the user's preferred genres and viewing time settings and sends this data to the server. During this process, the device collects the user's emotional data in real time using an emotion analysis engine.

[0873] The server collects data in real time from multiple sources and uses natural language processing techniques to categorize and index that information. The technologies used include natural language processing and speech synthesis engines. The collected data is filtered and prioritized based on stored profile data and emotional states analyzed by an emotion analysis engine. Following this process, text and multimedia content optimized to the user's emotions is generated.

[0874] The generated content is delivered to the device via streaming or download at a specified time. For example, if a user asks, "What news content can I find relaxing?", the system will prioritize delivering content that reduces stress. This allows for information delivery optimized to the user's state of mind.

[0875] Furthermore, user feedback is sent to the server via the device, and the algorithm is improved using machine learning models. This increases the accuracy and relevance of the information, making future information provision more appropriate.

[0876] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0877] Step 1:

[0878] The user uses a device to input their preferred genres of interest and desired viewing time. The device collects the user's current emotional data through sensors such as the camera and microphone. The input includes the user's genres of interest and emotional data, which is sent to the server. As output, this information is added to a profile database.

[0879] Step 2:

[0880] The server collects relevant news data from multiple sources based on the received interest genres and sentiment data. Natural language processing techniques are used to classify and index the data by theme. The input is news data obtained from numerous sources, and the output is classified news data.

[0881] Step 3:

[0882] The server filters and prioritizes collected news data based on profile data and sentiment analysis results. Inputs are stored profile data and sentiment states, while output prioritizes news with a relaxing effect and news from genres preferred by the user.

[0883] Step 4:

[0884] Using speech synthesis technology and video editing techniques, prioritized news data is generated as text and multimedia content. The input is filtered and prioritized news data, and the output is visually and aurally user-friendly content.

[0885] Step 5:

[0886] Based on the specified viewing time, the server delivers the generated content to the device via streaming or download. Here, the content is provided at the time reserved by the user. The input is the generated content and schedule information, and the output is the content available for viewing on the device.

[0887] Step 6:

[0888] Users enter feedback on their devices after viewing. This feedback is sent to the server. The input consists of user ratings and opinions, and the output is feedback data that helps in the continuous improvement of the algorithm.

[0889] Step 7:

[0890] The server updates its algorithm using a machine learning model based on feedback and sentiment data. This ensures that subsequent requests are better tailored to the user's preferences and emotional state. The input is feedback data and emotional state, and the output is an improved information delivery algorithm.

[0891] 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.

[0892] 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.

[0893] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0894] 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.

[0895] 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.

[0896] 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.

[0897] 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.

[0898] 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.

[0899] 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."

[0900] 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.

[0901] 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.

[0902] 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.

[0903] 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.

[0904] 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.

[0905] 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.

[0906] 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.

[0907] 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.

[0908] 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.

[0909] 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.

[0910] 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.

[0911] 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.

[0912] The following is further disclosed regarding the embodiments described above.

[0913] (Claim 1)

[0914] A means of storing profile data for collecting information based on user interests,

[0915] A means of collecting data in real time from multiple sources and indexing it based on specific classifications,

[0916] A means for filtering and prioritizing collected data by referring to stored profile data,

[0917] A means for generating text and multimedia content based on filtered and prioritized data,

[0918] A means of delivering the generated content to the user's device,

[0919] A means of receiving feedback from users and updating the algorithm based on that feedback,

[0920] A system that includes this.

[0921] (Claim 2)

[0922] The system according to claim 1, comprising a machine learning model for improving the accuracy and relevance of information collection based on profile data and feedback data.

[0923] (Claim 3)

[0924] The system according to claim 1, including scheduling means for editing generated content into a format that can be viewed within a time frame specified by the user.

[0925] "Example 1"

[0926] (Claim 1)

[0927] A means for generating and storing user profile information based on user interests,

[0928] A means of obtaining the latest data from multiple sources and classifying and organizing it into different categories,

[0929] A means of selecting acquired data based on accumulated profile information and ordering it according to its importance,

[0930] A means for generating text and multimedia content based on selected and ordered data,

[0931] Means for providing the generated content to the user's device,

[0932] A means of obtaining user evaluations and improving information selection methods based on them,

[0933] A system that includes this.

[0934] (Claim 2)

[0935] The system according to claim 1, comprising a machine learning mechanism for improving the efficiency and suitability of information acquisition based on profile information and user evaluation data.

[0936] (Claim 3)

[0937] The system according to claim 1, including a time management means for adjusting the generated content to a format that can be viewed within a time range specified by the user.

[0938] "Application Example 1"

[0939] (Claim 1)

[0940] A means for holding profile data to collect information based on user interests,

[0941] A means of collecting data in real time from multiple sources and indexing it based on specific classifications,

[0942] A means for filtering and prioritizing collected data by referring to stored profile data,

[0943] A means for creating text and multimedia content based on filtered and prioritized data,

[0944] A means for distributing the generated content to the user's information processing device and converting it into an audio format using speech synthesis technology,

[0945] A means of receiving feedback from users and improving the selection algorithm based on that feedback,

[0946] A system that includes this.

[0947] (Claim 2)

[0948] The system according to claim 1, comprising a machine learning model that improves the accuracy and relevance of information collection and contributes to the generation of audio and video clips based on profile data and feedback data.

[0949] (Claim 3)

[0950] The system according to claim 1, comprising scheduling means for editing the generated content into a format that can be received within a time frame specified by the user, and supplying it in streaming or download format.

[0951] "Example 2 of combining an emotion engine"

[0952] (Claim 1)

[0953] Information storage means for recording data based on the user's interests and emotional state,

[0954] A means of collecting data in real time from multiple sources and classifying and indexing it based on specific categories using natural language processing technology,

[0955] Means for filtering and prioritizing collected data by referring to stored data records and sentiment analysis results,

[0956] A means for generating text and multimedia data adapted to the user's emotional state based on filtered and prioritized data,

[0957] A means of distributing the generated data to the user's device,

[0958] A means of receiving feedback from users and improving the algorithm using a generative AI model based on that feedback,

[0959] A system that includes this.

[0960] (Claim 2)

[0961] The system according to claim 1, comprising a machine learning structure for improving the accuracy and relevance of information collection based on data recording and feedback data.

[0962] (Claim 3)

[0963] The system according to claim 1, including a time adjustment means for structuring the generated data into a format that can be viewed within a time frame specified by the user.

[0964] "Application example 2 when combining with an emotional engine"

[0965] (Claim 1)

[0966] A means for storing profile data to collect information based on the user's interests and emotional state,

[0967] A means of collecting data in real time from multiple sources and indexing it based on a specific classification using natural language processing technology,

[0968] A means for filtering and prioritizing collected data by referring to stored profile data and emotional states analyzed by an emotion analysis engine,

[0969] A means for generating text and multimedia content using speech synthesis technology and video editing means based on filtered and prioritized data,

[0970] A means of delivering the generated content to the user's device in streaming or download format,

[0971] A means of receiving feedback from users and updating algorithms and machine learning models based on that feedback,

[0972] A system that includes this.

[0973] (Claim 2)

[0974] The system according to claim 1, comprising a machine learning model for improving the accuracy and relevance of information collection based on profile data and feedback data.

[0975] (Claim 3)

[0976] The system according to claim 1, including scheduling means for editing generated content into a format that can be viewed within a time frame specified by the user. [Explanation of symbols]

[0977] 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 of storing profile data for collecting information based on user interests, A means of collecting data in real time from multiple sources and indexing it based on a specific classification, A means for filtering and prioritizing collected data by referring to stored profile data, A means for generating text and multimedia content based on filtered and prioritized data, A means of delivering the generated content to the user's device, A means of receiving feedback from users and updating the algorithm based on that feedback, A system that includes this.

2. The system according to claim 1, comprising a machine learning model for improving the accuracy and relevance of information collection based on profile data and feedback data.

3. The system according to claim 1, including scheduling means for editing generated content into a format that can be viewed within a time frame specified by the user.

Images