system

Abstract

Provide a system. A means for a user to input categories of interest when logging in for the first time; A means of collecting new information and categorizing it using generative AI; means for recommending the classified information based on the user's preferences; a means for communicating recommendations; A system including:

Description

[Technical Field]

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

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

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

[0004] Internal bulletin boards contain a wide range of information, from work-related information to information about drinking parties and clubs. However, because the amount of information is large and varied, users may miss information that interests them or is necessary for their work. Furthermore, in order to effectively obtain the necessary information, users must frequently check the bulletin boards themselves, which takes time and effort. This can reduce the efficiency of information acquisition and have a negative impact on work efficiency. [Means for solving the problem]

[0005] The present invention solves the above problem by providing a system that includes a means for a user to input categories of interest when logging in for the first time, a means for collecting new information and classifying it into categories using a generation AI, a means for recommending the classified information based on the user's preferences, and a means for notifying the user of the recommended information.

[0006] This system can effectively extract information necessary for a user's hobbies, preferences, and work, and notify the user of that information. Furthermore, by including a means for recording user action data and providing feedback to the generation AI, the system can learn the user's preferences more accurately and provide appropriate information. Furthermore, by including a means for notifying the user of recommended information on their device and displaying it on the feed page, the system allows the user to easily access the information they need. This is expected to improve the efficiency of information acquisition and operational efficiency.

[0007] A "user" is an individual belonging to an organization who can use an information system.

[0008] "First login" refers to the first time a user accesses the system and performs authentication.

[0009] "Categories of interest" are types of information in which a user is interested related to his or her hobbies or work.

[0010] "Information" refers to various data such as text, images, and links posted on internal bulletin boards.

[0011] "Generative AI" is an artificial intelligence technique that uses machine learning algorithms to analyze collected data and make classifications and recommendations.

[0012] "Categorizing" is the process of organizing collected information into predefined categories.

[0013] "Preferences" is a concept that refers to the types and trends of information that a user is interested in.

[0014] "Recommending" means providing appropriate information to the user based on specific conditions or algorithms.

[0015] A "notification" is an action that notifies a user of specific information, and includes forms such as push notification and email notification.

[0016] A "system" is a collection of multiple elements, such as hardware, software, and networks, designed to perform a specific task.

[0017] "Action Data" is a record of actions taken by users on the system (e.g., views, clicks, "likes," etc.).

[0018] "Feedback" refers to returning data to the system's learning model to improve its performance and accuracy.

[0019] A "terminal" is a device that a user uses to access an information system, and includes a personal computer, smartphone, tablet, etc.

[0020] A "feed page" is a web page or application screen that displays all relevant information to a user. [Brief explanation of the drawings]

[0021] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0022] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0023] First, the terms used in the following description will be explained.

[0024] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0025] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0026] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0027] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0028] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0029] [First embodiment]

[0030] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0031] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0032] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0033] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0034] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0035] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0036] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0037] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0038] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0039] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0040] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0041] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0042] This invention is a system for efficiently obtaining information that a user needs or is interested in. The specific implementation method and operation of this system will be described below.

[0043] System Overview

[0044] This system is composed of a server, a terminal, and a generation AI. When a user logs in for the first time, they set the information categories that interest them, and the server periodically collects new information from the company bulletin board and classifies it using the generation AI. The system then notifies the user of recommended information based on their preferences and displays appropriate information on the feed page, allowing the user to efficiently obtain the information they need.

[0045] Settings when you first log in

[0046] When a user logs in for the first time, the server displays a screen for the user to enter categories of hobbies and interests (e.g., "technical information," "product releases," "drinking party announcements," etc.).

[0047] The terminal (browser or app on the user's device) displays the setting screen sent from the server and collects the information entered by the user.

[0048] The user selects categories of interest and sends configuration information to the server.

[0049] Information collection and classification

[0050] The server periodically (for example, every hour) collects new posts from the internal bulletin board using an API or scraping.

[0051] The server converts the collected information into text format, preprocesses it, and then inputs it into the generative AI model.

[0052] The generative AI classifies the information into categories it has previously learned (e.g., "technical information," "drinking party," "important announcement," etc.).

[0053] The server stores the classified information in a database by category.

[0054] Learning user preferences

[0055] The device records the articles the user has viewed and actions such as "likes" and periodically transmits the records to the server.

[0056] The server stores the user's action data in a database and periodically provides feedback to the generating AI.

[0057] The generative AI uses this action data to update the user's preference profile, allowing it to recommend more relevant information.

[0058] Information recommendations and notifications

[0059] Every time new information is saved in the database, the server sends a request to the generative AI to recommend appropriate information based on the user's profile.

[0060] The generative AI selects recommended information based on the user's profile and returns the results to the server.

[0061] The server collects the recommended information for each user and generates a notification message.

[0062] The terminal receives the notification message sent from the server and displays it to the user.

[0063] The server then sends a request to display the recommendations on the feed page.

[0064] The device displays the recommended information on the feed page for easy reference by the user.

[0065] Specific examples

[0066] For example, if User A sets his / her interest in "technical information" and "drinking party announcements" when logging in for the first time, the server will use the generative AI to collect and classify new posts related to technical information or drinking party announcements. The server will then recommend the information that best suits User A's preferences from the classified information and notify the device. Furthermore, the recommended information will also be displayed on User A's feed page, allowing User A to efficiently obtain information of interest.

[0067] In this way, this system allows users to efficiently obtain information necessary for their work or information of interest without missing it.

[0068] The processing flow will be explained below.

[0069] Step 1:

[0070] When users log in for the first time, they are prompted to enter categories of hobbies and interests. Specifically, the screen displays options such as "Technical Information," "Product Releases," and "Drinking Party Announcements."

[0071] Step 2:

[0072] The device collects information about categories of interest selected by the user and sends it to the server in JSON format or similar.

[0073] Step 3:

[0074] The server stores the received configuration information in a database, which records the categories of interest for each user.

[0075] Step 4:

[0076] The server periodically collects information from the internal bulletin board by scraping or using an API. This process is executed, for example, every hour.

[0077] Step 5:

[0078] The server converts the collected information into text format and performs preprocessing (e.g., removing HTML tags, extracting text).

[0079] Step 6:

[0080] The generative AI analyzes the pre-processed information and uses a pre-trained model to categorize it, for example, into categories such as "technical information," "drinking parties," and "important announcements."

[0081] Step 7:

[0082] The server stores the information classified by the generation AI in a database by category.

[0083] Step 8:

[0084] The terminal records the articles the user has viewed and actions such as "likes" and transmits the records to the server periodically (for example, in real time or daily).

[0085] Step 9:

[0086] The server records the user's action data in a database and provides feedback to the generating AI.

[0087] Step 10:

[0088] The generative AI uses the feedback to update the user's preference profile, including which categories the user is most interested in.

[0089] Step 11:

[0090] Every time new information is saved in the database, the server sends a request to the generative AI to recommend appropriate information based on the user's profile.

[0091] Step 12:

[0092] The generative AI selects recommended information based on the user's profile and returns the results to the server.

[0093] Step 13:

[0094] The server compiles the recommendation information returned by the generation AI for each user and generates a notification message.

[0095] Step 14:

[0096] The device receives notification messages sent from the server and displays them to the user, including push notifications and email notifications.

[0097] Step 15:

[0098] The server then sends a request to display the recommendations on the feed page.

[0099] Step 16:

[0100] The device displays recommended information on the feed page for easy reference by the user, allowing the user to efficiently obtain information that they need or that interests them.

[0101] The above are the detailed processing steps of this system.

[0102] Example 1

[0103] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0104] The amount of information shared within a company or organization is enormous, making it difficult for users to efficiently obtain the information they need or are interested in. In addition, in many cases, information recommendations based on users' interests are not made, which can lead to users missing information or overlooking important information. This can lead to problems such as reduced work efficiency and satisfaction.

[0105] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0106] In this invention, the server includes a means for allowing a user to input categories of interest when logging in for the first time, a means for periodically collecting new information, a means for converting the collected information into text format and performing preprocessing, a means for classifying information by category using a generative AI model, a means for generating recommended information based on the user's preferences, a means for notifying the user of the generated recommended information, and a means for displaying the recommended information on a feed page, thereby enabling the user to efficiently obtain information of interest or need.

[0107] "User" refers to an individual or member of an organization who uses the system.

[0108] A "category" is a division that classifies information based on a particular group or theme.

[0109] "New Information" refers to new or updated data that the system periodically collects.

[0110] "Generative AI model" refers to an artificial intelligence model used to classify and recommend information using machine learning techniques.

[0111] "Preprocessing" refers to data processing such as tokenization and stop word removal that is performed on collected text data in order to input it into a generative AI model.

[0112] "Recommended information" refers to information selected by a generative AI model based on a user's preferences and past behavior.

[0113] "Notification" refers to the act of sending specific information or messages from the system to the user.

[0114] "Feed Page" refers to a page in the user interface that displays recommendations and updates.

[0115] "Action data" refers to records of actions taken by users within the system (e.g., viewing articles, liking articles, etc.).

[0116] A "user profile" refers to a data set containing personalized information generated based on a user's interests, preferences, and past behavior.

[0117] "Database" refers to a data storage system for storing and managing collected information, user profiles, and classification results.

[0118] This invention is a system for efficiently obtaining information that a user needs or is interested in. The specific implementation method and operation of this system will be described below.

[0119] System configuration

[0120] This system is composed of a server, a terminal, and a generative AI model. The server is responsible for collecting, classifying, recommending, and notifying information, while the terminal provides the interface that users operate. The generative AI model is used to classify and recommend information.

[0121] Settings when you first log in

[0122] When a user logs in for the first time, the server generates an HTML form for the user to enter categories of interest (e.g., "Technical Information," "Product Releases," "Drinking Party Announcements," etc.). Specifically, this is implemented using a Python framework (e.g., Django, Flask).

[0123] The terminal displays this HTML form in the user's browser and collects the data entered by the user.

[0124] The user selects the category of interest and sends the setting information to the server via the send button.

[0125] The server receives this configuration information and stores it in a database (e.g., MySQL (registered trademark), PostgreSQL). This information is used as a user profile.

[0126] Information collection and preprocessing

[0127] The server periodically collects new posts from the internal bulletin board using Python's requests library, BeautifulSoup, or the bulletin board's API.

[0128] The server converts the collected information into text format and performs preprocessing using the NLTK library and spaCy, which includes tokenizing the text and removing stop words.

[0129] Information classification

[0130] The generative AI model receives preprocessed text information as input and classifies it into pre-trained categories (e.g., "technical information," "drinking party," "important announcement," etc.) This AI model uses a transformer-based model (e.g., BERT, GPT-3 (registered trademark)).

[0131] The server receives the classification results from the generative AI model and stores them in a database by category.

[0132] Learning user preferences

[0133] The device records action data such as when a user views a feed page or clicks the "Like" button, using JavaScript (registered trademark) event tracking technology.

[0134] The server stores this action data in a database and feeds it back into the generative AI model.

[0135] The generative AI model updates the user's preference profile based on this action data and recommends more appropriate information.

[0136] Recommendation generation and notification

[0137] Every time new information is saved in the database, the server requests the generative AI model to recommend appropriate information based on the user's profile.

[0138] The generative AI model selects recommended information based on the user's interest categories and latest action data, and returns the results to the server.

[0139] The server organizes the list of recommended information returned by the generative AI model and generates a notification message for each user.

[0140] The device displays the notification message sent from the server in a pop-up notification or notification center.

[0141] The server sends a request to the terminal to update the content of the feed page as needed.

[0142] The terminal updates the feed page in real time, allowing the user to efficiently browse the recommended information.

[0143] Specific examples

[0144] For example, when User A logs in for the first time, he or she specifies that he or she is interested in "technical information" and "drinking party announcements." The server stores this information in a database. Next, the server periodically collects new posts from the company bulletin board and sends them to the generative AI model, where they are classified as "technical information" or "drinking party announcements." When User A views the feed page or clicks the "Like" button, this behavioral data is sent to the server and fed back to the generative AI model. Based on this information, the server generates optimal recommendations for User A and displays them on the device as notification messages. Furthermore, the feed page is also updated, allowing User A to efficiently obtain the information of interest to him or her.

[0145] Prompt Sentence Examples

[0146] Below are some examples of prompts to input to the generative AI model.

[0147] Please recommend information that matches User A's interests. Interest categories: technical information, drinking party announcements. Please categorize the following new posts and provide appropriate recommendations.

[0148] Post 1: "In-depth article on new technical information"

[0149] Post 2: "Information about tonight's drinking party"

[0150] As described above, this system provides functions that allow users to efficiently obtain information they need or are interested in.

[0151] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0152] Step 1: First login setup

[0153] When the user logs in for the first time, the server generates an HTML form for entering the user's categories of interest (e.g., "Technical Information," "Product Releases," "Drinking Party Announcements," etc.) and sends it to the terminal. The input includes the categories selected by the user. The output is the generated HTML form displayed on the terminal as an HTML page.

[0154] The device displays this HTML form in the user's browser and collects the data entered by the user. Specific actions include rendering the HTML form and pressing a "Submit" button to proceed to the next step.

[0155] The user selects the category of interest and clicks the "Submit" button. The input includes the category selection. The output is the selected category data sent to the server.

[0156] The server stores the received setting information in a database and manages it as a user profile. The input includes category data selected by the user. The output includes the user profile stored in the database.

[0157] Step 2: Gather information

[0158] The server periodically (e.g., every hour) collects new posts from the internal message boards. Techniques used include the Python requests library, BeautifulSoup, or the message board API. Inputs include the latest message board URLs and API endpoints. Outputs include the collected new post data.

[0159] The server converts the collected information into text format and preprocesses it for the next step. Preprocessing includes tokenizing the text and removing stop words, and uses the NLTK library and spaCy. The input includes the collected raw post data. The output includes the converted text format and the preprocessed data.

[0160] Step 3: Classify the information

[0161] The server sends the preprocessed text information to a generative AI model, which uses a Transformer-based model (e.g., BERT, GPT-3). The input includes the preprocessed text data. The output includes the classification results from the generative AI model.

[0162] A generative AI model classifies information based on pre-trained categories (e.g., "technical information," "drinking party," "important announcement," etc.). The input includes pre-processed text data. The output includes classified category information.

[0163] The server receives the classification results from the generative AI model and stores them in a database by category. The input includes the classification result data. The output includes the categorized information stored in the database.

[0164] Step 4: Learning user preferences

[0165] The device records action data such as when a user views a feed page or clicks the "Like" button. JavaScript-based event tracking technology is used. The input includes the user's operation actions. The output includes the recorded action data.

[0166] The server periodically receives action data collected from the terminals and stores it in a database. The input includes the user's action data. The output includes the action data stored in the database.

[0167] The generative AI model updates the user's preference profile based on this action data. The input includes the action data. The output includes the updated user's preference profile.

[0168] Step 5: Generate recommendations

[0169] Each time new information is saved to the database, the server requests the generative AI model to recommend appropriate information based on the user's profile. The input includes the user's profile data and the latest information. The output includes the recommended information from the generative AI model.

[0170] The generative AI model selects recommended information based on the user's interest categories and latest action data, and returns the results to the server. The input includes the user's preference profile and latest information. The output includes a list of recommended information.

[0171] The server organizes the list of recommendations returned by the generative AI model and generates a notification message for each user. The input includes the recommendations from the generative AI model. The output includes the generated notification message.

[0172] Step 6: Notification and display of information

[0173] The device receives notification messages sent from the server and displays them in a popup notification or in the app's internal notification center using JavaScript. The input includes the notification message from the server. The output includes the displayed notification.

[0174] The server sends a request to the terminal to update the content of the feed page as needed. The input includes the update request. The output includes the update request.

[0175] The device updates the content of the feed page in real time based on this request, allowing the user to efficiently browse recommended information. The input includes an update request from the server. The output includes an updated feed page.

[0176] (Application example 1)

[0177] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0178] It is difficult for factory workers to quickly and efficiently obtain the necessary business information and important notifications, which can result in work delays and mistakes.In addition, there is a lack of means to properly filter and provide information that meets workers' interests and work needs, so there is a need to prevent confusion caused by information overload.

[0179] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0180] In this invention, the server includes a means for a user to input categories of interest when logging in for the first time, a means for collecting new information and classifying it by category using a generative AI model, a means for recommending the classified information based on the user's preferences, a means for notifying the user of the recommended information, and a means for displaying the recommended information on the display screen of an automated device. This allows factory workers to efficiently obtain the information they need and reduces work delays and errors.

[0181] "Means for users to input categories of interest when logging in for the first time" is a function that provides an interface for users to select and input categories of interest or concern from a list when they access the system for the first time.

[0182] "Means of collecting new information and categorizing it using a generative AI model" is the process of automatically organizing the latest collected information into predefined categories using a trained AI model.

[0183] "Means for recommending classified information based on user preferences" is a mechanism that prioritizes the presentation of appropriate information based on the user's past behavioral data and categories of interest.

[0184] The "means for notifying recommended information" refers to a method by which the system notifies the user of recommended information in the form of a message or an alert.

[0185] "Means for displaying recommended information on a display screen of an automated device" means a system that includes procedures for displaying information recommended to a user on the display of a robot or other automated device.

[0186] MODE FOR CARRYING OUT THE INVENTION

[0187] System Overview

[0188] This invention is a system for efficiently obtaining information that users need or are interested in. The system is composed of a server, a terminal, and a generative AI model. When a user first logs in, they set the information categories that interest them, and the server periodically collects new information from various sources within the factory and classifies it using the generative AI model. The system then notifies the user of recommended information based on the user's preferences and provides appropriate information, enabling the user to efficiently obtain the information they need.

[0189] Settings when you first log in

[0190] When a user logs in for the first time, the server displays a screen for the user to enter their hobbies and interest categories (e.g., "Technical Information," "Important Notices," etc.). The terminal (the browser or app on the user's device) displays the setting screen sent from the server and collects the information entered by the user. The user selects the categories of interest and sends the setting information to the server.

[0191] Information collection and classification

[0192] The server periodically (for example, every hour) collects new information from sources within the factory using APIs or scraping. The server converts the collected information into text format, performs preprocessing, and then inputs it into the generative AI model. The generative AI model classifies the information into categories it has learned in advance (for example, "technical information," "important notices," etc.). The server stores the classified information in a database by category.

[0193] Learning user preferences

[0194] The device records the articles the user has viewed and actions such as "likes," and periodically sends these to the server. The server stores the user's action data in a database and periodically feeds it back to the generative AI model. The generative AI model uses this action data to update the user's preference profile, enabling it to recommend more appropriate information.

[0195] Information recommendations and notifications

[0196] Each time new information is saved in the database, the server sends a request to the generative AI model to recommend appropriate information based on the user's profile. The generative AI model selects recommended information based on the user's profile and returns the results to the server. The server then compiles the recommended information for each user and generates a notification message. The terminal receives the notification message sent from the server and displays it on the display of the user or automated equipment.

[0197] Hardware / Software used

[0198] The hardware uses a factory robot and its display, and the software uses the Python programming language, a REST API, and Hugging Face's Transformers library.

[0199] Examples of concrete examples and prompts

[0200] For example, if a worker is interested in "technical information" or "important notices" while working in a factory, he can set these categories in the robot and efficiently obtain important new information.

[0201] Example prompt sentence:

[0202] Prompt: 'Category the following text: Technical Information, Important Notice, Other'

[0203] Text: 'New machine introduced.'

[0204] Model output: 'Technical information'

[0205] Text: 'About tonight's social gathering.'

[0206] Model output: 'Other'

[0207] This ensures that only the information that is important to the worker is displayed on the robot's display.

[0208] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0209] Step 1:

[0210] When a user logs in for the first time, the server displays a screen for the user to enter their hobbies and categories of interest. The user enters the categories of interest on the displayed screen and sends this information from the terminal to the server. The input data is in the form of a list of category names. The server saves this list in a database.

[0211] Step 2:

[0212] The server periodically collects new information from sources within the factory using APIs or scraping techniques, and sends the collected data to the server as raw data, which is received in raw text format.

[0213] Step 3:

[0214] The server converts the collected raw information into text format and performs preprocessing before inputting it into the generative AI model. Specifically, this includes removing unnecessary tags and noise, and formatting the text. The preprocessed data is sent to the generative AI model as clean text data.

[0215] Step 4:

[0216] The server sends the preprocessed information to the generative AI model, which then classifies it into categories. The generative AI model then analyzes the input text data and classifies it into the appropriate category based on the pre-trained prompts. The classification results are returned to the server as data with category labels.

[0217] Step 5:

[0218] The server stores the classification results returned by the generative AI model in a database, which contains pairs of category labels and text data, keeping the information organized by category.

[0219] Step 6:

[0220] The device records the articles the user has viewed and actions such as "likes" and periodically sends the recorded action data to the server. The action data includes the viewing time, viewed categories, and user ratings. The server stores this action data in a database.

[0221] Step 7:

[0222] The server periodically feeds back the saved user action data to the generative AI model. This feedback allows the generative AI model to update the user's preference profile and make more advanced recommendations. The data used for feedback includes the latest category information along with the user's action data.

[0223] Step 8:

[0224] Every time new information is saved in the database, the server sends a request to the generative AI model to recommend appropriate information based on the user's profile. The generative AI model then refers to the user's profile, selects the most appropriate information, and returns the results to the server.

[0225] Step 9:

[0226] The server compiles the recommendations returned by the generative AI model into a notification message for each user, which includes the text and category of the recommendations.

[0227] Step 10:

[0228] The terminal receives notification messages sent from the server and displays them on the display of the user or automated equipment, providing the displayed information in a format that can be easily referenced by the user.

[0229] This allows users to efficiently obtain the necessary information, improving work efficiency within the factory.

[0230] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0231] This invention is a system that efficiently acquires information that a user needs or is interested in, and further recognizes the user's emotions using an emotion engine and reflects them in the information recommendations. The specific implementation method and operation of this system are described below.

[0232] System Overview

[0233] The system is composed of a server, a terminal, a generation AI, and an emotion engine. When a user first logs in, they set the information categories that interest them. The server periodically collects new information from the company's bulletin board and uses the generation AI to classify it, while also recognizing the user's emotions. Based on the user's preferences and emotions, the system notifies the user of recommended information and displays appropriate information on the feed page, allowing the user to efficiently obtain the information they need.

[0234] Settings when you first log in

[0235] When a user logs in for the first time, the server displays a screen for the user to enter categories of hobbies and interests (e.g., "technical information," "product releases," "drinking party announcements," etc.).

[0236] The terminal (browser or app on the user's device) displays the setting screen sent from the server and collects the information entered by the user.

[0237] The user selects categories of interest and sends configuration information to the server.

[0238] Information collection and classification

[0239] The server periodically (for example, every hour) collects new posts from the internal bulletin board using an API or scraping.

[0240] The server converts the collected information into text format and performs preprocessing (e.g., removing HTML tags, extracting text).

[0241] The generative AI analyzes the pre-processed information and uses a pre-trained model to categorize it, for example, into categories such as "technical information," "drinking parties," and "important announcements."

[0242] The server stores the information classified by the generation AI in a database by category.

[0243] Learning user preferences and recognizing emotions

[0244] The terminal records the articles the user has viewed and actions such as "likes" and transmits the records to the server periodically (for example, in real time or daily).

[0245] The server records the user's action data in a database and provides feedback to the generating AI.

[0246] The generative AI uses this action data to update the user's preference profile, which includes which categories the user is particularly interested in.

[0247] The server uses an emotion engine to recognize the emotions (e.g., joy, excitement, sadness, etc.) of the user when viewing information. For example, it analyzes emotions from facial expressions and voices via a camera or microphone.

[0248] The emotion engine feeds the recognized emotion data back to the generative AI.

[0249] Information recommendations and notifications

[0250] Every time new information is saved in the database, the server sends a request to the generative AI to recommend appropriate information based on the user's preference profile and emotional data.

[0251] The generative AI selects recommendations based on the user's profile and emotions and returns the results to the server.

[0252] The server compiles the recommendation information returned by the generation AI for each user and generates a notification message.

[0253] The device receives notification messages sent from the server and displays them to the user, including push notifications and email notifications.

[0254] The server then sends a request to display the recommendations on the feed page.

[0255] The device displays recommended information on the feed page for easy reference by the user, allowing the user to efficiently obtain information that they need or that interests them.

[0256] Specific examples

[0257] For example, if User A sets his / her interest in "technical information" and "drinking party announcements" when he / she logs in for the first time, the server will use generative AI to collect and classify new posts related to technical information or drinking party announcements. The server will then recommend the information that best suits User A's preferences and emotions from the classified information and notify the device. Furthermore, the recommended information will also be displayed on User A's feed page, allowing User A to efficiently obtain information that interests him / her.

[0258] For example, if User A is viewing a "Technical Information" article and the emotion engine recognizes that the user is very excited, the generative AI will receive this emotion data and reflect it in future recommended information. In this way, by combining emotion engines, it becomes possible to provide information that better suits the user's needs.

[0259] In this way, this system allows users to efficiently obtain information necessary for their work or that they are interested in, without missing anything. By using emotion data, it becomes possible to provide information with even greater accuracy.

[0260] The processing flow will be explained below.

[0261] Step 1:

[0262] When a user logs in for the first time, the server displays a screen for the user to enter categories of hobbies and interests (e.g., "technical information," "product releases," "drinking party announcements," etc.).

[0263] Step 2:

[0264] The terminal displays the setting screen sent from the server and collects information on categories of interest selected by the user.

[0265] Step 3:

[0266] The user selects categories of interest and sends configuration information to the server.

[0267] Step 4:

[0268] The server stores the received configuration information in a database, which records the categories of interest for each user.

[0269] Step 5:

[0270] The server periodically (for example, every hour) collects information from the internal bulletin board by scraping or using an API.

[0271] Step 6:

[0272] The server converts the collected information into text format and performs preprocessing (e.g., removing HTML tags, extracting text).

[0273] Step 7:

[0274] The generative AI analyzes the pre-processed information and uses a pre-trained model to categorize it, for example, into categories such as "technical information," "drinking parties," and "important announcements."

[0275] Step 8:

[0276] The server stores the information classified by the generation AI in a database by category.

[0277] Step 9:

[0278] The terminal records the articles the user has viewed and actions such as "likes" and transmits the records to the server periodically (for example, in real time or daily).

[0279] Step 10:

[0280] The server records the user's action data in a database and provides feedback to the generating AI.

[0281] Step 11:

[0282] The generative AI uses this action data to update the user's preference profile, which includes which categories the user is particularly interested in.

[0283] Step 12:

[0284] While the user is browsing information, the device sends the data necessary to recognize the user's emotions (e.g., happiness, excitement, sadness) to the emotion engine, including facial and voice data captured via the camera and microphone.

[0285] Step 13:

[0286] The emotion engine analyzes the transmitted data and recognizes the user's emotions, for example, analyzing facial expressions for joy or sadness and detecting changes in tone from the voice.

[0287] Step 14:

[0288] The emotion engine feeds the recognized emotion data back to the generative AI.

[0289] Step 15:

[0290] Every time new information is saved in the database, the server sends a request to the generative AI to recommend appropriate information based on the user's preference profile and emotional data.

[0291] Step 16:

[0292] The generative AI selects recommendations based on the user's profile and emotions and returns the results to the server.

[0293] Step 17:

[0294] The server compiles the recommendation information returned by the generation AI for each user and generates a notification message.

[0295] Step 18:

[0296] The device receives notification messages sent from the server and displays them to the user, including push notifications and email notifications.

[0297] Step 19:

[0298] The server then sends a request to display the recommendations on the feed page.

[0299] Step 20:

[0300] The device displays recommended information on the feed page for easy reference by the user, allowing the user to efficiently obtain information that they need or that interests them.

[0301] The above are the detailed processing steps of this system.

[0302] Example 2

[0303] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0304] In today's information society, it is difficult for users to efficiently obtain the information they want when they need it. Furthermore, there is a lack of information provided that takes into account the user's preferences and emotions, so there is a need for a method to provide more personalized information. Therefore, it is necessary to develop a system that recommends the most appropriate information based on the user's interests and emotions.

[0305] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0306] In this invention, the server includes a means for allowing a user to input categories of interest when logging in for the first time, a means for periodically collecting new information and classifying it into categories using a generative AI after preprocessing, a means for recommending information based on the user's preference profile and emotions, and a means for displaying the recommended information in notifications and on the feed page, thereby enabling personalized information to be provided based on the user's interests and emotions.

[0307] "User" means an individual or corporation that uses this system to obtain information.

[0308] "First login" refers to the act of a user accessing this system for the first time and performing the necessary settings.

[0309] A "category" is a concept that indicates a classification of information that a user is interested in, and examples include "technical information" and "drinking party announcements."

[0310] "Periodic collection" means obtaining new information at regular intervals.

[0311] "Preprocessing" refers to the process of formatting and cleaning data before analyzing collected information.

[0312] "Generative AI" is an artificial intelligence program that uses machine learning and deep learning techniques to analyze data and make classifications and recommendations.

[0313] "Classifying by category" means organizing collected information based on predefined categories.

[0314] A "preference profile" is a user-specific data profile created based on the user's interests and concerns.

[0315] "Emotion" refers to the psychological state that a user expresses when viewing information, examples of which include "joy" and "excitement."

[0316] A "notification" is an information message that the system sends to the user, and includes, for example, a push notification or an email notification.

[0317] A "feed page" is a web page or app screen that a user can access to view a list of various information.

[0318] This invention is a system designed to enable users to efficiently obtain information of interest. Furthermore, by using an emotion engine to recognize the user's emotions and reflecting them in the recommended information, personalized information can be provided. An embodiment of this system will be specifically described below.

[0319] Settings when you first log in

[0320] When a user logs in for the first time, the server generates a setting screen for the user to enter categories of interest and sends it to the terminal. The setting screen includes options such as "Technical Information," "Product Releases," and "Drinking Party Announcements," for example.

[0321] The device displays the setting screen sent from the server to the user on the browser or within the app.

[0322] The user selects a category of interest and transmits the selection information from the terminal to the server.

[0323] Information collection and classification

[0324] The server periodically (for example, every hour) collects new posts from the internal bulletin board using APIs or scraping. The collected data is converted into text format and preprocessed (removing HTML tags and extracting text).

[0325] Generative AI analyzes the pre-processed information and classifies it into categories using a pre-trained model. This process uses machine learning algorithms. The classified information is divided into categories such as "technical information," "drinking party," and "important announcement."

[0326] The server stores the information classified by the generation AI in a database by category.

[0327] Learning user preferences and recognizing emotions

[0328] The device records the articles the user has viewed and actions such as "likes" and transmits the records to the server in real time or periodically.

[0329] The server records the user's action data in a database and feeds that data back to the generating AI.

[0330] The generative AI uses the action data to update the user's preference profile, for example by analyzing the user's interest in a particular category.

[0331] The server recognizes the user's emotions using an emotion engine, which analyzes the user's emotions from facial expressions and voice recorded via a camera and microphone, and feeds that data back to the generation AI.

[0332] Information recommendations and notifications

[0333] Every time new information is saved in the database, the server sends a request to the generative AI to recommend appropriate information based on the user's preference profile and emotional data.

[0334] The generative AI selects recommendations based on the user's profile and emotional data and returns the results to the server.

[0335] The server compiles the recommendation information returned by the generation AI for each user and generates a notification message.

[0336] The device receives notification messages sent from the server and displays them to the user, including push notifications and email notifications.

[0337] The server then sends a request to display the recommendations on the feed page.

[0338] The terminal displays the recommended information on the feed page so that the user can easily refer to it.

[0339] Examples of concrete examples and prompts

[0340] For example, if User A sets his / her interest in "technical information" and "drinking party announcements" when logging in for the first time, the server will collect new posts related to these categories and classify them using generative AI. From the classified information, the server will then recommend the information that best suits User A's preferences and emotions and notify the device. Furthermore, the recommended information will also be displayed on User A's feed page, allowing User A to efficiently obtain information that interests him / her.

[0341] Specific examples of prompts include:

[0342] Prompt statement

[0343] If user A specifies that he is interested in "Technical Information" and "Drinking Party Announcements" when he logs in for the first time, please explain how the server will collect new posts related to these topics and notify the user.

[0344] This system allows users to efficiently obtain information necessary for their work or that they are interested in. Furthermore, by utilizing emotion data, it becomes possible to provide information with even greater accuracy.

[0345] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0346] Step 1: First login setup

[0347] Input: The user logs in for the first time.

[0348] Specific behavior:

[0349] The server generates an initial login screen and sends it to the terminal.

[0350] The device displays a settings screen (e.g., category selection such as "Technical Information," "Product Releases," and "Drinking Party Announcements").

[0351] The user selects the categories of interest and transmits the information to the server via the terminal.

[0352] Output: The user's interest category information is saved on the server.

[0353] Step 2: Collecting and Preprocessing Information

[0354] Input: The time to collect comes periodically (e.g. every hour).

[0355] Specific behavior:

[0356] The server uses APIs and scraping to collect new posts from internal bulletin boards.

[0357] The server converts the collected information into text format and performs preprocessing such as removing HTML tags and extracting text.

[0358] Output: Preprocessed text data.

[0359] Step 3: Classifying information using generative AI

[0360] Input: Preprocessed text data.

[0361] Specific behavior:

[0362] Generative AI uses a trained model to classify pre-processed text data into categories, a process that uses machine learning algorithms.

[0363] The server stores the classified information in a database by category.

[0364] Output: Information broken down by category.

[0365] Step 4: Recording user actions

[0366] Input: An action a user takes while using the system (e.g., viewing an article, pressing like).

[0367] Specific behavior:

[0368] The device records user actions (e.g., viewing articles, pressing "like," etc.).

[0369] The device sends these action data to the server in real time or on a daily basis.

[0370] Output: User action data is recorded on the server.

[0371] Step 5: Update your preference profile

[0372] Input: User action data.

[0373] Specific behavior:

[0374] The server records the user's action data in a database and feeds that data back to the generating AI.

[0375] The generative AI analyzes the action data and updates the user's preference profile, which includes the user's interest in specific categories.

[0376] Output: Updated user preference profile.

[0377] Step 6: Recognize emotions

[0378] Input: Facial expressions and voice data as the user browses the information.

[0379] Specific behavior:

[0380] The server uses an emotion engine to recognize the user's emotions (e.g., joy, excitement, sadness, etc.).

[0381] The emotion engine analyzes emotions from facial expressions and voices collected through the camera and microphone, and feeds that data back to the generative AI.

[0382] Output: Emotion data is fed back to the generative AI.

[0383] Step 7: Recommend information

[0384] Input: Newly stored information in the database, user preference profile, and emotional data.

[0385] Specific behavior:

[0386] Every time new information is saved in the database, the server sends a request to the generative AI to recommend appropriate information based on the user's preference profile and emotional data.

[0387] The generative AI analyzes the user's profile and emotional data, selects the most appropriate information, and returns the results to the server.

[0388] Output: Recommended information.

[0389] Step 8: Notification and display of recommendations

[0390] Input: Recommendations returned by the generative AI.

[0391] Specific behavior:

[0392] The server compiles the recommendation information returned by the generation AI for each user and generates a notification message.

[0393] The device receives the notification message sent from the server and displays it to the user via push notification or email notification.

[0394] The server then sends a request to display the recommendations on the feed page.

[0395] The device displays the recommended information on the feed page for easy reference by the user.

[0396] Output: The recommendation that is notified to the user and displayed on the feed page.

[0397] (Application example 2)

[0398] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0399] In modern virtual stores, it is difficult for users to efficiently find products that match their interests and preferences from a vast amount of product information. Furthermore, product recommendations that take user emotions into consideration are rarely performed. This can lead to a poor user experience and a decrease in purchasing intent.

[0400] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a means for the user to input categories of interest when logging in for the first time, a means for collecting new information and classifying it by category using a generation AI, a means for recommending the classified information based on the user's preferences, a means for recognizing the user's emotions and adjusting the recommended information based thereon, and a means for notifying the user of the recommended information. This allows the optimal products to be recommended based on the user's preferences and emotions, enabling the user to efficiently find products of interest.

[0401] "Means for users to input categories of interest when logging in for the first time" refers to an interface or function that allows users to input categories of interest or concern when logging in to an application or system for the first time.

[0402] "Means of collecting new information" refers to the processes and techniques by which servers and related devices obtain the latest information from the Internet and related databases.

[0403] "Methods of categorizing using generative AI" refers to algorithms and models that use natural language processing and machine learning to classify collected information into specific categories.

[0404] "Means for making recommendations based on user preferences" refers to technology that selects optimal information and products based on the user's past behavioral data and set preferences and provides them to the user.

[0405] "Means for recognizing a user's emotions and adjusting recommended information based on them" refers to technology that uses devices such as cameras and microphones to analyze emotions from a user's facial expressions and voice, and then changes the recommended information and product content based on that emotional data.

[0406] "Means for notifying recommended information" refers to a function for sending messages or push notifications to inform users of recommended information or products.

[0407] The present invention relates to a system that enables a user to obtain optimal information and products based on their interests and preferences. Detailed embodiments of the present invention will be described below.

[0408] System Overview

[0409] This system consists of the following main components:

[0410] 1. Server: Collects, categorizes, and recommends information.

[0411] 2. Terminal: A device such as a smartphone or tablet operated by a user.

[0412] 3. Generative AI: Algorithms that categorize information and make recommendations.

[0413] 4. Emotion engine: An engine that analyzes user emotions and reflects them in recommendations.

[0414] Settings when you first log in

[0415] When a user logs in to the system for the first time, the server provides the user with an interface to input the categories of interest. The device (smartphone or tablet) displays this interface and sends the information input by the user to the server. For example, the user may input that they are interested in "games" or "gadgets."

[0416] Information collection and classification

[0417] The server periodically collects the latest information, using APIs from the internet or specific databases. The collected information is pre-processed, and the generating AI analyzes and classifies it into categories. For example, it can classify information on new gadgets or the latest game releases.

[0418] Learning user preferences and recognizing emotions

[0419] The device records the user's action data (e.g., browsing history, "likes," etc.) and sends it to the server. The server feeds this data back to the generation AI and updates the user's preference profile. The emotion engine also analyzes the user's emotions from facial images and voice data. For example, if the user is excited or sad, that emotional data is sent to the server.

[0420] Information recommendations and notifications

[0421] Each time new information is collected, the server sends a request to the generation AI to recommend appropriate information based on the user's preference profile and emotional data. Based on this request, the generation AI selects the most appropriate information for the user and returns it to the server. The server then generates this recommended information as a notification message and sends it to the device. For example, it sends a push notification such as, "A new game has been released! Your favorite game category has been updated!"

[0422] Usage example

[0423] For example, suppose a user logs in and specifies that they are interested in "games" and "gadgets." While the user is browsing articles in the "games" category, the emotion engine scans the user's facial expressions and recognizes that the user is very excited. The AI ​​receives this emotion data, and the next time new game information is collected, it prioritizes and recommends information that is likely to excite the user. For example, it sends a notification message to the user saying, "The latest VR game has been released!"

[0424] Prompt Sentence Examples

[0425] "User ID: abc123, Preferences: Games, Gadgets, Emotion: Excitement. Please recommend the best products for the user based on this. New product list: [Product A, Product B, Product C...]"

[0426] In this way, users can efficiently obtain the information and products they are most interested in in real time, improving their virtual store experience. Utilizing emotional data also enables more personalized recommendations.

[0427] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0428] Step 1:

[0429] This is a way for users to input categories of interest when logging in for the first time. When a user logs in using a smartphone or tablet device, the server displays an interface for the user to input categories of interest. The user selects the categories of interest (e.g., "games," "gadgets," etc.) from this interface, and that information is sent to the server. The input data is the user's interests and concerns, and the output is that information is saved on the server.

[0430] Step 2:

[0431] It is a method by which a server collects new information and classifies it into categories using generative AI. The server periodically uses APIs to collect the latest information (e.g., new product information, news articles, etc.) from the internet and related databases. This collected data is converted into text format and preprocessed (removing HTML tags, extracting text, etc.). The input data is the collected raw information, and the output is preprocessed text data.

[0432] Step 3:

[0433] This is a method by which the server uses generative AI to classify information into categories. Preprocessed text data is passed to the generative AI, which uses a model to classify it into the appropriate category. For example, articles about games are classified as "games," and articles about gadgets are classified as "gadgets." The input data is preprocessed text data, and the output is information classified into categories.

[0434] Step 4:

[0435] It is a means by which a device records user action data (e.g., article viewing, "likes," etc.) and sends it to a server. When a user views an article or performs a specific action on the device, that data is recorded by the device and periodically sent to the server. The input data is the user action data, and the output is that it is sent to the server and recorded.

[0436] Step 5:

[0437] The server has a means to recognize the user's emotions and adjust the recommended information based on them. The emotion engine analyzes the user's facial image and voice data to recognize the user's emotions (e.g., joy, excitement, sadness). The input data is the user's image and voice data, and the output is the analyzed emotion data.

[0438] Step 6:

[0439] The server sends a request to the generation AI to recommend appropriate information based on the user's preference profile and emotional data. The generation AI uses the profile and emotional data to select appropriate products and information and returns the results to the server. For example, a prompt such as "User ID: abc123, Preferences: Games, Gadgets, Emotion: Excitement. Please recommend the most suitable information for the user based on this information" is passed to the generation AI. The input data is the user's preference profile and emotional data, and the output is recommended information.

[0440] Step 7:

[0441] The server has a means to notify the user's device of the recommended information. The recommended information is generated by the server as a push notification or in-app notification and sent to the user's device. The input data is the recommended information, and the output is a notification message that is displayed on the device.

[0442] Step 8:

[0443] The device has a means to display recommended information on a feed page. When the user opens the feed page, the recommended information and products are listed and can be easily referenced. The input data is the recommended information, and the output is the information displayed on the feed page.

[0444] In this way, users can efficiently obtain information that best suits their preferences and feelings.

[0445] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0446] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0447] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0448] [Second embodiment]

[0449] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0450] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0451] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0452] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0453] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0454] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0455] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0456] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0457] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0458] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0459] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0460] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0461] This invention is a system for efficiently obtaining information that a user needs or is interested in. The specific implementation method and operation of this system will be described below.

[0462] System Overview

[0463] This system is composed of a server, a terminal, and a generation AI. When a user logs in for the first time, they set the information categories that interest them, and the server periodically collects new information from the company bulletin board and classifies it using the generation AI. The system then notifies the user of recommended information based on their preferences and displays appropriate information on the feed page, allowing the user to efficiently obtain the information they need.

[0464] Settings when you first log in

[0465] When a user logs in for the first time, the server displays a screen for the user to enter categories of hobbies and interests (e.g., "technical information," "product releases," "drinking party announcements," etc.).

[0466] The terminal (browser or app on the user's device) displays the setting screen sent from the server and collects the information entered by the user.

[0467] The user selects categories of interest and sends configuration information to the server.

[0468] Information collection and classification

[0469] The server periodically (for example, every hour) collects new posts from the internal bulletin board using an API or scraping.

[0470] The server converts the collected information into text format, preprocesses it, and then inputs it into the generative AI model.

[0471] The generative AI classifies the information into categories it has previously learned (e.g., "technical information," "drinking party," "important announcement," etc.).

[0472] The server stores the classified information in a database by category.

[0473] Learning user preferences

[0474] The device records the articles the user has viewed and actions such as "likes" and periodically transmits the records to the server.

[0475] The server stores the user's action data in a database and periodically provides feedback to the generating AI.

[0476] The generative AI uses this action data to update the user's preference profile, allowing it to recommend more relevant information.

[0477] Information recommendations and notifications

[0478] Every time new information is saved in the database, the server sends a request to the generative AI to recommend appropriate information based on the user's profile.

[0479] The generative AI selects recommended information based on the user's profile and returns the results to the server.

[0480] The server collects the recommended information for each user and generates a notification message.

[0481] The terminal receives the notification message sent from the server and displays it to the user.

[0482] The server then sends a request to display the recommendations on the feed page.

[0483] The device displays the recommended information on the feed page for easy reference by the user.

[0484] Specific examples

[0485] For example, if User A sets his / her interest in "technical information" and "drinking party announcements" when logging in for the first time, the server will use the generative AI to collect and classify new posts related to technical information or drinking party announcements. The server will then recommend the information that best suits User A's preferences from the classified information and notify the device. Furthermore, the recommended information will also be displayed on User A's feed page, allowing User A to efficiently obtain information of interest.

[0486] In this way, this system allows users to efficiently obtain information necessary for their work or information of interest without missing it.

[0487] The processing flow will be explained below.

[0488] Step 1:

[0489] When users log in for the first time, they are prompted to enter categories of hobbies and interests. Specifically, the screen displays options such as "Technical Information," "Product Releases," and "Drinking Party Announcements."

[0490] Step 2:

[0491] The device collects information about categories of interest selected by the user and sends it to the server in JSON format or similar.

[0492] Step 3:

[0493] The server stores the received configuration information in a database, which records the categories of interest for each user.

[0494] Step 4:

[0495] The server periodically collects information from the internal bulletin board by scraping or using an API. This process is executed, for example, every hour.

[0496] Step 5:

[0497] The server converts the collected information into text format and performs preprocessing (e.g., removing HTML tags, extracting text).

[0498] Step 6:

[0499] The generative AI analyzes the pre-processed information and uses a pre-trained model to categorize it, for example, into categories such as "technical information," "drinking parties," and "important announcements."

[0500] Step 7:

[0501] The server stores the information classified by the generation AI in a database by category.

[0502] Step 8:

[0503] The terminal records the articles the user has viewed and actions such as "likes" and transmits the records to the server periodically (for example, in real time or daily).

[0504] Step 9:

[0505] The server records the user's action data in a database and provides feedback to the generating AI.

[0506] Step 10:

[0507] The generative AI uses the feedback to update the user's preference profile, including which categories the user is most interested in.

[0508] Step 11:

[0509] Every time new information is saved in the database, the server sends a request to the generative AI to recommend appropriate information based on the user's profile.

[0510] Step 12:

[0511] The generative AI selects recommended information based on the user's profile and returns the results to the server.

[0512] Step 13:

[0513] The server compiles the recommendation information returned by the generation AI for each user and generates a notification message.

[0514] Step 14:

[0515] The device receives notification messages sent from the server and displays them to the user, including push notifications and email notifications.

[0516] Step 15:

[0517] The server then sends a request to display the recommendations on the feed page.

[0518] Step 16:

[0519] The device displays recommended information on the feed page for easy reference by the user, allowing the user to efficiently obtain information that they need or that interests them.

[0520] The above are the detailed processing steps of this system.

[0521] Example 1

[0522] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0523] The amount of information shared within a company or organization is enormous, making it difficult for users to efficiently obtain the information they need or are interested in. In addition, in many cases, information recommendations based on users' interests are not made, which can lead to users missing information or overlooking important information. This can lead to problems such as reduced work efficiency and satisfaction.

[0524] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0525] In this invention, the server includes a means for allowing a user to input categories of interest when logging in for the first time, a means for periodically collecting new information, a means for converting the collected information into text format and performing preprocessing, a means for classifying information by category using a generative AI model, a means for generating recommended information based on the user's preferences, a means for notifying the user of the generated recommended information, and a means for displaying the recommended information on a feed page, thereby enabling the user to efficiently obtain information of interest or need.

[0526] "User" refers to an individual or member of an organization who uses the system.

[0527] A "category" is a division that classifies information based on a particular group or theme.

[0528] "New Information" refers to new or updated data that the system periodically collects.

[0529] "Generative AI model" refers to an artificial intelligence model used to classify and recommend information using machine learning techniques.

[0530] "Preprocessing" refers to data processing such as tokenization and stop word removal that is performed on collected text data in order to input it into a generative AI model.

[0531] "Recommended information" refers to information selected by a generative AI model based on a user's preferences and past behavior.

[0532] "Notification" refers to the act of sending specific information or messages from the system to the user.

[0533] "Feed Page" refers to a page in the user interface that displays recommendations and updates.

[0534] "Action data" refers to records of actions taken by users within the system (e.g., viewing articles, liking articles, etc.).

[0535] A "user profile" refers to a data set containing personalized information generated based on a user's interests, preferences, and past behavior.

[0536] "Database" refers to a data storage system for storing and managing collected information, user profiles, and classification results.

[0537] This invention is a system for efficiently obtaining information that a user needs or is interested in. The specific implementation method and operation of this system will be described below.

[0538] System configuration

[0539] This system is composed of a server, a terminal, and a generative AI model. The server is responsible for collecting, classifying, recommending, and notifying information, while the terminal provides the interface that users operate. The generative AI model is used to classify and recommend information.

[0540] Settings when you first log in

[0541] When a user logs in for the first time, the server generates an HTML form for the user to enter categories of interest (e.g., "Technical Information," "Product Releases," "Drinking Party Announcements," etc.). Specifically, this is implemented using a Python framework (e.g., Django, Flask).

[0542] The terminal displays this HTML form in the user's browser and collects the data entered by the user.

[0543] The user selects the category of interest and sends the setting information to the server via the send button.

[0544] The server takes this configuration information and stores it in a database (e.g. MySQL, PostgreSQL), which then serves as the user's profile.

[0545] Information collection and preprocessing

[0546] The server periodically collects new posts from the internal bulletin board using Python's requests library, BeautifulSoup, or the bulletin board's API.

[0547] The server converts the collected information into text format and performs preprocessing using the NLTK library and spaCy, which includes tokenizing the text and removing stop words.

[0548] Information classification

[0549] The generative AI model receives preprocessed text information as input and classifies it into pre-trained categories (e.g., "technical information," "drinking party," "important announcement," etc.) This AI model uses a transformer-based model (e.g., BERT, GPT-3).

[0550] The server receives the classification results from the generative AI model and stores them in a database by category.

[0551] Learning user preferences

[0552] The device records action data such as when a user views a feed page or clicks the "Like" button, using JavaScript event tracking technology.

[0553] The server stores this action data in a database and feeds it back into the generative AI model.

[0554] The generative AI model updates the user's preference profile based on this action data and recommends more appropriate information.

[0555] Recommendation generation and notification

[0556] Every time new information is saved in the database, the server requests the generative AI model to recommend appropriate information based on the user's profile.

[0557] The generative AI model selects recommended information based on the user's interest categories and latest action data, and returns the results to the server.

[0558] The server organizes the list of recommended information returned by the generative AI model and generates a notification message for each user.

[0559] The device displays the notification message sent from the server in a pop-up notification or notification center.

[0560] The server sends a request to the terminal to update the content of the feed page as needed.

[0561] The terminal updates the feed page in real time, allowing the user to efficiently browse the recommended information.

[0562] Specific examples

[0563] For example, when User A logs in for the first time, he or she specifies that he or she is interested in "technical information" and "drinking party announcements." The server stores this information in a database. Next, the server periodically collects new posts from the company bulletin board and sends them to the generative AI model, where they are classified as "technical information" or "drinking party announcements." When User A views the feed page or clicks the "Like" button, this behavioral data is sent to the server and fed back to the generative AI model. Based on this information, the server generates optimal recommendations for User A and displays them on the device as notification messages. Furthermore, the feed page is also updated, allowing User A to efficiently obtain the information of interest to him or her.

[0564] Prompt Sentence Examples

[0565] Below are some examples of prompts to input to the generative AI model.

[0566] Please recommend information that matches User A's interests. Interest categories: technical information, drinking party announcements. Please categorize the following new posts and provide appropriate recommendations.

[0567] Post 1: "In-depth article on new technical information"

[0568] Post 2: "Information about tonight's drinking party"

[0569] As described above, this system provides functions that allow users to efficiently obtain information they need or are interested in.

[0570] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0571] Step 1: First login setup

[0572] When the user logs in for the first time, the server generates an HTML form for entering the user's categories of interest (e.g., "Technical Information," "Product Releases," "Drinking Party Announcements," etc.) and sends it to the terminal. The input includes the categories selected by the user. The output is the generated HTML form displayed on the terminal as an HTML page.

[0573] The device displays this HTML form in the user's browser and collects the data entered by the user. Specific actions include rendering the HTML form and pressing a "Submit" button to proceed to the next step.

[0574] The user selects the category of interest and clicks the "Submit" button. The input includes the category selection. The output is the selected category data sent to the server.

[0575] The server stores the received setting information in a database and manages it as a user profile. The input includes category data selected by the user. The output includes the user profile stored in the database.

[0576] Step 2: Gather information

[0577] The server periodically (e.g., every hour) collects new posts from the internal message boards. Techniques used include the Python requests library, BeautifulSoup, or the message board API. Inputs include the latest message board URLs and API endpoints. Outputs include the collected new post data.

[0578] The server converts the collected information into text format and preprocesses it for the next step. Preprocessing includes tokenizing the text and removing stop words, and uses the NLTK library and spaCy. The input includes the collected raw post data. The output includes the converted text format and the preprocessed data.

[0579] Step 3: Classify the information

[0580] The server sends the preprocessed text information to a generative AI model, which uses a Transformer-based model (e.g., BERT, GPT-3). The input includes the preprocessed text data. The output includes the classification results from the generative AI model.

[0581] A generative AI model classifies information based on pre-trained categories (e.g., "technical information," "drinking party," "important announcement," etc.). The input includes pre-processed text data. The output includes classified category information.

[0582] The server receives the classification results from the generative AI model and stores them in a database by category. The input includes the classification result data. The output includes the categorized information stored in the database.

[0583] Step 4: Learning user preferences

[0584] The device records action data such as when a user views a feed page or clicks the "Like" button. JavaScript-based event tracking technology is used. The input includes the user's operation actions. The output includes the recorded action data.

[0585] The server periodically receives action data collected from the terminals and stores it in a database. The input includes the user's action data. The output includes the action data stored in the database.

[0586] The generative AI model updates the user's preference profile based on this action data. The input includes the action data. The output includes the updated user's preference profile.

[0587] Step 5: Generate recommendations

[0588] Each time new information is saved to the database, the server requests the generative AI model to recommend appropriate information based on the user's profile. The input includes the user's profile data and the latest information. The output includes the recommended information from the generative AI model.

[0589] The generative AI model selects recommended information based on the user's interest categories and latest action data, and returns the results to the server. The input includes the user's preference profile and latest information. The output includes a list of recommended information.

[0590] The server organizes the list of recommendations returned by the generative AI model and generates a notification message for each user. The input includes the recommendations from the generative AI model. The output includes the generated notification message.

[0591] Step 6: Notification and display of information

[0592] The device receives notification messages sent from the server and displays them in a popup notification or in the app's internal notification center using JavaScript. The input includes the notification message from the server. The output includes the displayed notification.

[0593] The server sends a request to the terminal to update the content of the feed page as needed. The input includes the update request. The output includes the update request.

[0594] The device updates the content of the feed page in real time based on this request, allowing the user to efficiently browse recommended information. The input includes an update request from the server. The output includes an updated feed page.

[0595] (Application example 1)

[0596] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0597] It is difficult for factory workers to quickly and efficiently obtain the necessary business information and important notifications, which can result in work delays and mistakes.In addition, there is a lack of means to properly filter and provide information that meets workers' interests and work needs, so there is a need to prevent confusion caused by information overload.

[0598] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0599] In this invention, the server includes a means for a user to input categories of interest when logging in for the first time, a means for collecting new information and classifying it by category using a generative AI model, a means for recommending the classified information based on the user's preferences, a means for notifying the user of the recommended information, and a means for displaying the recommended information on the display screen of an automated device. This allows factory workers to efficiently obtain the information they need and reduces work delays and errors.

[0600] "Means for users to input categories of interest when logging in for the first time" is a function that provides an interface for users to select and input categories of interest or concern from a list when they access the system for the first time.

[0601] "Means of collecting new information and categorizing it using a generative AI model" is the process of automatically organizing the latest collected information into predefined categories using a trained AI model.

[0602] "Means for recommending classified information based on user preferences" is a mechanism that prioritizes the presentation of appropriate information based on the user's past behavioral data and categories of interest.

[0603] The "means for notifying recommended information" refers to a method by which the system notifies the user of recommended information in the form of a message or an alert.

[0604] "Means for displaying recommended information on a display screen of an automated device" means a system that includes procedures for displaying information recommended to a user on the display of a robot or other automated device.

[0605] MODE FOR CARRYING OUT THE INVENTION

[0606] System Overview

[0607] This invention is a system for efficiently obtaining information that users need or are interested in. The system is composed of a server, a terminal, and a generative AI model. When a user first logs in, they set the information categories that interest them, and the server periodically collects new information from various sources within the factory and classifies it using the generative AI model. The system then notifies the user of recommended information based on the user's preferences and provides appropriate information, enabling the user to efficiently obtain the information they need.

[0608] Settings when you first log in

[0609] When a user logs in for the first time, the server displays a screen for the user to enter their hobbies and interest categories (e.g., "Technical Information," "Important Notices," etc.). The terminal (the browser or app on the user's device) displays the setting screen sent from the server and collects the information entered by the user. The user selects the categories of interest and sends the setting information to the server.

[0610] Information collection and classification

[0611] The server periodically (for example, every hour) collects new information from sources within the factory using APIs or scraping. The server converts the collected information into text format, performs preprocessing, and then inputs it into the generative AI model. The generative AI model classifies the information into categories it has learned in advance (for example, "technical information," "important notices," etc.). The server stores the classified information in a database by category.

[0612] Learning user preferences

[0613] The device records the articles the user has viewed and actions such as "likes," and periodically sends these to the server. The server stores the user's action data in a database and periodically feeds it back to the generative AI model. The generative AI model uses this action data to update the user's preference profile, enabling it to recommend more appropriate information.

[0614] Information recommendations and notifications

[0615] Each time new information is saved in the database, the server sends a request to the generative AI model to recommend appropriate information based on the user's profile. The generative AI model selects recommended information based on the user's profile and returns the results to the server. The server then compiles the recommended information for each user and generates a notification message. The terminal receives the notification message sent from the server and displays it on the display of the user or automated equipment.

[0616] Hardware / Software used

[0617] The hardware uses a factory robot and its display, and the software uses the Python programming language, a REST API, and Hugging Face's Transformers library.

[0618] Examples of concrete examples and prompts

[0619] For example, if a worker is interested in "technical information" or "important notices" while working in a factory, he can set these categories in the robot and efficiently obtain important new information.

[0620] Example prompt sentence:

[0621] Prompt: 'Category the following text: Technical Information, Important Notice, Other'

[0622] Text: 'New machine introduced.'

[0623] Model output: 'Technical information'

[0624] Text: 'About tonight's social gathering.'

[0625] Model output: 'Other'

[0626] This ensures that only the information that is important to the worker is displayed on the robot's display.

[0627] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0628] Step 1:

[0629] When a user logs in for the first time, the server displays a screen for the user to enter their hobbies and categories of interest. The user enters the categories of interest on the displayed screen and sends this information from the terminal to the server. The input data is in the form of a list of category names. The server saves this list in a database.

[0630] Step 2:

[0631] The server periodically collects new information from sources within the factory using APIs or scraping techniques, and sends the collected data to the server as raw data, which is received in raw text format.

[0632] Step 3:

[0633] The server converts the collected raw information into text format and performs preprocessing before inputting it into the generative AI model. Specifically, this includes removing unnecessary tags and noise, and formatting the text. The preprocessed data is sent to the generative AI model as clean text data.

[0634] Step 4:

[0635] The server sends the preprocessed information to the generative AI model, which then classifies it into categories. The generative AI model then analyzes the input text data and classifies it into the appropriate category based on the pre-trained prompts. The classification results are returned to the server as data with category labels.

[0636] Step 5:

[0637] The server stores the classification results returned by the generative AI model in a database, which contains pairs of category labels and text data, keeping the information organized by category.

[0638] Step 6:

[0639] The device records the articles the user has viewed and actions such as "likes" and periodically sends the recorded action data to the server. The action data includes the viewing time, viewed categories, and user ratings. The server stores this action data in a database.

[0640] Step 7:

[0641] The server periodically feeds back the saved user action data to the generative AI model. This feedback allows the generative AI model to update the user's preference profile and make more advanced recommendations. The data used for feedback includes the latest category information along with the user's action data.

[0642] Step 8:

[0643] Every time new information is saved in the database, the server sends a request to the generative AI model to recommend appropriate information based on the user's profile. The generative AI model then refers to the user's profile, selects the most appropriate information, and returns the results to the server.

[0644] Step 9:

[0645] The server compiles the recommendations returned by the generative AI model into a notification message for each user, which includes the text and category of the recommendations.

[0646] Step 10:

[0647] The terminal receives notification messages sent from the server and displays them on the display of the user or automated equipment, providing the displayed information in a format that can be easily referenced by the user.

[0648] This allows users to efficiently obtain the necessary information, improving work efficiency within the factory.

[0649] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0650] This invention is a system that efficiently acquires information that a user needs or is interested in, and further recognizes the user's emotions using an emotion engine and reflects them in the information recommendations. The specific implementation method and operation of this system are described below.

[0651] System Overview

[0652] The system is composed of a server, a terminal, a generation AI, and an emotion engine. When a user first logs in, they set the information categories that interest them. The server periodically collects new information from the company's bulletin board and uses the generation AI to classify it, while also recognizing the user's emotions. Based on the user's preferences and emotions, the system notifies the user of recommended information and displays appropriate information on the feed page, allowing the user to efficiently obtain the information they need.

[0653] Settings when you first log in

[0654] When a user logs in for the first time, the server displays a screen for the user to enter categories of hobbies and interests (e.g., "technical information," "product releases," "drinking party announcements," etc.).

[0655] The terminal (browser or app on the user's device) displays the setting screen sent from the server and collects the information entered by the user.

[0656] The user selects categories of interest and sends configuration information to the server.

[0657] Information collection and classification

[0658] The server periodically (for example, every hour) collects new posts from the internal bulletin board using an API or scraping.

[0659] The server converts the collected information into text format and performs preprocessing (e.g., removing HTML tags, extracting text).

[0660] The generative AI analyzes the pre-processed information and uses a pre-trained model to categorize it, for example, into categories such as "technical information," "drinking parties," and "important announcements."

[0661] The server stores the information classified by the generation AI in a database by category.

[0662] Learning user preferences and recognizing emotions

[0663] The terminal records the articles the user has viewed and actions such as "likes" and transmits the records to the server periodically (for example, in real time or daily).

[0664] The server records the user's action data in a database and provides feedback to the generating AI.

[0665] The generative AI uses this action data to update the user's preference profile, which includes which categories the user is particularly interested in.

[0666] The server uses an emotion engine to recognize the emotions (e.g., joy, excitement, sadness, etc.) of the user when viewing information. For example, it analyzes emotions from facial expressions and voices via a camera or microphone.

[0667] The emotion engine feeds the recognized emotion data back to the generative AI.

[0668] Information recommendations and notifications

[0669] Every time new information is saved in the database, the server sends a request to the generative AI to recommend appropriate information based on the user's preference profile and emotional data.

[0670] The generative AI selects recommendations based on the user's profile and emotions and returns the results to the server.

[0671] The server compiles the recommendation information returned by the generation AI for each user and generates a notification message.

[0672] The device receives notification messages sent from the server and displays them to the user, including push notifications and email notifications.

[0673] The server then sends a request to display the recommendations on the feed page.

[0674] The device displays recommended information on the feed page for easy reference by the user, allowing the user to efficiently obtain information that they need or that interests them.

[0675] Specific examples

[0676] For example, if User A sets his / her interest in "technical information" and "drinking party announcements" when he / she logs in for the first time, the server will use generative AI to collect and classify new posts related to technical information or drinking party announcements. The server will then recommend the information that best suits User A's preferences and emotions from the classified information and notify the device. Furthermore, the recommended information will also be displayed on User A's feed page, allowing User A to efficiently obtain information that interests him / her.

[0677] For example, if User A is viewing a "Technical Information" article and the emotion engine recognizes that the user is very excited, the generative AI will receive this emotion data and reflect it in future recommended information. In this way, by combining emotion engines, it becomes possible to provide information that better suits the user's needs.

[0678] In this way, this system allows users to efficiently obtain information necessary for their work or that they are interested in, without missing anything. By using emotion data, it becomes possible to provide information with even greater accuracy.

[0679] The processing flow will be explained below.

[0680] Step 1:

[0681] When a user logs in for the first time, the server displays a screen for the user to enter categories of hobbies and interests (e.g., "technical information," "product releases," "drinking party announcements," etc.).

[0682] Step 2:

[0683] The terminal displays the setting screen sent from the server and collects information on categories of interest selected by the user.

[0684] Step 3:

[0685] The user selects categories of interest and sends configuration information to the server.

[0686] Step 4:

[0687] The server stores the received configuration information in a database, which records the categories of interest for each user.

[0688] Step 5:

[0689] The server periodically (for example, every hour) collects information from the internal bulletin board by scraping or using an API.

[0690] Step 6:

[0691] The server converts the collected information into text format and performs preprocessing (e.g., removing HTML tags, extracting text).

[0692] Step 7:

[0693] The generative AI analyzes the pre-processed information and uses a pre-trained model to categorize it, for example, into categories such as "technical information," "drinking parties," and "important announcements."

[0694] Step 8:

[0695] The server stores the information classified by the generation AI in a database by category.

[0696] Step 9:

[0697] The terminal records the articles the user has viewed and actions such as "likes" and transmits the records to the server periodically (for example, in real time or daily).

[0698] Step 10:

[0699] The server records the user's action data in a database and provides feedback to the generating AI.

[0700] Step 11:

[0701] The generative AI uses this action data to update the user's preference profile, which includes which categories the user is particularly interested in.

[0702] Step 12:

[0703] While the user is browsing information, the device sends the data necessary to recognize the user's emotions (e.g., happiness, excitement, sadness) to the emotion engine, including facial and voice data captured via the camera and microphone.

[0704] Step 13:

[0705] The emotion engine analyzes the transmitted data and recognizes the user's emotions, for example, analyzing facial expressions for joy or sadness and detecting changes in tone from the voice.

[0706] Step 14:

[0707] The emotion engine feeds the recognized emotion data back to the generative AI.

[0708] Step 15:

[0709] Every time new information is saved in the database, the server sends a request to the generative AI to recommend appropriate information based on the user's preference profile and emotional data.

[0710] Step 16:

[0711] The generative AI selects recommendations based on the user's profile and emotions and returns the results to the server.

[0712] Step 17:

[0713] The server compiles the recommendation information returned by the generation AI for each user and generates a notification message.

[0714] Step 18:

[0715] The device receives notification messages sent from the server and displays them to the user, including push notifications and email notifications.

[0716] Step 19:

[0717] The server then sends a request to display the recommendations on the feed page.

[0718] Step 20:

[0719] The device displays recommended information on the feed page for easy reference by the user, allowing the user to efficiently obtain information that they need or that interests them.

[0720] The above are the detailed processing steps of this system.

[0721] Example 2

[0722] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0723] In today's information society, it is difficult for users to efficiently obtain the information they want when they need it. Furthermore, there is a lack of information provided that takes into account the user's preferences and emotions, so there is a need for a method to provide more personalized information. Therefore, it is necessary to develop a system that recommends the most appropriate information based on the user's interests and emotions.

[0724] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0725] In this invention, the server includes a means for allowing a user to input categories of interest when logging in for the first time, a means for periodically collecting new information and classifying it into categories using a generative AI after preprocessing, a means for recommending information based on the user's preference profile and emotions, and a means for displaying the recommended information in notifications and on the feed page, thereby enabling personalized information to be provided based on the user's interests and emotions.

[0726] "User" means an individual or corporation that uses this system to obtain information.

[0727] "First login" refers to the act of a user accessing this system for the first time and performing the necessary settings.

[0728] A "category" is a concept that indicates a classification of information that a user is interested in, and examples include "technical information" and "drinking party announcements."

[0729] "Periodic collection" means obtaining new information at regular intervals.

[0730] "Preprocessing" refers to the process of formatting and cleaning data before analyzing collected information.

[0731] "Generative AI" is an artificial intelligence program that uses machine learning and deep learning techniques to analyze data and make classifications and recommendations.

[0732] "Classifying by category" means organizing collected information based on predefined categories.

[0733] A "preference profile" is a user-specific data profile created based on the user's interests and concerns.

[0734] "Emotion" refers to the psychological state that a user expresses when viewing information, examples of which include "joy" and "excitement."

[0735] A "notification" is an information message that the system sends to the user, and includes, for example, a push notification or an email notification.

[0736] A "feed page" is a web page or app screen that a user can access to view a list of various information.

[0737] This invention is a system designed to enable users to efficiently obtain information of interest. Furthermore, by using an emotion engine to recognize the user's emotions and reflecting them in the recommended information, personalized information can be provided. An embodiment of this system will be specifically described below.

[0738] Settings when you first log in

[0739] When a user logs in for the first time, the server generates a setting screen for the user to enter categories of interest and sends it to the terminal. The setting screen includes options such as "Technical Information," "Product Releases," and "Drinking Party Announcements," for example.

[0740] The device displays the setting screen sent from the server to the user on the browser or within the app.

[0741] The user selects a category of interest and transmits the selection information from the terminal to the server.

[0742] Information collection and classification

[0743] The server periodically (for example, every hour) collects new posts from the internal bulletin board using APIs or scraping. The collected data is converted into text format and preprocessed (removing HTML tags and extracting text).

[0744] Generative AI analyzes the pre-processed information and classifies it into categories using a pre-trained model. This process uses machine learning algorithms. The classified information is divided into categories such as "technical information," "drinking party," and "important announcement."

[0745] The server stores the information classified by the generation AI in a database by category.

[0746] Learning user preferences and recognizing emotions

[0747] The device records the articles the user has viewed and actions such as "likes" and transmits the records to the server in real time or periodically.

[0748] The server records the user's action data in a database and feeds that data back to the generating AI.

[0749] The generative AI uses the action data to update the user's preference profile, for example by analyzing the user's interest in a particular category.

[0750] The server recognizes the user's emotions using an emotion engine, which analyzes the user's emotions from facial expressions and voice recorded via a camera and microphone, and feeds that data back to the generation AI.

[0751] Information recommendations and notifications

[0752] Every time new information is saved in the database, the server sends a request to the generative AI to recommend appropriate information based on the user's preference profile and emotional data.

[0753] The generative AI selects recommendations based on the user's profile and emotional data and returns the results to the server.

[0754] The server compiles the recommendation information returned by the generation AI for each user and generates a notification message.

[0755] The device receives notification messages sent from the server and displays them to the user, including push notifications and email notifications.

[0756] The server then sends a request to display the recommendations on the feed page.

[0757] The terminal displays the recommended information on the feed page so that the user can easily refer to it.

[0758] Examples of concrete examples and prompts

[0759] For example, if User A sets his / her interest in "technical information" and "drinking party announcements" when logging in for the first time, the server will collect new posts related to these categories and classify them using generative AI. From the classified information, the server will then recommend the information that best suits User A's preferences and emotions and notify the device. Furthermore, the recommended information will also be displayed on User A's feed page, allowing User A to efficiently obtain information that interests him / her.

[0760] Specific examples of prompts include:

[0761] Prompt statement

[0762] If user A specifies that he is interested in "Technical Information" and "Drinking Party Announcements" when he logs in for the first time, please explain how the server will collect new posts related to these topics and notify the user.

[0763] This system allows users to efficiently obtain information necessary for their work or that they are interested in. Furthermore, by utilizing emotion data, it becomes possible to provide information with even greater accuracy.

[0764] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0765] Step 1: First login setup

[0766] Input: The user logs in for the first time.

[0767] Specific behavior:

[0768] The server generates an initial login screen and sends it to the terminal.

[0769] The device displays a settings screen (e.g., category selection such as "Technical Information," "Product Releases," and "Drinking Party Announcements").

[0770] The user selects the categories of interest and transmits the information to the server via the terminal.

[0771] Output: The user's interest category information is saved on the server.

[0772] Step 2: Collecting and Preprocessing Information

[0773] Input: The time to collect comes periodically (e.g. every hour).

[0774] Specific behavior:

[0775] The server uses APIs and scraping to collect new posts from internal bulletin boards.

[0776] The server converts the collected information into text format and performs preprocessing such as removing HTML tags and extracting text.

[0777] Output: Preprocessed text data.

[0778] Step 3: Classifying information using generative AI

[0779] Input: Preprocessed text data.

[0780] Specific behavior:

[0781] Generative AI uses a trained model to classify pre-processed text data into categories, a process that uses machine learning algorithms.

[0782] The server stores the classified information in a database by category.

[0783] Output: Information broken down by category.

[0784] Step 4: Recording user actions

[0785] Input: An action a user takes while using the system (e.g., viewing an article, pressing like).

[0786] Specific behavior:

[0787] The device records user actions (e.g., viewing articles, pressing "like," etc.).

[0788] The device sends these action data to the server in real time or on a daily basis.

[0789] Output: User action data is recorded on the server.

[0790] Step 5: Update your preference profile

[0791] Input: User action data.

[0792] Specific behavior:

[0793] The server records the user's action data in a database and feeds that data back to the generating AI.

[0794] The generative AI analyzes the action data and updates the user's preference profile, which includes the user's interest in specific categories.

[0795] Output: Updated user preference profile.

[0796] Step 6: Recognize emotions

[0797] Input: Facial expressions and voice data as the user browses the information.

[0798] Specific behavior:

[0799] The server uses an emotion engine to recognize the user's emotions (e.g., joy, excitement, sadness, etc.).

[0800] The emotion engine analyzes emotions from facial expressions and voices collected through the camera and microphone, and feeds that data back to the generative AI.

[0801] Output: Emotion data is fed back to the generative AI.

[0802] Step 7: Recommend information

[0803] Input: Newly stored information in the database, user preference profile, and emotional data.

[0804] Specific behavior:

[0805] Every time new information is saved in the database, the server sends a request to the generative AI to recommend appropriate information based on the user's preference profile and emotional data.

[0806] The generative AI analyzes the user's profile and emotional data, selects the most appropriate information, and returns the results to the server.

[0807] Output: Recommended information.

[0808] Step 8: Notification and display of recommendations

[0809] Input: Recommendations returned by the generative AI.

[0810] Specific behavior:

[0811] The server compiles the recommendation information returned by the generation AI for each user and generates a notification message.

[0812] The device receives the notification message sent from the server and displays it to the user via push notification or email notification.

[0813] The server then sends a request to display the recommendations on the feed page.

[0814] The device displays the recommended information on the feed page for easy reference by the user.

[0815] Output: The recommendation that is notified to the user and displayed on the feed page.

[0816] (Application example 2)

[0817] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0818] In modern virtual stores, it is difficult for users to efficiently find products that match their interests and preferences from a vast amount of product information. Furthermore, product recommendations that take user emotions into consideration are rarely performed. This can lead to a poor user experience and a decrease in purchasing intent.

[0819] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a means for the user to input categories of interest when logging in for the first time, a means for collecting new information and classifying it by category using a generation AI, a means for recommending the classified information based on the user's preferences, a means for recognizing the user's emotions and adjusting the recommended information based thereon, and a means for notifying the user of the recommended information. This allows the optimal products to be recommended based on the user's preferences and emotions, enabling the user to efficiently find products of interest.

[0820] "Means for users to input categories of interest when logging in for the first time" refers to an interface or function that allows users to input categories of interest or concern when logging in to an application or system for the first time.

[0821] "Means of collecting new information" refers to the processes and techniques by which servers and related devices obtain the latest information from the Internet and related databases.

[0822] "Methods of categorizing using generative AI" refers to algorithms and models that use natural language processing and machine learning to classify collected information into specific categories.

[0823] "Means for making recommendations based on user preferences" refers to technology that selects optimal information and products based on the user's past behavioral data and set preferences and provides them to the user.

[0824] "Means for recognizing a user's emotions and adjusting recommended information based on them" refers to technology that uses devices such as cameras and microphones to analyze emotions from a user's facial expressions and voice, and then changes the recommended information and product content based on that emotional data.

[0825] "Means for notifying recommended information" refers to a function for sending messages or push notifications to inform users of recommended information or products.

[0826] The present invention relates to a system that enables a user to obtain optimal information and products based on their interests and preferences. Detailed embodiments of the present invention will be described below.

[0827] System Overview

[0828] This system consists of the following main components:

[0829] 1. Server: Collects, categorizes, and recommends information.

[0830] 2. Terminal: A device such as a smartphone or tablet operated by a user.

[0831] 3. Generative AI: Algorithms that categorize information and make recommendations.

[0832] 4. Emotion engine: An engine that analyzes user emotions and reflects them in recommendations.

[0833] Settings when you first log in

[0834] When a user logs in to the system for the first time, the server provides the user with an interface to input the categories of interest. The device (smartphone or tablet) displays this interface and sends the information input by the user to the server. For example, the user may input that they are interested in "games" or "gadgets."

[0835] Information collection and classification

[0836] The server periodically collects the latest information, using APIs from the internet or specific databases. The collected information is pre-processed, and the generating AI analyzes and classifies it into categories. For example, it can classify information on new gadgets or the latest game releases.

[0837] Learning user preferences and recognizing emotions

[0838] The device records the user's action data (e.g., browsing history, "likes," etc.) and sends it to the server. The server feeds this data back to the generation AI and updates the user's preference profile. The emotion engine also analyzes the user's emotions from facial images and voice data. For example, if the user is excited or sad, that emotional data is sent to the server.

[0839] Information recommendations and notifications

[0840] Each time new information is collected, the server sends a request to the generation AI to recommend appropriate information based on the user's preference profile and emotional data. Based on this request, the generation AI selects the most appropriate information for the user and returns it to the server. The server then generates this recommended information as a notification message and sends it to the device. For example, it sends a push notification such as, "A new game has been released! Your favorite game category has been updated!"

[0841] Usage example

[0842] For example, suppose a user logs in and specifies that they are interested in "games" and "gadgets." While the user is browsing articles in the "games" category, the emotion engine scans the user's facial expressions and recognizes that the user is very excited. The AI ​​receives this emotion data, and the next time new game information is collected, it prioritizes and recommends information that is likely to excite the user. For example, it sends a notification message to the user saying, "The latest VR game has been released!"

[0843] Prompt Sentence Examples

[0844] "User ID: abc123, Preferences: Games, Gadgets, Emotion: Excitement. Please recommend the best products for the user based on this. New product list: [Product A, Product B, Product C...]"

[0845] In this way, users can efficiently obtain the information and products they are most interested in in real time, improving their virtual store experience. Utilizing emotional data also enables more personalized recommendations.

[0846] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0847] Step 1:

[0848] This is a way for users to input categories of interest when logging in for the first time. When a user logs in using a smartphone or tablet device, the server displays an interface for the user to input categories of interest. The user selects the categories of interest (e.g., "games," "gadgets," etc.) from this interface, and that information is sent to the server. The input data is the user's interests and concerns, and the output is that information is saved on the server.

[0849] Step 2:

[0850] It is a method by which a server collects new information and classifies it into categories using generative AI. The server periodically uses APIs to collect the latest information (e.g., new product information, news articles, etc.) from the internet and related databases. This collected data is converted into text format and preprocessed (removing HTML tags, extracting text, etc.). The input data is the collected raw information, and the output is preprocessed text data.

[0851] Step 3:

[0852] This is a method by which the server uses generative AI to classify information into categories. Preprocessed text data is passed to the generative AI, which uses a model to classify it into the appropriate category. For example, articles about games are classified as "games," and articles about gadgets are classified as "gadgets." The input data is preprocessed text data, and the output is information classified into categories.

[0853] Step 4:

[0854] It is a means by which a device records user action data (e.g., article viewing, "likes," etc.) and sends it to a server. When a user views an article or performs a specific action on the device, that data is recorded by the device and periodically sent to the server. The input data is the user action data, and the output is that it is sent to the server and recorded.

[0855] Step 5:

[0856] The server has a means to recognize the user's emotions and adjust the recommended information based on them. The emotion engine analyzes the user's facial image and voice data to recognize the user's emotions (e.g., joy, excitement, sadness). The input data is the user's image and voice data, and the output is the analyzed emotion data.

[0857] Step 6:

[0858] The server sends a request to the generation AI to recommend appropriate information based on the user's preference profile and emotional data. The generation AI uses the profile and emotional data to select appropriate products and information and returns the results to the server. For example, a prompt such as "User ID: abc123, Preferences: Games, Gadgets, Emotion: Excitement. Please recommend the most suitable information for the user based on this information" is passed to the generation AI. The input data is the user's preference profile and emotional data, and the output is recommended information.

[0859] Step 7:

[0860] The server has a means to notify the user's device of the recommended information. The recommended information is generated by the server as a push notification or in-app notification and sent to the user's device. The input data is the recommended information, and the output is a notification message that is displayed on the device.

[0861] Step 8:

[0862] The device has a means to display recommended information on a feed page. When the user opens the feed page, the recommended information and products are listed and can be easily referenced. The input data is the recommended information, and the output is the information displayed on the feed page.

[0863] In this way, users can efficiently obtain information that best suits their preferences and feelings.

[0864] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0865] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0866] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0867] [Third embodiment]

[0868] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0869] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0870] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0871] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0872] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0873] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0874] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0875] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0876] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0877] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0878] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0879] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0880] This invention is a system for efficiently obtaining information that a user needs or is interested in. The specific implementation method and operation of this system will be described below.

[0881] System Overview

[0882] This system is composed of a server, a terminal, and a generation AI. When a user logs in for the first time, they set the information categories that interest them, and the server periodically collects new information from the company bulletin board and classifies it using the generation AI. The system then notifies the user of recommended information based on their preferences and displays appropriate information on the feed page, allowing the user to efficiently obtain the information they need.

[0883] Settings when you first log in

[0884] When a user logs in for the first time, the server displays a screen for the user to enter categories of hobbies and interests (e.g., "technical information," "product releases," "drinking party announcements," etc.).

[0885] The terminal (browser or app on the user's device) displays the setting screen sent from the server and collects the information entered by the user.

[0886] The user selects categories of interest and sends configuration information to the server.

[0887] Information collection and classification

[0888] The server periodically (for example, every hour) collects new posts from the internal bulletin board using an API or scraping.

[0889] The server converts the collected information into text format, preprocesses it, and then inputs it into the generative AI model.

[0890] The generative AI classifies the information into categories it has previously learned (e.g., "technical information," "drinking party," "important announcement," etc.).

[0891] The server stores the classified information in a database by category.

[0892] Learning user preferences

[0893] The device records the articles the user has viewed and actions such as "likes" and periodically transmits the records to the server.

[0894] The server stores the user's action data in a database and periodically provides feedback to the generating AI.

[0895] The generative AI uses this action data to update the user's preference profile, allowing it to recommend more relevant information.

[0896] Information recommendations and notifications

[0897] Every time new information is saved in the database, the server sends a request to the generative AI to recommend appropriate information based on the user's profile.

[0898] The generative AI selects recommended information based on the user's profile and returns the results to the server.

[0899] The server collects the recommended information for each user and generates a notification message.

[0900] The terminal receives the notification message sent from the server and displays it to the user.

[0901] The server then sends a request to display the recommendations on the feed page.

[0902] The device displays the recommended information on the feed page for easy reference by the user.

[0903] Specific examples

[0904] For example, if User A sets his / her interest in "technical information" and "drinking party announcements" when logging in for the first time, the server will use the generative AI to collect and classify new posts related to technical information or drinking party announcements. The server will then recommend the information that best suits User A's preferences from the classified information and notify the device. Furthermore, the recommended information will also be displayed on User A's feed page, allowing User A to efficiently obtain information of interest.

[0905] In this way, this system allows users to efficiently obtain information necessary for their work or information of interest without missing it.

[0906] The processing flow will be explained below.

[0907] Step 1:

[0908] When users log in for the first time, they are prompted to enter categories of hobbies and interests. Specifically, the screen displays options such as "Technical Information," "Product Releases," and "Drinking Party Announcements."

[0909] Step 2:

[0910] The device collects information about categories of interest selected by the user and sends it to the server in JSON format or similar.

[0911] Step 3:

[0912] The server stores the received configuration information in a database, which records the categories of interest for each user.

[0913] Step 4:

[0914] The server periodically collects information from the internal bulletin board by scraping or using an API. This process is executed, for example, every hour.

[0915] Step 5:

[0916] The server converts the collected information into text format and performs preprocessing (e.g., removing HTML tags, extracting text).

[0917] Step 6:

[0918] The generative AI analyzes the pre-processed information and uses a pre-trained model to categorize it, for example, into categories such as "technical information," "drinking parties," and "important announcements."

[0919] Step 7:

[0920] The server stores the information classified by the generation AI in a database by category.

[0921] Step 8:

[0922] The terminal records the articles the user has viewed and actions such as "likes" and transmits the records to the server periodically (for example, in real time or daily).

[0923] Step 9:

[0924] The server records the user's action data in a database and provides feedback to the generating AI.

[0925] Step 10:

[0926] The generative AI uses the feedback to update the user's preference profile, including which categories the user is most interested in.

[0927] Step 11:

[0928] Every time new information is saved in the database, the server sends a request to the generative AI to recommend appropriate information based on the user's profile.

[0929] Step 12:

[0930] The generative AI selects recommended information based on the user's profile and returns the results to the server.

[0931] Step 13:

[0932] The server compiles the recommendation information returned by the generation AI for each user and generates a notification message.

[0933] Step 14:

[0934] The device receives notification messages sent from the server and displays them to the user, including push notifications and email notifications.

[0935] Step 15:

[0936] The server then sends a request to display the recommendations on the feed page.

[0937] Step 16:

[0938] The device displays recommended information on the feed page for easy reference by the user, allowing the user to efficiently obtain information that they need or that interests them.

[0939] The above are the detailed processing steps of this system.

[0940] Example 1

[0941] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0942] The amount of information shared within a company or organization is enormous, making it difficult for users to efficiently obtain the information they need or are interested in. In addition, in many cases, information recommendations based on users' interests are not made, which can lead to users missing information or overlooking important information. This can lead to problems such as reduced work efficiency and satisfaction.

[0943] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0944] In this invention, the server includes a means for allowing a user to input categories of interest when logging in for the first time, a means for periodically collecting new information, a means for converting the collected information into text format and performing preprocessing, a means for classifying information by category using a generative AI model, a means for generating recommended information based on the user's preferences, a means for notifying the user of the generated recommended information, and a means for displaying the recommended information on a feed page, thereby enabling the user to efficiently obtain information of interest or need.

[0945] "User" refers to an individual or member of an organization who uses the system.

[0946] A "category" is a division that classifies information based on a particular group or theme.

[0947] "New Information" refers to new or updated data that the system periodically collects.

[0948] "Generative AI model" refers to an artificial intelligence model used to classify and recommend information using machine learning techniques.

[0949] "Preprocessing" refers to data processing such as tokenization and stop word removal that is performed on collected text data in order to input it into a generative AI model.

[0950] "Recommended information" refers to information selected by a generative AI model based on a user's preferences and past behavior.

[0951] "Notification" refers to the act of sending specific information or messages from the system to the user.

[0952] "Feed Page" refers to a page in the user interface that displays recommendations and updates.

[0953] "Action data" refers to records of actions taken by users within the system (e.g., viewing articles, liking articles, etc.).

[0954] A "user profile" refers to a data set containing personalized information generated based on a user's interests, preferences, and past behavior.

[0955] "Database" refers to a data storage system for storing and managing collected information, user profiles, and classification results.

[0956] This invention is a system for efficiently obtaining information that a user needs or is interested in. The specific implementation method and operation of this system will be described below.

[0957] System configuration

[0958] This system is composed of a server, a terminal, and a generative AI model. The server is responsible for collecting, classifying, recommending, and notifying information, while the terminal provides the interface that users operate. The generative AI model is used to classify and recommend information.

[0959] Settings when you first log in

[0960] When a user logs in for the first time, the server generates an HTML form for the user to enter categories of interest (e.g., "Technical Information," "Product Releases," "Drinking Party Announcements," etc.). Specifically, this is implemented using a Python framework (e.g., Django, Flask).

[0961] The terminal displays this HTML form in the user's browser and collects the data entered by the user.

[0962] The user selects the category of interest and sends the setting information to the server via the send button.

[0963] The server takes this configuration information and stores it in a database (e.g. MySQL, PostgreSQL), which then serves as the user's profile.

[0964] Information collection and preprocessing

[0965] The server periodically collects new posts from the internal bulletin board using Python's requests library, BeautifulSoup, or the bulletin board's API.

[0966] The server converts the collected information into text format and performs preprocessing using the NLTK library and spaCy, which includes tokenizing the text and removing stop words.

[0967] Information classification

[0968] The generative AI model receives preprocessed text information as input and classifies it into pre-trained categories (e.g., "technical information," "drinking party," "important announcement," etc.) This AI model uses a transformer-based model (e.g., BERT, GPT-3).

[0969] The server receives the classification results from the generative AI model and stores them in a database by category.

[0970] Learning user preferences

[0971] The device records action data such as when a user views a feed page or clicks the "Like" button, using JavaScript event tracking technology.

[0972] The server stores this action data in a database and feeds it back into the generative AI model.

[0973] The generative AI model updates the user's preference profile based on this action data and recommends more appropriate information.

[0974] Recommendation generation and notification

[0975] Every time new information is saved in the database, the server requests the generative AI model to recommend appropriate information based on the user's profile.

[0976] The generative AI model selects recommended information based on the user's interest categories and latest action data, and returns the results to the server.

[0977] The server organizes the list of recommended information returned by the generative AI model and generates a notification message for each user.

[0978] The device displays the notification message sent from the server in a pop-up notification or notification center.

[0979] The server sends a request to the terminal to update the content of the feed page as needed.

[0980] The terminal updates the feed page in real time, allowing the user to efficiently browse the recommended information.

[0981] Specific examples

[0982] For example, when User A logs in for the first time, he or she specifies that he or she is interested in "technical information" and "drinking party announcements." The server stores this information in a database. Next, the server periodically collects new posts from the company bulletin board and sends them to the generative AI model, where they are classified as "technical information" or "drinking party announcements." When User A views the feed page or clicks the "Like" button, this behavioral data is sent to the server and fed back to the generative AI model. Based on this information, the server generates optimal recommendations for User A and displays them on the device as notification messages. Furthermore, the feed page is also updated, allowing User A to efficiently obtain the information of interest to him or her.

[0983] Prompt Sentence Examples

[0984] Below are some examples of prompts to input to the generative AI model.

[0985] Please recommend information that matches User A's interests. Interest categories: technical information, drinking party announcements. Please categorize the following new posts and provide appropriate recommendations.

[0986] Post 1: "In-depth article on new technical information"

[0987] Post 2: "Information about tonight's drinking party"

[0988] As described above, this system provides functions that allow users to efficiently obtain information they need or are interested in.

[0989] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0990] Step 1: First login setup

[0991] When the user logs in for the first time, the server generates an HTML form for entering the user's categories of interest (e.g., "Technical Information," "Product Releases," "Drinking Party Announcements," etc.) and sends it to the terminal. The input includes the categories selected by the user. The output is the generated HTML form displayed on the terminal as an HTML page.

[0992] The device displays this HTML form in the user's browser and collects the data entered by the user. Specific actions include rendering the HTML form and pressing a "Submit" button to proceed to the next step.

[0993] The user selects the category of interest and clicks the "Submit" button. The input includes the category selection. The output is the selected category data sent to the server.

[0994] The server stores the received setting information in a database and manages it as a user profile. The input includes category data selected by the user. The output includes the user profile stored in the database.

[0995] Step 2: Gather information

[0996] The server periodically (e.g., every hour) collects new posts from the internal message boards. Techniques used include the Python requests library, BeautifulSoup, or the message board API. Inputs include the latest message board URLs and API endpoints. Outputs include the collected new post data.

[0997] The server converts the collected information into text format and preprocesses it for the next step. Preprocessing includes tokenizing the text and removing stop words, and uses the NLTK library and spaCy. The input includes the collected raw post data. The output includes the converted text format and the preprocessed data.

[0998] Step 3: Classify the information

[0999] The server sends the preprocessed text information to a generative AI model, which uses a Transformer-based model (e.g., BERT, GPT-3). The input includes the preprocessed text data. The output includes the classification results from the generative AI model.

[1000] A generative AI model classifies information based on pre-trained categories (e.g., "technical information," "drinking party," "important announcement," etc.). The input includes pre-processed text data. The output includes classified category information.

[1001] The server receives the classification results from the generative AI model and stores them in a database by category. The input includes the classification result data. The output includes the categorized information stored in the database.

[1002] Step 4: Learning user preferences

[1003] The device records action data such as when a user views a feed page or clicks the "Like" button. JavaScript-based event tracking technology is used. The input includes the user's operation actions. The output includes the recorded action data.

[1004] The server periodically receives action data collected from the terminals and stores it in a database. The input includes the user's action data. The output includes the action data stored in the database.

[1005] The generative AI model updates the user's preference profile based on this action data. The input includes the action data. The output includes the updated user's preference profile.

[1006] Step 5: Generate recommendations

[1007] Each time new information is saved to the database, the server requests the generative AI model to recommend appropriate information based on the user's profile. The input includes the user's profile data and the latest information. The output includes the recommended information from the generative AI model.

[1008] The generative AI model selects recommended information based on the user's interest categories and latest action data, and returns the results to the server. The input includes the user's preference profile and latest information. The output includes a list of recommended information.

[1009] The server organizes the list of recommendations returned by the generative AI model and generates a notification message for each user. The input includes the recommendations from the generative AI model. The output includes the generated notification message.

[1010] Step 6: Notification and display of information

[1011] The device receives notification messages sent from the server and displays them in a popup notification or in the app's internal notification center using JavaScript. The input includes the notification message from the server. The output includes the displayed notification.

[1012] The server sends a request to the terminal to update the content of the feed page as needed. The input includes the update request. The output includes the update request.

[1013] The device updates the content of the feed page in real time based on this request, allowing the user to efficiently browse recommended information. The input includes an update request from the server. The output includes an updated feed page.

[1014] (Application example 1)

[1015] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1016] It is difficult for factory workers to quickly and efficiently obtain the necessary business information and important notifications, which can result in work delays and mistakes.In addition, there is a lack of means to properly filter and provide information that meets workers' interests and work needs, so there is a need to prevent confusion caused by information overload.

[1017] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1018] In this invention, the server includes a means for a user to input categories of interest when logging in for the first time, a means for collecting new information and classifying it by category using a generative AI model, a means for recommending the classified information based on the user's preferences, a means for notifying the user of the recommended information, and a means for displaying the recommended information on the display screen of an automated device. This allows factory workers to efficiently obtain the information they need and reduces work delays and errors.

[1019] "Means for users to input categories of interest when logging in for the first time" is a function that provides an interface for users to select and input categories of interest or concern from a list when they access the system for the first time.

[1020] "Means of collecting new information and categorizing it using a generative AI model" is the process of automatically organizing the latest collected information into predefined categories using a trained AI model.

[1021] "Means for recommending classified information based on user preferences" is a mechanism that prioritizes the presentation of appropriate information based on the user's past behavioral data and categories of interest.

[1022] The "means for notifying recommended information" refers to a method by which the system notifies the user of recommended information in the form of a message or an alert.

[1023] "Means for displaying recommended information on a display screen of an automated device" means a system that includes procedures for displaying information recommended to a user on the display of a robot or other automated device.

[1024] MODE FOR CARRYING OUT THE INVENTION

[1025] System Overview

[1026] This invention is a system for efficiently obtaining information that users need or are interested in. The system is composed of a server, a terminal, and a generative AI model. When a user first logs in, they set the information categories that interest them, and the server periodically collects new information from various sources within the factory and classifies it using the generative AI model. The system then notifies the user of recommended information based on the user's preferences and provides appropriate information, enabling the user to efficiently obtain the information they need.

[1027] Settings when you first log in

[1028] When a user logs in for the first time, the server displays a screen for the user to enter their hobbies and interest categories (e.g., "Technical Information," "Important Notices," etc.). The terminal (the browser or app on the user's device) displays the setting screen sent from the server and collects the information entered by the user. The user selects the categories of interest and sends the setting information to the server.

[1029] Information collection and classification

[1030] The server periodically (for example, every hour) collects new information from sources within the factory using APIs or scraping. The server converts the collected information into text format, performs preprocessing, and then inputs it into the generative AI model. The generative AI model classifies the information into categories it has learned in advance (for example, "technical information," "important notices," etc.). The server stores the classified information in a database by category.

[1031] Learning user preferences

[1032] The device records the articles the user has viewed and actions such as "likes," and periodically sends these to the server. The server stores the user's action data in a database and periodically feeds it back to the generative AI model. The generative AI model uses this action data to update the user's preference profile, enabling it to recommend more appropriate information.

[1033] Information recommendations and notifications

[1034] Each time new information is saved in the database, the server sends a request to the generative AI model to recommend appropriate information based on the user's profile. The generative AI model selects recommended information based on the user's profile and returns the results to the server. The server then compiles the recommended information for each user and generates a notification message. The terminal receives the notification message sent from the server and displays it on the display of the user or automated equipment.

[1035] Hardware / Software used

[1036] The hardware uses a factory robot and its display, and the software uses the Python programming language, a REST API, and Hugging Face's Transformers library.

[1037] Examples of concrete examples and prompts

[1038] For example, if a worker is interested in "technical information" or "important notices" while working in a factory, he can set these categories in the robot and efficiently obtain important new information.

[1039] Example prompt sentence:

[1040] Prompt: 'Category the following text: Technical Information, Important Notice, Other'

[1041] Text: 'New machine introduced.'

[1042] Model output: 'Technical information'

[1043] Text: 'About tonight's social gathering.'

[1044] Model output: 'Other'

[1045] This ensures that only the information that is important to the worker is displayed on the robot's display.

[1046] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1047] Step 1:

[1048] When a user logs in for the first time, the server displays a screen for the user to enter their hobbies and categories of interest. The user enters the categories of interest on the displayed screen and sends this information from the terminal to the server. The input data is in the form of a list of category names. The server saves this list in a database.

[1049] Step 2:

[1050] The server periodically collects new information from sources within the factory using APIs or scraping techniques, and sends the collected data to the server as raw data, which is received in raw text format.

[1051] Step 3:

[1052] The server converts the collected raw information into text format and performs preprocessing before inputting it into the generative AI model. Specifically, this includes removing unnecessary tags and noise, and formatting the text. The preprocessed data is sent to the generative AI model as clean text data.

[1053] Step 4:

[1054] The server sends the preprocessed information to the generative AI model, which then classifies it into categories. The generative AI model then analyzes the input text data and classifies it into the appropriate category based on the pre-trained prompts. The classification results are returned to the server as data with category labels.

[1055] Step 5:

[1056] The server stores the classification results returned by the generative AI model in a database, which contains pairs of category labels and text data, keeping the information organized by category.

[1057] Step 6:

[1058] The device records the articles the user has viewed and actions such as "likes" and periodically sends the recorded action data to the server. The action data includes the viewing time, viewed categories, and user ratings. The server stores this action data in a database.

[1059] Step 7:

[1060] The server periodically feeds back the saved user action data to the generative AI model. This feedback allows the generative AI model to update the user's preference profile and make more advanced recommendations. The data used for feedback includes the latest category information along with the user's action data.

[1061] Step 8:

[1062] Every time new information is saved in the database, the server sends a request to the generative AI model to recommend appropriate information based on the user's profile. The generative AI model then refers to the user's profile, selects the most appropriate information, and returns the results to the server.

[1063] Step 9:

[1064] The server compiles the recommendations returned by the generative AI model into a notification message for each user, which includes the text and category of the recommendations.

[1065] Step 10:

[1066] The terminal receives notification messages sent from the server and displays them on the display of the user or automated equipment, providing the displayed information in a format that can be easily referenced by the user.

[1067] This allows users to efficiently obtain the necessary information, improving work efficiency within the factory.

[1068] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1069] This invention is a system that efficiently acquires information that a user needs or is interested in, and further recognizes the user's emotions using an emotion engine and reflects them in the information recommendations. The specific implementation method and operation of this system are described below.

[1070] System Overview

[1071] The system is composed of a server, a terminal, a generation AI, and an emotion engine. When a user first logs in, they set the information categories that interest them. The server periodically collects new information from the company's bulletin board and uses the generation AI to classify it, while also recognizing the user's emotions. Based on the user's preferences and emotions, the system notifies the user of recommended information and displays appropriate information on the feed page, allowing the user to efficiently obtain the information they need.

[1072] Settings when you first log in

[1073] When a user logs in for the first time, the server displays a screen for the user to enter categories of hobbies and interests (e.g., "technical information," "product releases," "drinking party announcements," etc.).

[1074] The terminal (browser or app on the user's device) displays the setting screen sent from the server and collects the information entered by the user.

[1075] The user selects categories of interest and sends configuration information to the server.

[1076] Information collection and classification

[1077] The server periodically (for example, every hour) collects new posts from the internal bulletin board using an API or scraping.

[1078] The server converts the collected information into text format and performs preprocessing (e.g., removing HTML tags, extracting text).

[1079] The generative AI analyzes the pre-processed information and uses a pre-trained model to categorize it, for example, into categories such as "technical information," "drinking parties," and "important announcements."

[1080] The server stores the information classified by the generation AI in a database by category.

[1081] Learning user preferences and recognizing emotions

[1082] The terminal records the articles the user has viewed and actions such as "likes" and transmits the records to the server periodically (for example, in real time or daily).

[1083] The server records the user's action data in a database and provides feedback to the generating AI.

[1084] The generative AI uses this action data to update the user's preference profile, which includes which categories the user is particularly interested in.

[1085] The server uses an emotion engine to recognize the emotions (e.g., joy, excitement, sadness, etc.) of the user when viewing information. For example, it analyzes emotions from facial expressions and voices via a camera or microphone.

[1086] The emotion engine feeds the recognized emotion data back to the generative AI.

[1087] Information recommendations and notifications

[1088] Every time new information is saved in the database, the server sends a request to the generative AI to recommend appropriate information based on the user's preference profile and emotional data.

[1089] The generative AI selects recommendations based on the user's profile and emotions and returns the results to the server.

[1090] The server compiles the recommendation information returned by the generation AI for each user and generates a notification message.

[1091] The device receives notification messages sent from the server and displays them to the user, including push notifications and email notifications.

[1092] The server then sends a request to display the recommendations on the feed page.

[1093] The device displays recommended information on the feed page for easy reference by the user, allowing the user to efficiently obtain information that they need or that interests them.

[1094] Specific examples

[1095] For example, if User A sets his / her interest in "technical information" and "drinking party announcements" when he / she logs in for the first time, the server will use generative AI to collect and classify new posts related to technical information or drinking party announcements. The server will then recommend the information that best suits User A's preferences and emotions from the classified information and notify the device. Furthermore, the recommended information will also be displayed on User A's feed page, allowing User A to efficiently obtain information that interests him / her.

[1096] For example, if User A is viewing a "Technical Information" article and the emotion engine recognizes that the user is very excited, the generative AI will receive this emotion data and reflect it in future recommended information. In this way, by combining emotion engines, it becomes possible to provide information that better suits the user's needs.

[1097] In this way, this system allows users to efficiently obtain information necessary for their work or that they are interested in, without missing anything. By using emotion data, it becomes possible to provide information with even greater accuracy.

[1098] The processing flow will be explained below.

[1099] Step 1:

[1100] When a user logs in for the first time, the server displays a screen for the user to enter categories of hobbies and interests (e.g., "technical information," "product releases," "drinking party announcements," etc.).

[1101] Step 2:

[1102] The terminal displays the setting screen sent from the server and collects information on categories of interest selected by the user.

[1103] Step 3:

[1104] The user selects categories of interest and sends configuration information to the server.

[1105] Step 4:

[1106] The server stores the received configuration information in a database, which records the categories of interest for each user.

[1107] Step 5:

[1108] The server periodically (for example, every hour) collects information from the internal bulletin board by scraping or using an API.

[1109] Step 6:

[1110] The server converts the collected information into text format and performs preprocessing (e.g., removing HTML tags, extracting text).

[1111] Step 7:

[1112] The generative AI analyzes the pre-processed information and uses a pre-trained model to categorize it, for example, into categories such as "technical information," "drinking parties," and "important announcements."

[1113] Step 8:

[1114] The server stores the information classified by the generation AI in a database by category.

[1115] Step 9:

[1116] The terminal records the articles the user has viewed and actions such as "likes" and transmits the records to the server periodically (for example, in real time or daily).

[1117] Step 10:

[1118] The server records the user's action data in a database and provides feedback to the generating AI.

[1119] Step 11:

[1120] The generative AI uses this action data to update the user's preference profile, which includes which categories the user is particularly interested in.

[1121] Step 12:

[1122] While the user is browsing information, the device sends the data necessary to recognize the user's emotions (e.g., happiness, excitement, sadness) to the emotion engine, including facial and voice data captured via the camera and microphone.

[1123] Step 13:

[1124] The emotion engine analyzes the transmitted data and recognizes the user's emotions, for example, analyzing facial expressions for joy or sadness and detecting changes in tone from the voice.

[1125] Step 14:

[1126] The emotion engine feeds the recognized emotion data back to the generative AI.

[1127] Step 15:

[1128] Every time new information is saved in the database, the server sends a request to the generative AI to recommend appropriate information based on the user's preference profile and emotional data.

[1129] Step 16:

[1130] The generative AI selects recommendations based on the user's profile and emotions and returns the results to the server.

[1131] Step 17:

[1132] The server compiles the recommendation information returned by the generation AI for each user and generates a notification message.

[1133] Step 18:

[1134] The device receives notification messages sent from the server and displays them to the user, including push notifications and email notifications.

[1135] Step 19:

[1136] The server then sends a request to display the recommendations on the feed page.

[1137] Step 20:

[1138] The device displays recommended information on the feed page for easy reference by the user, allowing the user to efficiently obtain information that they need or that interests them.

[1139] The above are the detailed processing steps of this system.

[1140] Example 2

[1141] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1142] In today's information society, it is difficult for users to efficiently obtain the information they want when they need it. Furthermore, there is a lack of information provided that takes into account the user's preferences and emotions, so there is a need for a method to provide more personalized information. Therefore, it is necessary to develop a system that recommends the most appropriate information based on the user's interests and emotions.

[1143] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1144] In this invention, the server includes a means for allowing a user to input categories of interest when logging in for the first time, a means for periodically collecting new information and classifying it into categories using a generative AI after preprocessing, a means for recommending information based on the user's preference profile and emotions, and a means for displaying the recommended information in notifications and on the feed page, thereby enabling personalized information to be provided based on the user's interests and emotions.

[1145] "User" means an individual or corporation that uses this system to obtain information.

[1146] "First login" refers to the act of a user accessing this system for the first time and performing the necessary settings.

[1147] A "category" is a concept that indicates a classification of information that a user is interested in, and examples include "technical information" and "drinking party announcements."

[1148] "Periodic collection" means obtaining new information at regular intervals.

[1149] "Preprocessing" refers to the process of formatting and cleaning data before analyzing collected information.

[1150] "Generative AI" is an artificial intelligence program that uses machine learning and deep learning techniques to analyze data and make classifications and recommendations.

[1151] "Classifying by category" means organizing collected information based on predefined categories.

[1152] A "preference profile" is a user-specific data profile created based on the user's interests and concerns.

[1153] "Emotion" refers to the psychological state that a user expresses when viewing information, examples of which include "joy" and "excitement."

[1154] A "notification" is an information message that the system sends to the user, and includes, for example, a push notification or an email notification.

[1155] A "feed page" is a web page or app screen that a user can access to view a list of various information.

[1156] This invention is a system designed to enable users to efficiently obtain information of interest. Furthermore, by using an emotion engine to recognize the user's emotions and reflecting them in the recommended information, personalized information can be provided. An embodiment of this system will be specifically described below.

[1157] Settings when you first log in

[1158] When a user logs in for the first time, the server generates a setting screen for the user to enter categories of interest and sends it to the terminal. The setting screen includes options such as "Technical Information," "Product Releases," and "Drinking Party Announcements," for example.

[1159] The device displays the setting screen sent from the server to the user on the browser or within the app.

[1160] The user selects a category of interest and transmits the selection information from the terminal to the server.

[1161] Information collection and classification

[1162] The server periodically (for example, every hour) collects new posts from the internal bulletin board using APIs or scraping. The collected data is converted into text format and preprocessed (removing HTML tags and extracting text).

[1163] Generative AI analyzes the pre-processed information and classifies it into categories using a pre-trained model. This process uses machine learning algorithms. The classified information is divided into categories such as "technical information," "drinking party," and "important announcement."

[1164] The server stores the information classified by the generation AI in a database by category.

[1165] Learning user preferences and recognizing emotions

[1166] The device records the articles the user has viewed and actions such as "likes" and transmits the records to the server in real time or periodically.

[1167] The server records the user's action data in a database and feeds that data back to the generating AI.

[1168] The generative AI uses the action data to update the user's preference profile, for example by analyzing the user's interest in a particular category.

[1169] The server recognizes the user's emotions using an emotion engine, which analyzes the user's emotions from facial expressions and voice recorded via a camera and microphone, and feeds that data back to the generation AI.

[1170] Information recommendations and notifications

[1171] Every time new information is saved in the database, the server sends a request to the generative AI to recommend appropriate information based on the user's preference profile and emotional data.

[1172] The generative AI selects recommendations based on the user's profile and emotional data and returns the results to the server.

[1173] The server compiles the recommendation information returned by the generation AI for each user and generates a notification message.

[1174] The device receives notification messages sent from the server and displays them to the user, including push notifications and email notifications.

[1175] The server then sends a request to display the recommendations on the feed page.

[1176] The terminal displays the recommended information on the feed page so that the user can easily refer to it.

[1177] Examples of concrete examples and prompts

[1178] For example, if User A sets his / her interest in "technical information" and "drinking party announcements" when logging in for the first time, the server will collect new posts related to these categories and classify them using generative AI. From the classified information, the server will then recommend the information that best suits User A's preferences and emotions and notify the device. Furthermore, the recommended information will also be displayed on User A's feed page, allowing User A to efficiently obtain information that interests him / her.

[1179] Specific examples of prompts include:

[1180] Prompt statement

[1181] If user A specifies that he is interested in "Technical Information" and "Drinking Party Announcements" when he logs in for the first time, please explain how the server will collect new posts related to these topics and notify the user.

[1182] This system allows users to efficiently obtain information necessary for their work or that they are interested in. Furthermore, by utilizing emotion data, it becomes possible to provide information with even greater accuracy.

[1183] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1184] Step 1: First login setup

[1185] Input: The user logs in for the first time.

[1186] Specific behavior:

[1187] The server generates an initial login screen and sends it to the terminal.

[1188] The device displays a settings screen (e.g., category selection such as "Technical Information," "Product Releases," and "Drinking Party Announcements").

[1189] The user selects the categories of interest and transmits the information to the server via the terminal.

[1190] Output: The user's interest category information is saved on the server.

[1191] Step 2: Collecting and Preprocessing Information

[1192] Input: The time to collect comes periodically (e.g. every hour).

[1193] Specific behavior:

[1194] The server uses APIs and scraping to collect new posts from internal bulletin boards.

[1195] The server converts the collected information into text format and performs preprocessing such as removing HTML tags and extracting text.

[1196] Output: Preprocessed text data.

[1197] Step 3: Classifying information using generative AI

[1198] Input: Preprocessed text data.

[1199] Specific behavior:

[1200] Generative AI uses a trained model to classify pre-processed text data into categories, a process that uses machine learning algorithms.

[1201] The server stores the classified information in a database by category.

[1202] Output: Information broken down by category.

[1203] Step 4: Recording user actions

[1204] Input: An action a user takes while using the system (e.g., viewing an article, pressing like).

[1205] Specific behavior:

[1206] The device records user actions (e.g., viewing articles, pressing "like," etc.).

[1207] The device sends these action data to the server in real time or on a daily basis.

[1208] Output: User action data is recorded on the server.

[1209] Step 5: Update your preference profile

[1210] Input: User action data.

[1211] Specific behavior:

[1212] The server records the user's action data in a database and feeds that data back to the generating AI.

[1213] The generative AI analyzes the action data and updates the user's preference profile, which includes the user's interest in specific categories.

[1214] Output: Updated user preference profile.

[1215] Step 6: Recognize emotions

[1216] Input: Facial expressions and voice data as the user browses the information.

[1217] Specific behavior:

[1218] The server uses an emotion engine to recognize the user's emotions (e.g., joy, excitement, sadness, etc.).

[1219] The emotion engine analyzes emotions from facial expressions and voices collected through the camera and microphone, and feeds that data back to the generative AI.

[1220] Output: Emotion data is fed back to the generative AI.

[1221] Step 7: Recommend information

[1222] Input: Newly stored information in the database, user preference profile, and emotional data.

[1223] Specific behavior:

[1224] Every time new information is saved in the database, the server sends a request to the generative AI to recommend appropriate information based on the user's preference profile and emotional data.

[1225] The generative AI analyzes the user's profile and emotional data, selects the most appropriate information, and returns the results to the server.

[1226] Output: Recommended information.

[1227] Step 8: Notification and display of recommendations

[1228] Input: Recommendations returned by the generative AI.

[1229] Specific behavior:

[1230] The server compiles the recommendation information returned by the generation AI for each user and generates a notification message.

[1231] The device receives the notification message sent from the server and displays it to the user via push notification or email notification.

[1232] The server then sends a request to display the recommendations on the feed page.

[1233] The device displays the recommended information on the feed page for easy reference by the user.

[1234] Output: The recommendation that is notified to the user and displayed on the feed page.

[1235] (Application example 2)

[1236] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1237] In modern virtual stores, it is difficult for users to efficiently find products that match their interests and preferences from a vast amount of product information. Furthermore, product recommendations that take user emotions into consideration are rarely performed. This can lead to a poor user experience and a decrease in purchasing intent.

[1238] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a means for the user to input categories of interest when logging in for the first time, a means for collecting new information and classifying it by category using a generation AI, a means for recommending the classified information based on the user's preferences, a means for recognizing the user's emotions and adjusting the recommended information based thereon, and a means for notifying the user of the recommended information. This allows the optimal products to be recommended based on the user's preferences and emotions, enabling the user to efficiently find products of interest.

[1239] "Means for users to input categories of interest when logging in for the first time" refers to an interface or function that allows users to input categories of interest or concern when logging in to an application or system for the first time.

[1240] "Means of collecting new information" refers to the processes and techniques by which servers and related devices obtain the latest information from the Internet and related databases.

[1241] "Methods of categorizing using generative AI" refers to algorithms and models that use natural language processing and machine learning to classify collected information into specific categories.

[1242] "Means for making recommendations based on user preferences" refers to technology that selects optimal information and products based on the user's past behavioral data and set preferences and provides them to the user.

[1243] "Means for recognizing a user's emotions and adjusting recommended information based on them" refers to technology that uses devices such as cameras and microphones to analyze emotions from a user's facial expressions and voice, and then changes the recommended information and product content based on that emotional data.

[1244] "Means for notifying recommended information" refers to a function for sending messages or push notifications to inform users of recommended information or products.

[1245] The present invention relates to a system that enables a user to obtain optimal information and products based on their interests and preferences. Detailed embodiments of the present invention will be described below.

[1246] System Overview

[1247] This system consists of the following main components:

[1248] 1. Server: Collects, categorizes, and recommends information.

[1249] 2. Terminal: A device such as a smartphone or tablet operated by a user.

[1250] 3. Generative AI: Algorithms that categorize information and make recommendations.

[1251] 4. Emotion engine: An engine that analyzes user emotions and reflects them in recommendations.

[1252] Settings when you first log in

[1253] When a user logs in to the system for the first time, the server provides the user with an interface to input the categories of interest. The device (smartphone or tablet) displays this interface and sends the information input by the user to the server. For example, the user may input that they are interested in "games" or "gadgets."

[1254] Information collection and classification

[1255] The server periodically collects the latest information, using APIs from the internet or specific databases. The collected information is pre-processed, and the generating AI analyzes and classifies it into categories. For example, it can classify information on new gadgets or the latest game releases.

[1256] Learning user preferences and recognizing emotions

[1257] The device records the user's action data (e.g., browsing history, "likes," etc.) and sends it to the server. The server feeds this data back to the generation AI and updates the user's preference profile. The emotion engine also analyzes the user's emotions from facial images and voice data. For example, if the user is excited or sad, that emotional data is sent to the server.

[1258] Information recommendations and notifications

[1259] Each time new information is collected, the server sends a request to the generation AI to recommend appropriate information based on the user's preference profile and emotional data. Based on this request, the generation AI selects the most appropriate information for the user and returns it to the server. The server then generates this recommended information as a notification message and sends it to the device. For example, it sends a push notification such as, "A new game has been released! Your favorite game category has been updated!"

[1260] Usage example

[1261] For example, suppose a user logs in and specifies that they are interested in "games" and "gadgets." While the user is browsing articles in the "games" category, the emotion engine scans the user's facial expressions and recognizes that the user is very excited. The AI ​​receives this emotion data, and the next time new game information is collected, it prioritizes and recommends information that is likely to excite the user. For example, it sends a notification message to the user saying, "The latest VR game has been released!"

[1262] Prompt Sentence Examples

[1263] "User ID: abc123, Preferences: Games, Gadgets, Emotion: Excitement. Please recommend the best products for the user based on this. New product list: [Product A, Product B, Product C...]"

[1264] In this way, users can efficiently obtain the information and products they are most interested in in real time, improving their virtual store experience. Utilizing emotional data also enables more personalized recommendations.

[1265] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1266] Step 1:

[1267] This is a way for users to input categories of interest when logging in for the first time. When a user logs in using a smartphone or tablet device, the server displays an interface for the user to input categories of interest. The user selects the categories of interest (e.g., "games," "gadgets," etc.) from this interface, and that information is sent to the server. The input data is the user's interests and concerns, and the output is that information is saved on the server.

[1268] Step 2:

[1269] It is a method by which a server collects new information and classifies it into categories using generative AI. The server periodically uses APIs to collect the latest information (e.g., new product information, news articles, etc.) from the internet and related databases. This collected data is converted into text format and preprocessed (removing HTML tags, extracting text, etc.). The input data is the collected raw information, and the output is preprocessed text data.

[1270] Step 3:

[1271] This is a method by which the server uses generative AI to classify information into categories. Preprocessed text data is passed to the generative AI, which uses a model to classify it into the appropriate category. For example, articles about games are classified as "games," and articles about gadgets are classified as "gadgets." The input data is preprocessed text data, and the output is information classified into categories.

[1272] Step 4:

[1273] It is a means by which a device records user action data (e.g., article viewing, "likes," etc.) and sends it to a server. When a user views an article or performs a specific action on the device, that data is recorded by the device and periodically sent to the server. The input data is the user action data, and the output is that it is sent to the server and recorded.

[1274] Step 5:

[1275] The server has a means to recognize the user's emotions and adjust the recommended information based on them. The emotion engine analyzes the user's facial image and voice data to recognize the user's emotions (e.g., joy, excitement, sadness). The input data is the user's image and voice data, and the output is the analyzed emotion data.

[1276] Step 6:

[1277] The server sends a request to the generation AI to recommend appropriate information based on the user's preference profile and emotional data. The generation AI uses the profile and emotional data to select appropriate products and information and returns the results to the server. For example, a prompt such as "User ID: abc123, Preferences: Games, Gadgets, Emotion: Excitement. Please recommend the most suitable information for the user based on this information" is passed to the generation AI. The input data is the user's preference profile and emotional data, and the output is recommended information.

[1278] Step 7:

[1279] The server has a means to notify the user's device of the recommended information. The recommended information is generated by the server as a push notification or in-app notification and sent to the user's device. The input data is the recommended information, and the output is a notification message that is displayed on the device.

[1280] Step 8:

[1281] The device has a means to display recommended information on a feed page. When the user opens the feed page, the recommended information and products are listed and can be easily referenced. The input data is the recommended information, and the output is the information displayed on the feed page.

[1282] In this way, users can efficiently obtain information that best suits their preferences and feelings.

[1283] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1284] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1285] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1286] [Fourth embodiment]

[1287] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1288] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1289] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1290] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1291] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1292] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1293] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1294] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1295] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1296] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1297] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1298] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1299] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1300] This invention is a system for efficiently obtaining information that a user needs or is interested in. The specific implementation method and operation of this system will be described below.

[1301] System Overview

[1302] This system is composed of a server, a terminal, and a generation AI. When a user logs in for the first time, they set the information categories that interest them, and the server periodically collects new information from the company bulletin board and classifies it using the generation AI. The system then notifies the user of recommended information based on their preferences and displays appropriate information on the feed page, allowing the user to efficiently obtain the information they need.

[1303] Settings when you first log in

[1304] When a user logs in for the first time, the server displays a screen for the user to enter categories of hobbies and interests (e.g., "technical information," "product releases," "drinking party announcements," etc.).

[1305] The terminal (browser or app on the user's device) displays the setting screen sent from the server and collects the information entered by the user.

[1306] The user selects categories of interest and sends configuration information to the server.

[1307] Information collection and classification

[1308] The server periodically (for example, every hour) collects new posts from the internal bulletin board using an API or scraping.

[1309] The server converts the collected information into text format, preprocesses it, and then inputs it into the generative AI model.

[1310] The generative AI classifies the information into categories it has previously learned (e.g., "technical information," "drinking party," "important announcement," etc.).

[1311] The server stores the classified information in a database by category.

[1312] Learning user preferences

[1313] The device records the articles the user has viewed and actions such as "likes" and periodically transmits the records to the server.

[1314] The server stores the user's action data in a database and periodically provides feedback to the generating AI.

[1315] The generative AI uses this action data to update the user's preference profile, allowing it to recommend more relevant information.

[1316] Information recommendations and notifications

[1317] Every time new information is saved in the database, the server sends a request to the generative AI to recommend appropriate information based on the user's profile.

[1318] The generative AI selects recommended information based on the user's profile and returns the results to the server.

[1319] The server collects the recommended information for each user and generates a notification message.

[1320] The terminal receives the notification message sent from the server and displays it to the user.

[1321] The server then sends a request to display the recommendations on the feed page.

[1322] The device displays the recommended information on the feed page for easy reference by the user.

[1323] Specific examples

[1324] For example, if User A sets his / her interest in "technical information" and "drinking party announcements" when logging in for the first time, the server will use the generative AI to collect and classify new posts related to technical information or drinking party announcements. The server will then recommend the information that best suits User A's preferences from the classified information and notify the device. Furthermore, the recommended information will also be displayed on User A's feed page, allowing User A to efficiently obtain information of interest.

[1325] In this way, this system allows users to efficiently obtain information necessary for their work or information of interest without missing it.

[1326] The processing flow will be explained below.

[1327] Step 1:

[1328] When users log in for the first time, they are prompted to enter categories of hobbies and interests. Specifically, the screen displays options such as "Technical Information," "Product Releases," and "Drinking Party Announcements."

[1329] Step 2:

[1330] The device collects information about categories of interest selected by the user and sends it to the server in JSON format or similar.

[1331] Step 3:

[1332] The server stores the received configuration information in a database, which records the categories of interest for each user.

[1333] Step 4:

[1334] The server periodically collects information from the internal bulletin board by scraping or using an API. This process is executed, for example, every hour.

[1335] Step 5:

[1336] The server converts the collected information into text format and performs preprocessing (e.g., removing HTML tags, extracting text).

[1337] Step 6:

[1338] The generative AI analyzes the pre-processed information and uses a pre-trained model to categorize it, for example, into categories such as "technical information," "drinking parties," and "important announcements."

[1339] Step 7:

[1340] The server stores the information classified by the generation AI in a database by category.

[1341] Step 8:

[1342] The terminal records the articles the user has viewed and actions such as "likes" and transmits the records to the server periodically (for example, in real time or daily).

[1343] Step 9:

[1344] The server records the user's action data in a database and provides feedback to the generating AI.

[1345] Step 10:

[1346] The generative AI uses the feedback to update the user's preference profile, including which categories the user is most interested in.

[1347] Step 11:

[1348] Every time new information is saved in the database, the server sends a request to the generative AI to recommend appropriate information based on the user's profile.

[1349] Step 12:

[1350] The generative AI selects recommended information based on the user's profile and returns the results to the server.

[1351] Step 13:

[1352] The server compiles the recommendation information returned by the generation AI for each user and generates a notification message.

[1353] Step 14:

[1354] The device receives notification messages sent from the server and displays them to the user, including push notifications and email notifications.

[1355] Step 15:

[1356] The server then sends a request to display the recommendations on the feed page.

[1357] Step 16:

[1358] The device displays recommended information on the feed page for easy reference by the user, allowing the user to efficiently obtain information that they need or that interests them.

[1359] The above are the detailed processing steps of this system.

[1360] Example 1

[1361] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1362] The amount of information shared within a company or organization is enormous, making it difficult for users to efficiently obtain the information they need or are interested in. In addition, in many cases, information recommendations based on users' interests are not made, which can lead to users missing information or overlooking important information. This can lead to problems such as reduced work efficiency and satisfaction.

[1363] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1364] In this invention, the server includes a means for allowing a user to input categories of interest when logging in for the first time, a means for periodically collecting new information, a means for converting the collected information into text format and performing preprocessing, a means for classifying information by category using a generative AI model, a means for generating recommended information based on the user's preferences, a means for notifying the user of the generated recommended information, and a means for displaying the recommended information on a feed page, thereby enabling the user to efficiently obtain information of interest or need.

[1365] "User" refers to an individual or member of an organization who uses the system.

[1366] A "category" is a division that classifies information based on a particular group or theme.

[1367] "New Information" refers to new or updated data that the system periodically collects.

[1368] "Generative AI model" refers to an artificial intelligence model used to classify and recommend information using machine learning techniques.

[1369] "Preprocessing" refers to data processing such as tokenization and stop word removal that is performed on collected text data in order to input it into a generative AI model.

[1370] "Recommended information" refers to information selected by a generative AI model based on a user's preferences and past behavior.

[1371] "Notification" refers to the act of sending specific information or messages from the system to the user.

[1372] "Feed Page" refers to a page in the user interface that displays recommendations and updates.

[1373] "Action data" refers to records of actions taken by users within the system (e.g., viewing articles, liking articles, etc.).

[1374] A "user profile" refers to a data set containing personalized information generated based on a user's interests, preferences, and past behavior.

[1375] "Database" refers to a data storage system for storing and managing collected information, user profiles, and classification results.

[1376] This invention is a system for efficiently obtaining information that a user needs or is interested in. The specific implementation method and operation of this system will be described below.

[1377] System configuration

[1378] This system is composed of a server, a terminal, and a generative AI model. The server is responsible for collecting, classifying, recommending, and notifying information, while the terminal provides the interface that users operate. The generative AI model is used to classify and recommend information.

[1379] Settings when you first log in

[1380] When a user logs in for the first time, the server generates an HTML form for the user to enter categories of interest (e.g., "Technical Information," "Product Releases," "Drinking Party Announcements," etc.). Specifically, this is implemented using a Python framework (e.g., Django, Flask).

[1381] The terminal displays this HTML form in the user's browser and collects the data entered by the user.

[1382] The user selects the category of interest and sends the setting information to the server via the send button.

[1383] The server takes this configuration information and stores it in a database (e.g. MySQL, PostgreSQL), which then serves as the user's profile.

[1384] Information collection and preprocessing

[1385] The server periodically collects new posts from the internal bulletin board using Python's requests library, BeautifulSoup, or the bulletin board's API.

[1386] The server converts the collected information into text format and performs preprocessing using the NLTK library and spaCy, which includes tokenizing the text and removing stop words.

[1387] Information classification

[1388] The generative AI model receives preprocessed text information as input and classifies it into pre-trained categories (e.g., "technical information," "drinking party," "important announcement," etc.) This AI model uses a transformer-based model (e.g., BERT, GPT-3).

[1389] The server receives the classification results from the generative AI model and stores them in a database by category.

[1390] Learning user preferences

[1391] The device records action data such as when a user views a feed page or clicks the "Like" button, using JavaScript event tracking technology.

[1392] The server stores this action data in a database and feeds it back into the generative AI model.

[1393] The generative AI model updates the user's preference profile based on this action data and recommends more appropriate information.

[1394] Recommendation generation and notification

[1395] Every time new information is saved in the database, the server requests the generative AI model to recommend appropriate information based on the user's profile.

[1396] The generative AI model selects recommended information based on the user's interest categories and latest action data, and returns the results to the server.

[1397] The server organizes the list of recommended information returned by the generative AI model and generates a notification message for each user.

[1398] The device displays the notification message sent from the server in a pop-up notification or notification center.

[1399] The server sends a request to the terminal to update the content of the feed page as needed.

[1400] The terminal updates the feed page in real time, allowing the user to efficiently browse the recommended information.

[1401] Specific examples

[1402] For example, when User A logs in for the first time, he or she specifies that he or she is interested in "technical information" and "drinking party announcements." The server stores this information in a database. Next, the server periodically collects new posts from the company bulletin board and sends them to the generative AI model, where they are classified as "technical information" or "drinking party announcements." When User A views the feed page or clicks the "Like" button, this behavioral data is sent to the server and fed back to the generative AI model. Based on this information, the server generates optimal recommendations for User A and displays them on the device as notification messages. Furthermore, the feed page is also updated, allowing User A to efficiently obtain the information of interest to him or her.

[1403] Prompt Sentence Examples

[1404] Below are some examples of prompts to input to the generative AI model.

[1405] Please recommend information that matches User A's interests. Interest categories: technical information, drinking party announcements. Please categorize the following new posts and provide appropriate recommendations.

[1406] Post 1: "In-depth article on new technical information"

[1407] Post 2: "Information about tonight's drinking party"

[1408] As described above, this system provides functions that allow users to efficiently obtain information they need or are interested in.

[1409] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1410] Step 1: First login setup

[1411] When the user logs in for the first time, the server generates an HTML form for entering the user's categories of interest (e.g., "Technical Information," "Product Releases," "Drinking Party Announcements," etc.) and sends it to the terminal. The input includes the categories selected by the user. The output is the generated HTML form displayed on the terminal as an HTML page.

[1412] The device displays this HTML form in the user's browser and collects the data entered by the user. Specific actions include rendering the HTML form and pressing a "Submit" button to proceed to the next step.

[1413] The user selects the category of interest and clicks the "Submit" button. The input includes the category selection. The output is the selected category data sent to the server.

[1414] The server stores the received setting information in a database and manages it as a user profile. The input includes category data selected by the user. The output includes the user profile stored in the database.

[1415] Step 2: Gather information

[1416] The server periodically (e.g., every hour) collects new posts from the internal message boards. Techniques used include the Python requests library, BeautifulSoup, or the message board API. Inputs include the latest message board URLs and API endpoints. Outputs include the collected new post data.

[1417] The server converts the collected information into text format and preprocesses it for the next step. Preprocessing includes tokenizing the text and removing stop words, and uses the NLTK library and spaCy. The input includes the collected raw post data. The output includes the converted text format and the preprocessed data.

[1418] Step 3: Classify the information

[1419] The server sends the preprocessed text information to a generative AI model, which uses a Transformer-based model (e.g., BERT, GPT-3). The input includes the preprocessed text data. The output includes the classification results from the generative AI model.

[1420] A generative AI model classifies information based on pre-trained categories (e.g., "technical information," "drinking party," "important announcement," etc.). The input includes pre-processed text data. The output includes classified category information.

[1421] The server receives the classification results from the generative AI model and stores them in a database by category. The input includes the classification result data. The output includes the categorized information stored in the database.

[1422] Step 4: Learning user preferences

[1423] The device records action data such as when a user views a feed page or clicks the "Like" button. JavaScript-based event tracking technology is used. The input includes the user's operation actions. The output includes the recorded action data.

[1424] The server periodically receives action data collected from the terminals and stores it in a database. The input includes the user's action data. The output includes the action data stored in the database.

[1425] The generative AI model updates the user's preference profile based on this action data. The input includes the action data. The output includes the updated user's preference profile.

[1426] Step 5: Generate recommendations

[1427] Each time new information is saved to the database, the server requests the generative AI model to recommend appropriate information based on the user's profile. The input includes the user's profile data and the latest information. The output includes the recommended information from the generative AI model.

[1428] The generative AI model selects recommended information based on the user's interest categories and latest action data, and returns the results to the server. The input includes the user's preference profile and latest information. The output includes a list of recommended information.

[1429] The server organizes the list of recommendations returned by the generative AI model and generates a notification message for each user. The input includes the recommendations from the generative AI model. The output includes the generated notification message.

[1430] Step 6: Notification and display of information

[1431] The device receives notification messages sent from the server and displays them in a popup notification or in the app's internal notification center using JavaScript. The input includes the notification message from the server. The output includes the displayed notification.

[1432] The server sends a request to the terminal to update the content of the feed page as needed. The input includes the update request. The output includes the update request.

[1433] The device updates the content of the feed page in real time based on this request, allowing the user to efficiently browse recommended information. The input includes an update request from the server. The output includes an updated feed page.

[1434] (Application example 1)

[1435] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1436] It is difficult for factory workers to quickly and efficiently obtain the necessary business information and important notifications, which can result in work delays and mistakes.In addition, there is a lack of means to properly filter and provide information that meets workers' interests and work needs, so there is a need to prevent confusion caused by information overload.

[1437] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1438] In this invention, the server includes a means for a user to input categories of interest when logging in for the first time, a means for collecting new information and classifying it by category using a generative AI model, a means for recommending the classified information based on the user's preferences, a means for notifying the user of the recommended information, and a means for displaying the recommended information on the display screen of an automated device. This allows factory workers to efficiently obtain the information they need and reduces work delays and errors.

[1439] "Means for users to input categories of interest when logging in for the first time" is a function that provides an interface for users to select and input categories of interest or concern from a list when they access the system for the first time.

[1440] "Means of collecting new information and categorizing it using a generative AI model" is the process of automatically organizing the latest collected information into predefined categories using a trained AI model.

[1441] "Means for recommending classified information based on user preferences" is a mechanism that prioritizes the presentation of appropriate information based on the user's past behavioral data and categories of interest.

[1442] The "means for notifying recommended information" refers to a method by which the system notifies the user of recommended information in the form of a message or an alert.

[1443] "Means for displaying recommended information on a display screen of an automated device" means a system that includes procedures for displaying information recommended to a user on the display of a robot or other automated device.

[1444] MODE FOR CARRYING OUT THE INVENTION

[1445] System Overview

[1446] This invention is a system for efficiently obtaining information that users need or are interested in. The system is composed of a server, a terminal, and a generative AI model. When a user first logs in, they set the information categories that interest them, and the server periodically collects new information from various sources within the factory and classifies it using the generative AI model. The system then notifies the user of recommended information based on the user's preferences and provides appropriate information, enabling the user to efficiently obtain the information they need.

[1447] Settings when you first log in

[1448] When a user logs in for the first time, the server displays a screen for the user to enter their hobbies and interest categories (e.g., "Technical Information," "Important Notices," etc.). The terminal (the browser or app on the user's device) displays the setting screen sent from the server and collects the information entered by the user. The user selects the categories of interest and sends the setting information to the server.

[1449] Information collection and classification

[1450] The server periodically (for example, every hour) collects new information from sources within the factory using APIs or scraping. The server converts the collected information into text format, performs preprocessing, and then inputs it into the generative AI model. The generative AI model classifies the information into categories it has learned in advance (for example, "technical information," "important notices," etc.). The server stores the classified information in a database by category.

[1451] Learning user preferences

[1452] The device records the articles the user has viewed and actions such as "likes," and periodically sends these to the server. The server stores the user's action data in a database and periodically feeds it back to the generative AI model. The generative AI model uses this action data to update the user's preference profile, enabling it to recommend more appropriate information.

[1453] Information recommendations and notifications

[1454] Each time new information is saved in the database, the server sends a request to the generative AI model to recommend appropriate information based on the user's profile. The generative AI model selects recommended information based on the user's profile and returns the results to the server. The server then compiles the recommended information for each user and generates a notification message. The terminal receives the notification message sent from the server and displays it on the display of the user or automated equipment.

[1455] Hardware / Software used

[1456] The hardware uses a factory robot and its display, and the software uses the Python programming language, a REST API, and Hugging Face's Transformers library.

[1457] Examples of concrete examples and prompts

[1458] For example, if a worker is interested in "technical information" or "important notices" while working in a factory, he can set these categories in the robot and efficiently obtain important new information.

[1459] Example prompt sentence:

[1460] Prompt: 'Category the following text: Technical Information, Important Notice, Other'

[1461] Text: 'New machine introduced.'

[1462] Model output: 'Technical information'

[1463] Text: 'About tonight's social gathering.'

[1464] Model output: 'Other'

[1465] This ensures that only the information that is important to the worker is displayed on the robot's display.

[1466] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1467] Step 1:

[1468] When a user logs in for the first time, the server displays a screen for the user to enter their hobbies and categories of interest. The user enters the categories of interest on the displayed screen and sends this information from the terminal to the server. The input data is in the form of a list of category names. The server saves this list in a database.

[1469] Step 2:

[1470] The server periodically collects new information from sources within the factory using APIs or scraping techniques, and sends the collected data to the server as raw data, which is received in raw text format.

[1471] Step 3:

[1472] The server converts the collected raw information into text format and performs preprocessing before inputting it into the generative AI model. Specifically, this includes removing unnecessary tags and noise, and formatting the text. The preprocessed data is sent to the generative AI model as clean text data.

[1473] Step 4:

[1474] The server sends the preprocessed information to the generative AI model, which then classifies it into categories. The generative AI model then analyzes the input text data and classifies it into the appropriate category based on the pre-trained prompts. The classification results are returned to the server as data with category labels.

[1475] Step 5:

[1476] The server stores the classification results returned by the generative AI model in a database, which contains pairs of category labels and text data, keeping the information organized by category.

[1477] Step 6:

[1478] The device records the articles the user has viewed and actions such as "likes" and periodically sends the recorded action data to the server. The action data includes the viewing time, viewed categories, and user ratings. The server stores this action data in a database.

[1479] Step 7:

[1480] The server periodically feeds back the saved user action data to the generative AI model. This feedback allows the generative AI model to update the user's preference profile and make more advanced recommendations. The data used for feedback includes the latest category information along with the user's action data.

[1481] Step 8:

[1482] Every time new information is saved in the database, the server sends a request to the generative AI model to recommend appropriate information based on the user's profile. The generative AI model then refers to the user's profile, selects the most appropriate information, and returns the results to the server.

[1483] Step 9:

[1484] The server compiles the recommendations returned by the generative AI model into a notification message for each user, which includes the text and category of the recommendations.

[1485] Step 10:

[1486] The terminal receives notification messages sent from the server and displays them on the display of the user or automated equipment, providing the displayed information in a format that can be easily referenced by the user.

[1487] This allows users to efficiently obtain the necessary information, improving work efficiency within the factory.

[1488] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1489] This invention is a system that efficiently acquires information that a user needs or is interested in, and further recognizes the user's emotions using an emotion engine and reflects them in the information recommendations. The specific implementation method and operation of this system are described below.

[1490] System Overview

[1491] The system is composed of a server, a terminal, a generation AI, and an emotion engine. When a user first logs in, they set the information categories that interest them. The server periodically collects new information from the company's bulletin board and uses the generation AI to classify it, while also recognizing the user's emotions. Based on the user's preferences and emotions, the system notifies the user of recommended information and displays appropriate information on the feed page, allowing the user to efficiently obtain the information they need.

[1492] Settings when you first log in

[1493] When a user logs in for the first time, the server displays a screen for the user to enter categories of hobbies and interests (e.g., "technical information," "product releases," "drinking party announcements," etc.).

[1494] The terminal (browser or app on the user's device) displays the setting screen sent from the server and collects the information entered by the user.

[1495] The user selects categories of interest and sends configuration information to the server.

[1496] Information collection and classification

[1497] The server periodically (for example, every hour) collects new posts from the internal bulletin board using an API or scraping.

[1498] The server converts the collected information into text format and performs preprocessing (e.g., removing HTML tags, extracting text).

[1499] The generative AI analyzes the pre-processed information and uses a pre-trained model to categorize it, for example, into categories such as "technical information," "drinking parties," and "important announcements."

[1500] The server stores the information classified by the generation AI in a database by category.

[1501] Learning user preferences and recognizing emotions

[1502] The terminal records the articles the user has viewed and actions such as "likes" and transmits the records to the server periodically (for example, in real time or daily).

[1503] The server records the user's action data in a database and provides feedback to the generating AI.

[1504] The generative AI uses this action data to update the user's preference profile, which includes which categories the user is particularly interested in.

[1505] The server uses an emotion engine to recognize the emotions (e.g., joy, excitement, sadness, etc.) of the user when viewing information. For example, it analyzes emotions from facial expressions and voices via a camera or microphone.

[1506] The emotion engine feeds the recognized emotion data back to the generative AI.

[1507] Information recommendations and notifications

[1508] Every time new information is saved in the database, the server sends a request to the generative AI to recommend appropriate information based on the user's preference profile and emotional data.

[1509] The generative AI selects recommendations based on the user's profile and emotions and returns the results to the server.

[1510] The server compiles the recommendation information returned by the generation AI for each user and generates a notification message.

[1511] The device receives notification messages sent from the server and displays them to the user, including push notifications and email notifications.

[1512] The server then sends a request to display the recommendations on the feed page.

[1513] The device displays recommended information on the feed page for easy reference by the user, allowing the user to efficiently obtain information that they need or that interests them.

[1514] Specific examples

[1515] For example, if User A sets his / her interest in "technical information" and "drinking party announcements" when he / she logs in for the first time, the server will use generative AI to collect and classify new posts related to technical information or drinking party announcements. The server will then recommend the information that best suits User A's preferences and emotions from the classified information and notify the device. Furthermore, the recommended information will also be displayed on User A's feed page, allowing User A to efficiently obtain information that interests him / her.

[1516] For example, if User A is viewing a "Technical Information" article and the emotion engine recognizes that the user is very excited, the generative AI will receive this emotion data and reflect it in future recommended information. In this way, by combining emotion engines, it becomes possible to provide information that better suits the user's needs.

[1517] In this way, this system allows users to efficiently obtain information necessary for their work or that they are interested in, without missing anything. By using emotion data, it becomes possible to provide information with even greater accuracy.

[1518] The processing flow will be explained below.

[1519] Step 1:

[1520] When a user logs in for the first time, the server displays a screen for the user to enter categories of hobbies and interests (e.g., "technical information," "product releases," "drinking party announcements," etc.).

[1521] Step 2:

[1522] The terminal displays the setting screen sent from the server and collects information on categories of interest selected by the user.

[1523] Step 3:

[1524] The user selects categories of interest and sends configuration information to the server.

[1525] Step 4:

[1526] The server stores the received configuration information in a database, which records the categories of interest for each user.

[1527] Step 5:

[1528] The server periodically (for example, every hour) collects information from the internal bulletin board by scraping or using an API.

[1529] Step 6:

[1530] The server converts the collected information into text format and performs preprocessing (e.g., removing HTML tags, extracting text).

[1531] Step 7:

[1532] The generative AI analyzes the pre-processed information and uses a pre-trained model to categorize it, for example, into categories such as "technical information," "drinking parties," and "important announcements."

[1533] Step 8:

[1534] The server stores the information classified by the generation AI in a database by category.

[1535] Step 9:

[1536] The terminal records the articles the user has viewed and actions such as "likes" and transmits the records to the server periodically (for example, in real time or daily).

[1537] Step 10:

[1538] The server records the user's action data in a database and provides feedback to the generating AI.

[1539] Step 11:

[1540] The generative AI uses this action data to update the user's preference profile, which includes which categories the user is particularly interested in.

[1541] Step 12:

[1542] While the user is browsing information, the device sends the data necessary to recognize the user's emotions (e.g., happiness, excitement, sadness) to the emotion engine, including facial and voice data captured via the camera and microphone.

[1543] Step 13:

[1544] The emotion engine analyzes the transmitted data and recognizes the user's emotions, for example, analyzing facial expressions for joy or sadness and detecting changes in tone from the voice.

[1545] Step 14:

[1546] The emotion engine feeds the recognized emotion data back to the generative AI.

[1547] Step 15:

[1548] Every time new information is saved in the database, the server sends a request to the generative AI to recommend appropriate information based on the user's preference profile and emotional data.

[1549] Step 16:

[1550] The generative AI selects recommendations based on the user's profile and emotions and returns the results to the server.

[1551] Step 17:

[1552] The server compiles the recommendation information returned by the generation AI for each user and generates a notification message.

[1553] Step 18:

[1554] The device receives notification messages sent from the server and displays them to the user, including push notifications and email notifications.

[1555] Step 19:

[1556] The server then sends a request to display the recommendations on the feed page.

[1557] Step 20:

[1558] The device displays recommended information on the feed page for easy reference by the user, allowing the user to efficiently obtain information that they need or that interests them.

[1559] The above are the detailed processing steps of this system.

[1560] Example 2

[1561] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1562] In today's information society, it is difficult for users to efficiently obtain the information they want when they need it. Furthermore, there is a lack of information provided that takes into account the user's preferences and emotions, so there is a need for a method to provide more personalized information. Therefore, it is necessary to develop a system that recommends the most appropriate information based on the user's interests and emotions.

[1563] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1564] In this invention, the server includes a means for allowing a user to input categories of interest when logging in for the first time, a means for periodically collecting new information and classifying it into categories using a generative AI after preprocessing, a means for recommending information based on the user's preference profile and emotions, and a means for displaying the recommended information in notifications and on the feed page, thereby enabling personalized information to be provided based on the user's interests and emotions.

[1565] "User" means an individual or corporation that uses this system to obtain information.

[1566] "First login" refers to the act of a user accessing this system for the first time and performing the necessary settings.

[1567] A "category" is a concept that indicates a classification of information that a user is interested in, and examples include "technical information" and "drinking party announcements."

[1568] "Periodic collection" means obtaining new information at regular intervals.

[1569] "Preprocessing" refers to the process of formatting and cleaning data before analyzing collected information.

[1570] "Generative AI" is an artificial intelligence program that uses machine learning and deep learning techniques to analyze data and make classifications and recommendations.

[1571] "Classifying by category" means organizing collected information based on predefined categories.

[1572] A "preference profile" is a user-specific data profile created based on the user's interests and concerns.

[1573] "Emotion" refers to the psychological state that a user expresses when viewing information, examples of which include "joy" and "excitement."

[1574] A "notification" is an information message that the system sends to the user, and includes, for example, a push notification or an email notification.

[1575] A "feed page" is a web page or app screen that a user can access to view a list of various information.

[1576] This invention is a system designed to enable users to efficiently obtain information of interest. Furthermore, by using an emotion engine to recognize the user's emotions and reflecting them in the recommended information, personalized information can be provided. An embodiment of this system will be specifically described below.

[1577] Settings when you first log in

[1578] When a user logs in for the first time, the server generates a setting screen for the user to enter categories of interest and sends it to the terminal. The setting screen includes options such as "Technical Information," "Product Releases," and "Drinking Party Announcements," for example.

[1579] The device displays the setting screen sent from the server to the user on the browser or within the app.

[1580] The user selects a category of interest and transmits the selection information from the terminal to the server.

[1581] Information collection and classification

[1582] The server periodically (for example, every hour) collects new posts from the internal bulletin board using APIs or scraping. The collected data is converted into text format and preprocessed (removing HTML tags and extracting text).

[1583] Generative AI analyzes the pre-processed information and classifies it into categories using a pre-trained model. This process uses machine learning algorithms. The classified information is divided into categories such as "technical information," "drinking party," and "important announcement."

[1584] The server stores the information classified by the generation AI in a database by category.

[1585] Learning user preferences and recognizing emotions

[1586] The device records the articles the user has viewed and actions such as "likes" and transmits the records to the server in real time or periodically.

[1587] The server records the user's action data in a database and feeds that data back to the generating AI.

[1588] The generative AI uses the action data to update the user's preference profile, for example by analyzing the user's interest in a particular category.

[1589] The server recognizes the user's emotions using an emotion engine, which analyzes the user's emotions from facial expressions and voice recorded via a camera and microphone, and feeds that data back to the generation AI.

[1590] Information recommendations and notifications

[1591] Every time new information is saved in the database, the server sends a request to the generative AI to recommend appropriate information based on the user's preference profile and emotional data.

[1592] The generative AI selects recommendations based on the user's profile and emotional data and returns the results to the server.

[1593] The server compiles the recommendation information returned by the generation AI for each user and generates a notification message.

[1594] The device receives notification messages sent from the server and displays them to the user, including push notifications and email notifications.

[1595] The server then sends a request to display the recommendations on the feed page.

[1596] The terminal displays the recommended information on the feed page so that the user can easily refer to it.

[1597] Examples of concrete examples and prompts

[1598] For example, if User A sets his / her interest in "technical information" and "drinking party announcements" when logging in for the first time, the server will collect new posts related to these categories and classify them using generative AI. From the classified information, the server will then recommend the information that best suits User A's preferences and emotions and notify the device. Furthermore, the recommended information will also be displayed on User A's feed page, allowing User A to efficiently obtain information that interests him / her.

[1599] Specific examples of prompts include:

[1600] Prompt statement

[1601] If user A specifies that he is interested in "Technical Information" and "Drinking Party Announcements" when he logs in for the first time, please explain how the server will collect new posts related to these topics and notify the user.

[1602] This system allows users to efficiently obtain information necessary for their work or that they are interested in. Furthermore, by utilizing emotion data, it becomes possible to provide information with even greater accuracy.

[1603] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1604] Step 1: First login setup

[1605] Input: The user logs in for the first time.

[1606] Specific behavior:

[1607] The server generates an initial login screen and sends it to the terminal.

[1608] The device displays a settings screen (e.g., category selection such as "Technical Information," "Product Releases," and "Drinking Party Announcements").

[1609] The user selects the categories of interest and transmits the information to the server via the terminal.

[1610] Output: The user's interest category information is saved on the server.

[1611] Step 2: Collecting and Preprocessing Information

[1612] Input: The time to collect comes periodically (e.g. every hour).

[1613] Specific behavior:

[1614] The server uses APIs and scraping to collect new posts from internal bulletin boards.

[1615] The server converts the collected information into text format and performs preprocessing such as removing HTML tags and extracting text.

[1616] Output: Preprocessed text data.

[1617] Step 3: Classifying information using generative AI

[1618] Input: Preprocessed text data.

[1619] Specific behavior:

[1620] Generative AI uses a trained model to classify pre-processed text data into categories, a process that uses machine learning algorithms.

[1621] The server stores the classified information in a database by category.

[1622] Output: Information broken down by category.

[1623] Step 4: Recording user actions

[1624] Input: An action a user takes while using the system (e.g., viewing an article, pressing like).

[1625] Specific behavior:

[1626] The device records user actions (e.g., viewing articles, pressing "like," etc.).

[1627] The device sends these action data to the server in real time or on a daily basis.

[1628] Output: User action data is recorded on the server.

[1629] Step 5: Update your preference profile

[1630] Input: User action data.

[1631] Specific behavior:

[1632] The server records the user's action data in a database and feeds that data back to the generating AI.

[1633] The generative AI analyzes the action data and updates the user's preference profile, which includes the user's interest in specific categories.

[1634] Output: Updated user preference profile.

[1635] Step 6: Recognize emotions

[1636] Input: Facial expressions and voice data as the user browses the information.

[1637] Specific behavior:

[1638] The server uses an emotion engine to recognize the user's emotions (e.g., joy, excitement, sadness, etc.).

[1639] The emotion engine analyzes emotions from facial expressions and voices collected through the camera and microphone, and feeds that data back to the generative AI.

[1640] Output: Emotion data is fed back to the generative AI.

[1641] Step 7: Recommend information

[1642] Input: Newly stored information in the database, user preference profile, and emotional data.

[1643] Specific behavior:

[1644] Every time new information is saved in the database, the server sends a request to the generative AI to recommend appropriate information based on the user's preference profile and emotional data.

[1645] The generative AI analyzes the user's profile and emotional data, selects the most appropriate information, and returns the results to the server.

[1646] Output: Recommended information.

[1647] Step 8: Notification and display of recommendations

[1648] Input: Recommendations returned by the generative AI.

[1649] Specific behavior:

[1650] The server compiles the recommendation information returned by the generation AI for each user and generates a notification message.

[1651] The device receives the notification message sent from the server and displays it to the user via push notification or email notification.

[1652] The server then sends a request to display the recommendations on the feed page.

[1653] The device displays the recommended information on the feed page for easy reference by the user.

[1654] Output: The recommendation that is notified to the user and displayed on the feed page.

[1655] (Application example 2)

[1656] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1657] In modern virtual stores, it is difficult for users to efficiently find products that match their interests and preferences from a vast amount of product information. Furthermore, product recommendations that take user emotions into consideration are rarely performed. This can lead to a poor user experience and a decrease in purchasing intent.

[1658] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a means for the user to input categories of interest when logging in for the first time, a means for collecting new information and classifying it by category using a generation AI, a means for recommending the classified information based on the user's preferences, a means for recognizing the user's emotions and adjusting the recommended information based thereon, and a means for notifying the user of the recommended information. This allows the optimal products to be recommended based on the user's preferences and emotions, enabling the user to efficiently find products of interest.

[1659] "Means for users to input categories of interest when logging in for the first time" refers to an interface or function that allows users to input categories of interest or concern when logging in to an application or system for the first time.

[1660] "Means of collecting new information" refers to the processes and techniques by which servers and related devices obtain the latest information from the Internet and related databases.

[1661] "Methods of categorizing using generative AI" refers to algorithms and models that use natural language processing and machine learning to classify collected information into specific categories.

[1662] "Means for making recommendations based on user preferences" refers to technology that selects optimal information and products based on the user's past behavioral data and set preferences and provides them to the user.

[1663] "Means for recognizing a user's emotions and adjusting recommended information based on them" refers to technology that uses devices such as cameras and microphones to analyze emotions from a user's facial expressions and voice, and then changes the recommended information and product content based on that emotional data.

[1664] "Means for notifying recommended information" refers to a function for sending messages or push notifications to inform users of recommended information or products.

[1665] The present invention relates to a system that enables a user to obtain optimal information and products based on their interests and preferences. Detailed embodiments of the present invention will be described below.

[1666] System Overview

[1667] This system consists of the following main components:

[1668] 1. Server: Collects, categorizes, and recommends information.

[1669] 2. Terminal: A device such as a smartphone or tablet operated by a user.

[1670] 3. Generative AI: Algorithms that categorize information and make recommendations.

[1671] 4. Emotion engine: An engine that analyzes user emotions and reflects them in recommendations.

[1672] Settings when you first log in

[1673] When a user logs in to the system for the first time, the server provides the user with an interface to input the categories of interest. The device (smartphone or tablet) displays this interface and sends the information input by the user to the server. For example, the user may input that they are interested in "games" or "gadgets."

[1674] Information collection and classification

[1675] The server periodically collects the latest information, using APIs from the internet or specific databases. The collected information is pre-processed, and the generating AI analyzes and classifies it into categories. For example, it can classify information on new gadgets or the latest game releases.

[1676] Learning user preferences and recognizing emotions

[1677] The device records the user's action data (e.g., browsing history, "likes," etc.) and sends it to the server. The server feeds this data back to the generation AI and updates the user's preference profile. The emotion engine also analyzes the user's emotions from facial images and voice data. For example, if the user is excited or sad, that emotional data is sent to the server.

[1678] Information recommendations and notifications

[1679] Each time new information is collected, the server sends a request to the generation AI to recommend appropriate information based on the user's preference profile and emotional data. Based on this request, the generation AI selects the most appropriate information for the user and returns it to the server. The server then generates this recommended information as a notification message and sends it to the device. For example, it sends a push notification such as, "A new game has been released! Your favorite game category has been updated!"

[1680] Usage example

[1681] For example, suppose a user logs in and specifies that they are interested in "games" and "gadgets." While the user is browsing articles in the "games" category, the emotion engine scans the user's facial expressions and recognizes that the user is very excited. The AI ​​receives this emotion data, and the next time new game information is collected, it prioritizes and recommends information that is likely to excite the user. For example, it sends a notification message to the user saying, "The latest VR game has been released!"

[1682] Prompt Sentence Examples

[1683] "User ID: abc123, Preferences: Games, Gadgets, Emotion: Excitement. Please recommend the best products for the user based on this. New product list: [Product A, Product B, Product C...]"

[1684] In this way, users can efficiently obtain the information and products they are most interested in in real time, improving their virtual store experience. Utilizing emotional data also enables more personalized recommendations.

[1685] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1686] Step 1:

[1687] This is a way for users to input categories of interest when logging in for the first time. When a user logs in using a smartphone or tablet device, the server displays an interface for the user to input categories of interest. The user selects the categories of interest (e.g., "games," "gadgets," etc.) from this interface, and that information is sent to the server. The input data is the user's interests and concerns, and the output is that information is saved on the server.

[1688] Step 2:

[1689] It is a method by which a server collects new information and classifies it into categories using generative AI. The server periodically uses APIs to collect the latest information (e.g., new product information, news articles, etc.) from the internet and related databases. This collected data is converted into text format and preprocessed (removing HTML tags, extracting text, etc.). The input data is the collected raw information, and the output is preprocessed text data.

[1690] Step 3:

[1691] This is a method by which the server uses generative AI to classify information into categories. Preprocessed text data is passed to the generative AI, which uses a model to classify it into the appropriate category. For example, articles about games are classified as "games," and articles about gadgets are classified as "gadgets." The input data is preprocessed text data, and the output is information classified into categories.

[1692] Step 4:

[1693] It is a means by which a device records user action data (e.g., article viewing, "likes," etc.) and sends it to a server. When a user views an article or performs a specific action on the device, that data is recorded by the device and periodically sent to the server. The input data is the user action data, and the output is that it is sent to the server and recorded.

[1694] Step 5:

[1695] The server has a means to recognize the user's emotions and adjust the recommended information based on them. The emotion engine analyzes the user's facial image and voice data to recognize the user's emotions (e.g., joy, excitement, sadness). The input data is the user's image and voice data, and the output is the analyzed emotion data.

[1696] Step 6:

[1697] The server sends a request to the generation AI to recommend appropriate information based on the user's preference profile and emotional data. The generation AI uses the profile and emotional data to select appropriate products and information and returns the results to the server. For example, a prompt such as "User ID: abc123, Preferences: Games, Gadgets, Emotion: Excitement. Please recommend the most suitable information for the user based on this information" is passed to the generation AI. The input data is the user's preference profile and emotional data, and the output is recommended information.

[1698] Step 7:

[1699] The server has a means to notify the user's device of the recommended information. The recommended information is generated by the server as a push notification or in-app notification and sent to the user's device. The input data is the recommended information, and the output is a notification message that is displayed on the device.

[1700] Step 8:

[1701] The device has a means to display recommended information on a feed page. When the user opens the feed page, the recommended information and products are listed and can be easily referenced. The input data is the recommended information, and the output is the information displayed on the feed page.

[1702] In this way, users can efficiently obtain information that best suits their preferences and feelings.

[1703] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1704] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1705] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1706] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1707] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1708] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1709] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1710] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1711] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1712] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1713] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1714] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1715] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1716] 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.

[1717] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1718] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1719] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1720] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1721] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1722] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1723] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1724] The following is further disclosed regarding the above embodiment.

[1725] (Claim 1)

[1726] A means for users to enter categories of interest when they first log in;

[1727] A means of collecting new information and categorizing it using generative AI;

[1728] means for recommending the classified information based on the user's preferences;

[1729] a means for communicating recommendations;

[1730] A system including:

[1731] (Claim 2)

[1732] 10. The system of claim 1, further comprising means for recording user action data and feeding it back to the generating AI.

[1733] (Claim 3)

[1734] A means for notifying a user of the recommended information on the terminal;

[1735] 10. The system of claim 1, further comprising means for displaying the recommendation information on the feed page.

[1736] "Example 1"

[1737] (Claim 1)

[1738] A means for users to enter categories of interest when they first log in;

[1739] a means of regularly gathering new information;

[1740] A means for converting the collected information into text format and preprocessing it;

[1741] A means of categorizing information using a generative AI model; and

[1742] means for generating recommendation information based on user preferences;

[1743] a means for notifying the generated recommendations;

[1744] A means to display recommendations on the feed page;

[1745] A system including:

[1746] (Claim 2)

[1747] means for recording user action data and transmitting the data to a server;

[1748] Further includes means for feeding back the recorded action data to the generative AI model.

[1749] 10. The system of claim 1.

[1750] (Claim 3)

[1751] a means for storing the classified information by category in a database;

[1752] Further includes means for updating a user profile.

[1753] 10. The system of claim 1.

[1754] "Application Example 1"

[1755] (Claim 1)

[1756] A means for users to enter categories of interest when they first log in;

[1757] A means of collecting new information and classifying it into categories using generative AI models; and

[1758] means for recommending the classified information based on the user's preferences;

[1759] a means for communicating recommendations;

[1760] means for displaying the recommendation information on a display screen of the automated equipment;

[1761] A system including:

[1762] (Claim 2)

[1763] 10. The system of claim 1, further comprising means for recording user action data and feeding it back to the generative AI model.

[1764] (Claim 3)

[1765] A means for notifying a user of the recommended information on the terminal;

[1766] 10. The system of claim 1, further comprising means for displaying the recommendation information on the feed page.

[1767] "Example 2: Combining Emotion Engines"

[1768] (Claim 1)

[1769] A means for users to enter categories of interest when they first log in;

[1770] A method to periodically collect new information, preprocess it, and then categorize it using generative AI.

[1771] a means for recommending information based on a user's preference profile and emotions;

[1772] A means to display recommendations on notifications and feed pages; and

[1773] A system including:

[1774] (Claim 2)

[1775] 10. The system of claim 1, further comprising means for recording user action data and feeding it back to the generating AI.

[1776] (Claim 3)

[1777] means for preprocessing the collected information;

[1778] 10. The system of claim 1, further comprising means for recognizing a user's emotions and feeding that data back to the generating AI.

[1779] "Application example 2 when combining emotion engines"

[1780] (Claim 1)

[1781] A means for users to enter categories of interest when they first log in;

[1782] A means of collecting new information and categorizing it using generative AI;

[1783] means for recommending the classified information based on the user's preferences;

[1784] means for recognizing a user's emotions and tailoring recommendations accordingly;

[1785] a means for communicating recommendations;

[1786] A system including:

[1787] (Claim 2)

[1788] 10. The system of claim 1, further comprising means for recording user action data and feeding it back to the generating AI.

[1789] (Claim 3)

[1790] A means for notifying a user of the recommended information on the terminal;

[1791] 10. The system of claim 1, further comprising means for displaying the recommendation information on the feed page. [Explanation of symbols]

[1792] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for users to enter categories of interest when they first log in; A means of collecting new information and categorizing it using generative AI; means for recommending the classified information based on the user's preferences; a means for communicating recommendations; A system including:

2. 2. The system according to claim 1, further comprising means for recording user action data and feeding it back to the generating AI.

3. A means for notifying a user of the recommended information on the terminal; The system of claim 1 , further comprising: means for displaying the recommendation information on the feed page.

Images