System

Abstract

A system is provided.SOLUTION: A system, comprising: means for receiving and storing user profile information; means for using a generative AI model to select an optimal narrative video based on the user profile information; means for using the generative AI model to summarize the selected narrative video to provide specific action steps that the user can perform in real life; and means for using the generative AI model to generate and provide customized feedback to the user based on the progress information.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With traditional methods for viewing lecture videos, many users are unsure which videos to watch, often resulting in inaccessibility to the appropriate lecture content. Furthermore, because no concrete action plan is provided for applying the content of the viewed video to real life, users are unable to take actual action after viewing. Another issue is the lack of progress feedback and advice to promote continuous self-improvement. To solve these issues, a system is needed that selects videos that are individually optimized based on the user's profile information, presents specific action plans, and provides feedback based on progress. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides the following means. First, a means for receiving and storing user profile information is provided. Next, a means for selecting the most suitable lecture video using a generative AI model based on the user profile information is provided. Next, a means for creating a summary from the selected lecture video using the generative AI model and providing the user with specific action steps that can be implemented in real life is provided. Also, a means for receiving and storing user progress data is provided. Finally, a means for generating customized feedback using the generative AI model based on the progress data and providing it to the user is provided. This allows users to watch the most suitable lecture video and apply the content in real life, enabling sustainable growth.

[0006] "Profile Information" refers to information about a user, such as their interests, goals, and life stage.

[0007] A "generative AI model" refers to an artificial intelligence algorithm that analyzes large amounts of data to learn certain patterns, selects the most suitable lecture video for the user, and generates summaries and action plans.

[0008] "Lecture videos" refer to video content in which experts or celebrities give lectures on specific topics.

[0009] "Summary" refers to information that concisely summarizes the contents of the lecture video.

[0010] "Action steps" refer to guidelines for specific actions that users can take in real life based on the summarized content.

[0011] "Progress Data" refers to information about the specific actions taken by a user based on a behavioral step and the results of those actions.

[0012] "Feedback" refers to advice and suggestions for improvement provided to users based on progress data.

[0013] A "system" includes the above elements and refers to a set of processes and functions that provide users with personalized learning and action plans. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0022] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0035] This invention relates to a system that personalizes lecture videos based on a user's profile information, summarizes the content, and provides a concrete action plan. It also aims to provide feedback based on the user's progress and promote sustainable growth. This system is realized using a user terminal, a server, and a generative AI model.

[0036] System Overview

[0037] Entering User Profile Information

[0038] Terminal

[0039] Users access a dedicated form to enter information about their interests, goals, and life stages, which the device receives and transmits to the server.

[0040] server

[0041] The server receives the user profile information sent from the device and stores it in a database.

[0042] Selected TED Talks

[0043] server

[0044] The server runs a generative AI model based on the stored user profile information, which analyzes a large database of lecture videos and selects the most relevant videos for the user.

[0045] Terminal

[0046] The selection results sent from the server are displayed on the device, allowing the user to select the video to watch.

[0047] Generate a summary and action plan

[0048] server

[0049] The server analyzes the selected lecture videos and uses a generative AI model to summarize the content, then generates specific action steps that users can implement in their real lives based on the summarized information.

[0050] Terminal

[0051] The summary and action plan sent from the server are displayed to the user, who then confirms and executes the action plan.

[0052] Progress tracking and feedback

[0053] Terminal

[0054] The user inputs the specific actions taken based on the action plan and their results into the device, which generates progress data.

[0055] server

[0056] The server receives the progress data sent from the device and stores it in a database, where it runs a generative AI model to generate customized feedback and next steps for the user.

[0057] Terminal

[0058] The feedback sent from the server and next steps of action are displayed to the user, which the user can use as a reference for continuous improvement.

[0059] Specific examples

[0060] Entering User Profile Information

[0061] Terminal

[0062] For example, if a user selects the areas of interest "health" and "career" and sets the goal of "improving leadership skills," they fill out this information in an input form and submit it.

[0063] server

[0064] The server receives this information and stores it in a database.

[0065] Selected TED Talks

[0066] server

[0067] The generative AI model analyzes the user's profile information and selects TED Talks related to "leadership," such as "Talks to improve leadership skills," and sends them to the user's device.

[0068] Terminal

[0069] A list of lecture videos sent from the server is displayed to the user, and the user can watch the videos from the options provided.

[0070] Generate a summary and action plan

[0071] server

[0072] It analyzes "lectures to improve leadership skills," generates summaries, and provides action steps such as "hold one-on-one discussions with team members once a week."

[0073] Terminal

[0074] A summary and action plan is presented to the user, who then follows through.

[0075] Progress tracking and feedback

[0076] Terminal

[0077] The user inputs the action they performed (e.g., "Had a one-on-one discussion").

[0078] server

[0079] The server receives the progress data, stores it in a database, and runs the generative AI model to generate feedback for the user (e.g., "Advice on how to further refine the discussion next time").

[0080] Terminal

[0081] It displays feedback and next steps to the user, allowing them to plan their next actions.

[0082] This allows users to achieve continuous growth and effectively apply the knowledge gained from lectures to real life.

[0083] The processing flow will be explained below.

[0084] Step 1:

[0085] Terminal

[0086] Present users with a form to input their interests, goals, and life stages. Users select their interests using checkboxes and enter their goals in text boxes. Ask them to select their life stage using a drop-down menu.

[0087] Step 2:

[0088] User

[0089] Enter the required information and click the submit button.

[0090] Step 3:

[0091] server

[0092] Receives user profile information (interests, goals, life stage) submitted through the form and stores it in a database.

[0093] Step 4:

[0094] server

[0095] The generative AI model is run based on the saved user profile information to select the most suitable lecture videos. For example, if a user's goal is to "improve leadership," the generative AI model will select lecture videos related to "leadership."

[0096] Step 5:

[0097] server

[0098] The generated list of lecture videos is sent to the user's device.

[0099] Step 6:

[0100] Terminal

[0101] The list of lecture videos sent from the server is displayed to the user, who then selects the video they wish to watch from the presented options.

[0102] Step 7:

[0103] User

[0104] Select the video you want to watch from the list of lecture videos displayed.

[0105] Step 8:

[0106] server

[0107] Selected lecture videos are analyzed and summaries are created using a generative AI model.

[0108] Step 9:

[0109] server

[0110] Based on the summary, the system generates concrete action steps that users can implement in their real lives, such as "Have one-on-one discussions with team members once a week."

[0111] Step 10:

[0112] server

[0113] A summary and action steps are sent to the user's device.

[0114] Step 11:

[0115] Terminal

[0116] The summary and action steps sent from the server are displayed to the user, who then confirms and executes the proposed action plan.

[0117] Step 12:

[0118] User

[0119] The user enters the actions they have taken (e.g., having a one-on-one discussion) into the device, which generates progress data.

[0120] Step 13:

[0121] Terminal

[0122] Sends progress data to the server.

[0123] Step 14:

[0124] server

[0125] Save the received progress data in a database.

[0126] Step 15:

[0127] server

[0128] Based on the progress data, generative AI models are run to generate customized feedback and next action steps for the user, such as advice to "provide specific feedback in the next discussion."

[0129] Step 16:

[0130] server

[0131] The generated feedback and next action steps are sent to the user's device.

[0132] Step 17:

[0133] Terminal

[0134] The feedback and next steps sent from the server are displayed to the user, allowing the user to plan their next action.

[0135] This allows users to watch the most relevant lecture videos, apply the content to their real lives, and receive feedback and advice to achieve sustainable growth.

[0136] Example 1

[0137] 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."

[0138] Current lecture videos and other video content make it difficult for users to find content that matches their interests and goals, and to obtain specific action plans for sustainable growth. As a result, users are overwhelmed with information and are unable to take effective action. Furthermore, there is insufficient provision of progress and feedback to individual users, and a lack of mechanisms to support sustainable growth.

[0139] 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.

[0140] In this invention, the server includes means for receiving and storing user profile information, means for selecting optimal video content using a generative AI model based on the user profile information, means for creating a summary from the selected video content using the generative AI model and providing a specific action plan that the user can implement in real life, means for receiving and storing user progress data, means for generating customized feedback using the generative AI model based on the progress data and providing it to the user, means for executing the generative AI model based on the stored user profile information to analyze and select relevant video content, means for analyzing the selected video content and generating a summary and an action plan, and means for generating customized feedback and next action steps. This allows users to easily find relevant content that aligns with their interests and goals, and to receive effective action plans and continuous feedback.

[0141] "User profile information" is information about a user that includes data such as their interests, goals, and life stage.

[0142] A "generative AI model" is an artificial intelligence algorithm that analyzes large amounts of data and generates optimal results based on specific conditions.

[0143] "Video Content" refers to lecture videos and other viewable video materials.

[0144] A "summary" is information that briefly summarizes the contents of the video content.

[0145] An "action plan" refers to specific action steps that users can take in their real lives based on the summarized information.

[0146] "Progress Data" is information including the specific actions taken by the user based on the action plan and the results of those actions.

[0147] "Feedback" refers to customized advice and next steps of action generated based on progress data.

[0148] "Server" means the computer system that receives and stores user profile information and progress data and runs the generative AI model.

[0149] "Terminal" refers to a device through which a user inputs information and displays information sent from a server.

[0150] This invention is a system that personalizes video content based on a user's profile information, summarizes the content, and provides a concrete action plan that the user can actually take. It also promotes sustainable growth by providing customized feedback based on the user's progress. The details are described below.

[0151] The system is realized using a user terminal, a server, and a generative AI model.

[0152] Entering User Profile Information

[0153] Terminal

[0154] Users enter information about their interests, goals, and life stages using a dedicated input form. For example, they can select areas of interest such as "health" or "career" and set a goal of "improving leadership skills." The device then sends this information to the server.

[0155] Store user profile information

[0156] server

[0157] The server receives the user profile information sent from the device and stores it in a database, allowing detailed profile information for each user to be accumulated.

[0158] Selected TED Talks

[0159] server

[0160] The server runs a generative AI model based on the stored user profile information. The generative AI model analyzes a large database of lecture videos and selects videos that are highly relevant to the user, such as a TED Talk on "Improving Leadership Skills."

[0161] Terminal

[0162] The selection results sent from the server are displayed on the device, and the user can select the video they want to watch. The user can then click on the video they are interested in from the displayed options to watch it.

[0163] Generate summaries and action plans

[0164] server

[0165] The server analyzes the selected lecture videos and summarizes their content using a generative AI model. Based on the summarized information, the server then provides users with a concrete action plan that they can implement in their daily lives. For example, it suggests specific action steps such as "Have one-on-one discussions with team members once a week."

[0166] Terminal

[0167] The summary and action plan sent from the server are displayed to the user, who then plans and executes specific actions based on the summary and action plan.

[0168] Tracking your progress

[0169] Terminal

[0170] The user inputs the specific actions they took based on the action plan and the results into the device. For example, they input the result of "having a one-on-one discussion." The device then sends this data to the server.

[0171] Providing feedback

[0172] server

[0173] The server receives the progress data and stores it in a database, then uses a generative AI model to analyze the user's progress and generate customized feedback and next action steps, such as "advice on how to further refine the discussion next time."

[0174] Terminal

[0175] The device displays feedback and next steps sent from the server to the user, allowing the user to plan their next actions and achieve continuous growth.

[0176] Examples of concrete examples and prompts

[0177] Specific examples

[0178] The user selects their areas of interest, "health" and "career," and sets the goal of "improving leadership skills." Then, they enter this information into a dedicated form and click the submit button. The server receives this information and stores it in a database.

[0179] The generative AI model analyzes the user's profile information and selects TED Talks related to "improving leadership skills." For example, it selects "lectures for improving leadership skills." The selection results sent from the server are displayed on the device, and the user selects the video to watch.

[0180] It analyzes the "Lecture for Improving Leadership Skills" and generates a summary. It then suggests specific action steps, such as "Have one-on-one discussions with team members once a week." The summary and action plan are displayed to the user, who then follows them.

[0181] Prompt Sentence Examples

[0182] "My areas of interest are health and career, and I am looking to improve my leadership skills."

[0183] "Please recommend a TED Talk related to leadership."

[0184] "Generate an action plan to help improve your leadership skills."

[0185] "Please suggest next steps of action after the discussion."

[0186] The system allows users to easily find relevant video content that aligns with their interests and goals, and provides effective action plans and continuous feedback.

[0187] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0188] Step 1:

[0189] Entering User Profile Information

[0190] Terminal

[0191] A user enters information about their interests, goals, and life stage into a dedicated input form. For example, they can select the areas of interest "health" and "career" and set the goal of "improving leadership skills." The entered information (input) is sent from the device to the server (output). The specific action performed by the device is for the user to fill in the information in the input form and click the submit button.

[0192] Step 2:

[0193] Store user profile information

[0194] server

[0195] The server receives the user profile information sent from the device (input) and stores it in a database (output). Specific operations include sorting the data received by the server and storing it in the corresponding database table.

[0196] Step 3:

[0197] Selected TED Talks

[0198] server

[0199] The server runs a generative AI model based on the stored user profile information. Using the user profile information as input, the generative AI model analyzes a large-scale lecture video database (data processing) and selects videos that are highly relevant to the user (output). Specifically, the AI ​​model filters out videos that best fit the user's interests and goals and outputs them as a list.

[0200] Terminal

[0201] The selection results (input) sent from the server are displayed on the terminal (output). The user selects the video they want to watch from the displayed video list. Specifically, the selected video list is displayed on the user's screen, allowing the user to make a selection.

[0202] Step 4:

[0203] Generate summaries and action plans

[0204] server

[0205] The server analyzes the selected lecture videos and uses a generative AI model to summarize their content. Using the selected video data as input, the generative AI model generates a summary of the content (data processing) and then generates an action plan that the user can implement in real life (output). Specifically, the AI ​​model extracts key points from the videos and devise action steps based on them.

[0206] Terminal

[0207] The summary and action plan (input) sent from the server are displayed to the user (output). The user uses this information to plan and execute specific actions. Specifically, the summarized information and action steps are displayed on the user's screen, allowing the user to understand and act.

[0208] Step 5:

[0209] Tracking your progress

[0210] Terminal

[0211] The user fills in an input form with the specific actions they took based on the action plan and the results. For example, they might enter "I had a one-on-one discussion" (input). The device then sends this data to the server (output). Specific actions include the user entering their progress and clicking the submit button.

[0212] Step 6:

[0213] Providing feedback

[0214] server

[0215] The server receives the progress data (input) and stores it in a database. It then uses a generative AI model to analyze the user's progress and generate customized feedback and next action steps (output). Specifically, the AI ​​model evaluates the user's progress and suggests the next action to take.

[0216] Terminal

[0217] The feedback sent from the server and the next action steps (input) are displayed to the user (output). The user uses this information to plan their next actions and aim for continuous growth. Specifically, the feedback information and next action plan are displayed on the user's screen so that the user can understand it and take the next step.

[0218] The above is the specific processing flow of this system.

[0219] (Application example 1)

[0220] 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."

[0221] Conventional lecture video delivery systems lacked personalization tailored to individual users' interests and goals, and did not clearly explain how the provided information could be applied to real life. Furthermore, they lacked the ability to provide feedback based on the user's progress or next steps of action, creating a need for a system that could support sustainable growth.

[0222] 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.

[0223] In this invention, the server includes means for receiving and storing user profile information, means for selecting an optimal lecture video using a generative AI model based on the user profile information, means for creating a summary from the selected lecture video using the generative AI model and providing the user with specific action steps that can be taken in real life, means for receiving and storing user progress data, means for generating customized feedback using the generative AI model based on the progress data and providing it to the user, and means for the user to wear a head-mounted display and watch the personalized video. This makes it possible to provide users with an individually optimized lecture video viewing experience and promote sustainable growth through the provision of specific action steps and feedback.

[0224] "User profile information" refers to individual information entered by a user, such as interests, goals, and life stage.

[0225] A "generative AI model" is an artificial intelligence model that performs generative tasks based on provided data, such as generating text, summarizing, and proposing action plans.

[0226] "Lecture videos" refers to video data of lectures or presentations intended to provide information.

[0227] A "summary" is a concise summary of a long lecture video.

[0228] "Specific action steps" refer to specific action items that users can carry out in their real lives based on the summarized content.

[0229] "Progress Data" refers to information about actions taken by a User and their results.

[0230] "Feedback" includes advice and suggestions for next actions provided to users based on progress data.

[0231] A "head-mounted display" is a display device worn by the user on the head, providing an immersive viewing experience.

[0232] This invention is a system for head-mounted displays (HMDs) that personalizes lecture videos based on the user's profile information, provides summaries and specific action plans, and provides feedback based on progress.

[0233] System Overview

[0234] Entering User Profile Information

[0235] Device:

[0236] Users access a dedicated form to input information such as interests, goals, and life stages, and then enter this information. The information is then sent to the server.

[0237] server:

[0238] The server receives the user profile information sent from the terminal and stores it in a database.

[0239] Selected TED Talks

[0240] server:

[0241] The server runs a generative AI model based on the stored user profile information. The generative AI model analyzes a database of lecture videos and selects the most relevant videos for the user. To do this, it uses a generative AI model such as OpenAI's GPT-3.

[0242] Device:

[0243] The selection results sent from the server are displayed on the device, and the user can select the video to watch.

[0244] Generate a summary and action plan

[0245] server:

[0246] The server analyzes the selected lecture videos and summarizes their content using a generative AI model. It then generates specific action steps that users can take in real life based on the summarized information. To achieve this, it uses the summarization function in Hugging Face's transformers package.

[0247] Device:

[0248] The summary and action plan sent from the server are displayed to the user, who then confirms the summary and takes action according to the action plan.

[0249] Progress tracking and feedback

[0250] Device:

[0251] The user inputs the specific actions taken based on the action plan and their results into the device, which generates progress data.

[0252] server:

[0253] The server receives the progress data sent from the device and stores it in a database, where it runs a generative AI model to generate customized feedback and next steps for the user.

[0254] Device:

[0255] The feedback and next action steps sent from the server are displayed to the user, who can use this to plan their next action.

[0256] Specific examples

[0257] Enter your user profile information:

[0258] For example, if a user selects the areas of interest "health" and "career" and sets "improving leadership skills" as a goal, the user inputs this information and transmits it to the server.

[0259] Selected TED Talks:

[0260] The server uses a generative AI model to analyze the user's profile information and select TED Talks related to "leadership," resulting in videos such as "lectures to improve leadership skills."

[0261] Generate a summary and action plan:

[0262] For example, a "lecture to improve leadership skills" could be analyzed and a generative AI model could generate a summary, providing specific action steps such as "hold one-on-one discussions with team members once a week."

[0263] Progress tracking and feedback:

[0264] When a user inputs "I had a one-on-one discussion," the server generates the next feedback (for example, "Advice on how to make the discussion more specific next time") based on the progress data.

[0265] Prompt Sentence Examples

[0266] "Find relevant TED Talks based on your profile: {Interests: 'Health, Career', Goal: 'Improve leadership skills', Life stage: '30s, Manager'}"

[0267] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0268] Step 1:

[0269] Entering User Profile Information

[0270] Device: The user enters profile information such as interests, goals, and life stage into a dedicated form. For example, they enter information such as "health," "career," and "improving leadership skills." The entered information is sent from the device to the server.

[0271] Input: Interests, goals, life stage

[0272] Output: User profile information data

[0273] Step 2:

[0274] Storing User Profile Information

[0275] Server: The server receives the user profile information sent from the device and stores it in a database.

[0276] Input: User profile information data

[0277] Output: User profile information stored in a database

[0278] Step 3:

[0279] Selected TED Talks

[0280] Server: The server runs a generative AI model (e.g., OpenAI's GPT-3) based on the stored user profile information. It sends prompts to the generative AI model to select relevant TED Talks. This process aims to select the best talk videos that correspond to the user's interests and goals.

[0281] Input: User profile information stored in the database

[0282] Output: The best TED Talk link for the user

[0283] Step 4:

[0284] Display of selection results

[0285] Terminal: Receives the selection results sent from the server and displays them to the user, who can then select the TED Talks that interest them.

[0286] Input: Link to the best TED Talk

[0287] Output: A link to the TED Talk displayed on the user's device.

[0288] Step 5:

[0289] Generate a summary and action plan

[0290] Server: The server analyzes selected TED Talk videos, creates summaries using a generative AI model (e.g., the summarization function in Hugging Face's transformers package), and generates specific action steps based on the summaries using the generative AI model.

[0291] Input: Video link of selected TED Talk

[0292] Output: Summary and concrete action plan

[0293] Step 6:

[0294] View summary and action plan

[0295] Terminal: Receives the summary and action plan sent from the server and displays it to the user. The user confirms the presented action plan and puts it into action.

[0296] Input: Summary and specific action plan data

[0297] Output: Summary and action plan displayed on user's device

[0298] Step 7:

[0299] Tracking your progress

[0300] Terminal: The user inputs the specific actions taken based on the action plan and their results into the terminal, which generates progress data and sends it to the server.

[0301] Input: User action result

[0302] Output: Progress data

[0303] Step 8:

[0304] Saving progress data

[0305] Server: The server receives the progress data sent from the terminal and stores it in a database.

[0306] Input: Progress data

[0307] Output: Progress data stored in a database

[0308] Step 9:

[0309] Generate feedback

[0310] Server: The server runs a generative AI model based on the stored progress data to generate customized feedback and next action steps for the user.

[0311] Input: Progress data stored in a database

[0312] Output: Customized feedback and next action steps

[0313] Step 10:

[0314] View Feedback

[0315] Terminal: Receives feedback and next action steps sent from the server and displays them to the user, who can then plan and execute their next action.

[0316] Input: Customized feedback and next action steps

[0317] Output: Feedback and next action steps displayed on the user's device

[0318] 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.

[0319] This invention relates to a system that personalizes lecture videos based on a user's profile information, summarizes the content, and provides a concrete action plan. It also aims to provide feedback based on the user's progress, promoting sustainable growth. Furthermore, the invention incorporates an emotion engine to improve the quality of TED Talk selection, summarization, action steps, and feedback based on the user's emotions. This system is implemented using a user device, a server, a generative AI model, and an emotion engine.

[0320] System Overview

[0321] Entering User Profile Information

[0322] Terminal

[0323] Users access a dedicated form to enter information about their interests, goals, and life stages, which the device receives and transmits to the server.

[0324] server

[0325] The server receives the user profile information sent from the device and stores it in a database.

[0326] Using an Emotion Engine to Select TED Talks

[0327] server

[0328] The server runs a generative AI model based on the user's saved profile information to select the most suitable lecture video. It also uses an emotion engine to analyze the user's emotional responses based on their past viewing history and optimizes the selection results based on their emotions. For example, if a user previously showed positive emotions toward videos related to "improving motivation," the server will prioritize videos with similar themes.

[0329] Terminal

[0330] The selection results sent from the server are displayed on the device, allowing the user to select the video to watch.

[0331] Generate a summary and action plan

[0332] server

[0333] The server analyzes the selected lecture videos and uses a generative AI model to summarize their content. It utilizes an emotion engine to analyze the user's real-time emotions and improve the applicability of the generated summaries and action plans. For example, it prioritizes content that the user expressed positive emotions about while watching and includes it in the summary. It also generates specific action steps that the user can implement in their real life based on the summary content.

[0334] Terminal

[0335] The summary and action plan sent from the server are displayed to the user, who then confirms and executes the action plan.

[0336] Progress tracking and feedback

[0337] Terminal

[0338] The user inputs the specific actions they took based on the action plan and their results into the device, which generates progress data. The emotion engine also collects emotional data during the action.

[0339] server

[0340] The server receives the progress and emotion data sent from the device and stores it in a database. Based on this data, it runs a generative AI model to generate customized feedback and next steps for the user. For example, based on the emotion data, it might provide advice such as "Create a relaxing environment for the next discussion."

[0341] Terminal

[0342] The feedback and next steps sent from the server are displayed to the user, allowing the user to plan their next action.

[0343] Specific examples

[0344] Entering User Profile Information

[0345] Terminal

[0346] For example, if a user selects the areas of interest "health" and "career" and sets the goal of "improving leadership skills," they fill out this information in an input form and submit it.

[0347] server

[0348] The server receives this information and stores it in a database.

[0349] Using an Emotion Engine to Select TED Talks

[0350] server

[0351] The generative AI model analyzes a user's profile information to select TED Talks related to "leadership." The emotion engine analyzes emotional data based on the user's viewing history and prioritizes leadership videos that elicit positive reactions. For example, if a user has previously shown high motivation from "leadership" videos, the model will select similar videos.

[0352] Terminal

[0353] A list of lecture videos sent from the server is displayed to the user, and the user can watch the videos from the options provided.

[0354] Generate a summary and action plan

[0355] server

[0356] The "Lecture for Improving Leadership Skills" is analyzed and a summary is generated. The emotion engine analyzes the user's emotional data in real time as they watch and reflects this in the summary. For example, points that elicit positive reactions are particularly emphasized. Action steps are also created, such as "Have one-on-one discussions with team members once a week."

[0357] Terminal

[0358] A summary and action plan is presented to the user, who then follows through.

[0359] Progress tracking and feedback

[0360] Terminal

[0361] Users input the actions they have taken (e.g., having a one-on-one discussion), and the device also collects emotional data during the action using an emotion engine.

[0362] server

[0363] The server receives the progress and emotion data, stores it in a database, and uses a generative AI model to generate customized feedback based on this data, such as "Create a relaxing environment for the next discussion."

[0364] Terminal

[0365] It displays feedback and next steps to the user so they can plan their next action.

[0366] This allows users to watch the most suitable lecture videos, receive support in applying the content to their real lives, taking into account their motivations and emotions, and receive emotionally-based feedback and advice to achieve continuous growth.

[0367] The processing flow will be explained below.

[0368] Step 1:

[0369] Terminal

[0370] Present users with a form to input their interests, goals, and life stages. Users select their interests using checkboxes and enter their goals in text boxes. Ask them to select their life stage using a drop-down menu.

[0371] Step 2:

[0372] User

[0373] Enter the required information and click the submit button.

[0374] Step 3:

[0375] server

[0376] Receives user profile information (interests, goals, life stage) submitted through the form and stores it in a database.

[0377] Step 4:

[0378] server

[0379] A generative AI model is run based on the saved user profile information to select the most suitable lecture video.

[0380] Step 5:

[0381] server

[0382] The emotional engine is used to analyze a user's emotional reactions based on their past viewing history and optimize the list of selected lecture videos. For example, if a user previously showed positive emotions from videos related to "motivation," videos on similar themes will be prioritized.

[0383] Step 6:

[0384] server

[0385] The generated list of lecture videos is sent to the user's device.

[0386] Step 7:

[0387] Terminal

[0388] The list of lecture videos sent from the server is displayed to the user, who then selects the video they wish to watch from the presented options.

[0389] Step 8:

[0390] User

[0391] Select the video you want to watch from the list of lecture videos displayed.

[0392] Step 9:

[0393] server

[0394] Selected lecture videos are analyzed and summaries are created using a generative AI model.

[0395] Step 10:

[0396] server

[0397] Based on the summary, the system generates specific action steps that users can take in real life. It uses an emotion engine to analyze the user's real-time emotions and reflect them in the summary. For example, it will emphasize content that the user expressed positive emotions about while watching.

[0398] Step 11:

[0399] server

[0400] A summary and action steps are sent to the user's device.

[0401] Step 12:

[0402] Terminal

[0403] The summary and action steps sent from the server are displayed to the user, who then confirms and executes the proposed action plan.

[0404] Step 13:

[0405] User

[0406] The user inputs the actions they have taken (e.g., having a one-on-one discussion) into the device, which generates progress data. The emotion engine also collects emotional data during the action.

[0407] Step 14:

[0408] Terminal

[0409] Send progress and emotion data to the server.

[0410] Step 15:

[0411] server

[0412] The received progress data and emotion data are stored in a database, and the emotion information is added to the progress data and run through a generative AI model to generate customized feedback and next action steps for the user.

[0413] Step 16:

[0414] server

[0415] The generated feedback and next steps are sent to the user's device, providing advice such as "Create a relaxing environment for your next discussion."

[0416] Step 17:

[0417] Terminal

[0418] The feedback sent from the server and next action steps are displayed to the user, allowing the user to plan their next action.

[0419] This allows users to watch the most suitable lecture videos, receive support in applying the content to their real lives, taking into account their motivations and emotions, and receive emotionally-based feedback and advice to achieve continuous growth.

[0420] Example 2

[0421] 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."

[0422] Conventional video content platforms lack personalization based on users' interests and goals, making it difficult to generate specific action plans after watching videos or provide emotional feedback. Furthermore, they lack support for continuous growth that takes into account users' progress and emotional data, making it difficult for users to apply these platforms in their real lives.

[0423] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving and storing user information, means for selecting optimal videos using a generative AI model based on the user's profile information, means for creating summaries from the selected videos using the generative AI model and providing specific action steps that the user can take in real life, means for analyzing the user's past viewing history using an emotion engine and optimizing the selection results based on emotions, means for receiving and storing user progress data and emotion data, and means for generating customized feedback using the generative AI model based on the progress data and emotion data and providing it to the user. This makes it possible to provide personalized video content that takes into account the user's profile information and emotion data, generate specific action plans, and provide feedback based on the user's progress.

[0424] "Your Information" refers to personal data you enter, such as your interests, goals, and life stage.

[0425] "Profile Information" refers to eclectic data about a user's interests, goals, and life stage.

[0426] "Generative AI models" refer to artificial intelligence algorithms that use collected data to select the most suitable videos, generate summaries, and provide action plans and feedback.

[0427] "Optimal videos" refer to video content that is determined to be most suitable and beneficial for an individual user based on the user's profile information and emotional data.

[0428] "Summary" refers to text information that briefly summarizes the content of the selected video.

[0429] "Action steps" refer to specific action plans that users can implement in their real lives based on the summarized video content.

[0430] The "emotion engine" refers to a function that analyzes users' viewing history and real-time emotional responses to improve the accuracy of video selection and feedback.

[0431] "Progress Data" refers to data regarding the specific actions a User takes based on an Action Plan and the results of those actions.

[0432] "Emotional data" refers to data that quantitatively or qualitatively evaluates the emotional responses shown by users while viewing or performing certain activities.

[0433] "Customized feedback" refers to advice and next steps that are individually tailored based on the user's progress and emotional data.

[0434] "System" refers to a collection of devices or software that includes a set of means for receiving user information, selecting videos, generating summaries, providing action plans, storing data, and providing feedback.

[0435] Entering User Profile Information

[0436] Terminal

[0437] Users enter information about their interests, goals, and life stages through a dedicated form. For example, if they select the areas of interest "health" and "career" and set "improving leadership skills" as their goal, they fill out the information in the input form and submit it. The device receives this information and sends it to the server.

[0438] server

[0439] The server receives the user profile information sent from the device and stores it in a database, which is used for subsequent processing to help select the most suitable TED Talk videos and generate summaries.

[0440] Using an Emotion Engine to Select TED Talks

[0441] server

[0442] The server runs a generative AI model based on the user's saved profile information to select the most suitable TED Talk video. During this process, the generative AI model lists multiple candidate videos that match the user's interests and goals. Next, an emotion engine analyzes the user's emotional response based on their past viewing history and prioritizes videos that elicit positive emotions. For example, if a user has previously expressed high motivation through videos related to "leadership," similar videos will be selected.

[0443] Terminal

[0444] The server sends the selection results to the device and displays them to the user, who can then select the video they want to watch from this list.

[0445] Generate a summary and action plan

[0446] server

[0447] The server analyzes selected TED Talk videos and uses a generative AI model to summarize their content. It also uses an emotion engine to analyze the user's real-time emotional responses and highlight parts that elicit positive reactions. Based on this, it generates specific action steps that the user can implement in their daily lives. For example, the server suggests specific actions based on the summary, such as "hold one-on-one discussions with team members once a week."

[0448] Terminal

[0449] The summary and action plan sent from the server are displayed on the terminal, allowing the user to confirm and put into action.

[0450] Progress tracking and feedback

[0451] Terminal

[0452] The user inputs specific actions based on the action plan and their results into the device. For example, they input information such as "I had a one-on-one discussion." The emotion engine also collects emotional data during the action and sends it to the server.

[0453] server

[0454] The server receives the progress and emotion data sent from the device and stores it in a database. Based on this data, it runs a generative AI model to generate customized feedback and next steps. For example, specific feedback such as "Create a relaxing environment for the next discussion" may be provided to the user.

[0455] Terminal

[0456] Feedback and next steps are displayed on the device, allowing users to plan their next actions.

[0457] Examples of concrete examples and prompts

[0458] Examples of entering user profile information

[0459] The user selects the areas of interest, "health" and "career," sets the goal as "learning leadership," and presses the "send" button.

[0460] A concrete example of using the Emotion Engine to select TED Talks

[0461] The generative AI model selects TED Talks related to "leadership," while the emotion engine prioritizes videos that have a positive response to "motivation" based on viewing history.

[0462] Example of generating a summary and action plan

[0463] The generative AI model summarizes "leadership skill improvement videos," highlights positive responses, and provides action steps such as "have a weekly discussion."

[0464] Prompt Sentence Examples

[0465] "Please enter your interests and goals below. Interests: Health, Career. Goal: Improve leadership skills."

[0466] "Select TED Talks related to leadership and prioritize videos that have shown high motivation in the past with your emotion engine."

[0467] "Summarize a TED Talk on improving leadership skills, highlight the points that generate positive responses, and generate action steps."

[0468] "Collect user behavior and their emotions, and provide feedback to recommend improvements to the next relaxing environment."

[0469] This allows the system to select the best TED Talk for each user, generate a summary, provide a specific action plan, and provide personalized feedback based on progress.

[0470] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0471] Step 1: Enter your user profile information

[0472] Terminal

[0473] Users access a dedicated form and enter information such as their areas of interest (e.g., "health" or "career"), goals (e.g., "improving leadership skills"), and life stage (e.g., "student" or "working adult"). The input data is converted into JSON format and sent to the server when the "Submit" button is pressed.

[0474] Input: Profile information entered by the user

[0475] Output: User profile information in JSON format sent to the server

[0476] server

[0477] The server receives the user profile information sent from the device, analyzes the received data with a parser, and stores it in a database.

[0478] Input: User profile information in JSON format

[0479] Output: User information is saved in the database

[0480] Step 2: Using the Emotion Engine to Select TED Talks

[0481] server

[0482] The server reads the user's profile information from the database and runs a generative AI model to select the most suitable TED Talk video. During this process, the generative AI model lists videos that match the user's interests and goals. Next, an emotion engine analyzes the user's past viewing history and prioritizes videos that show positive emotions based on the user's emotional response.

[0483] Input: User profile information stored in the database

[0484] Output: A list of selected TED Talk videos in JSON format

[0485] Terminal

[0486] The video list sent from the server is displayed on the device, and the user selects the video to watch from this list.

[0487] Input: A list of selected TED Talk videos in JSON format

[0488] Output: The ID of the video selected by the user.

[0489] Step 3: Generate a summary and action plan

[0490] server

[0491] Based on the video ID of the TED Talk selected by the user, the server uses a generative AI model to analyze the video content and generate a summary. An emotion engine analyzes the user's emotional data in real time and highlights parts that elicited positive reactions. Based on this, it generates specific action steps that the user can implement in their daily lives. For example, it generates an action step such as "Have one-on-one discussions with team members once a week."

[0492] Input: The ID of the video selected by the user

[0493] Output: JSON summary with specific action steps

[0494] Terminal

[0495] The summary and action plan sent from the server are displayed on the device, and the user confirms and carries out the plan.

[0496] Input: JSON summary and specific action steps

[0497] Output: A summary and action plan displayed to the user

[0498] Step 4: Progress tracking and feedback

[0499] Terminal

[0500] The user inputs the actions they performed based on the action plan and their results into the device. For example, they input information such as "I held a one-on-one discussion." The emotion engine also collects emotional data during the action and sends it to the server in JSON format.

[0501] Input: User actions and results, emotional data

[0502] Output: Progress and emotion data in JSON format is sent to the server.

[0503] server

[0504] The server receives the progress and emotion data sent from the device and stores it in a database. Based on this, it uses a generative AI model to generate customized feedback and next action steps, such as "Create a relaxing environment for the next discussion."

[0505] Input: User progress and emotion data in JSON format

[0506] Output: Customized feedback and next action steps in JSON format

[0507] Terminal

[0508] Feedback and next steps are displayed on the device, allowing users to plan their next actions.

[0509] Input: Customized feedback and next action steps in JSON format

[0510] Output: Feedback and next action steps displayed to the user

[0511] (Application example 2)

[0512] 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."

[0513] Conventional lecture video delivery systems often fail to adequately select optimal videos, summaries, and action plans based on the user's interests and goals. It is also difficult to provide feedback and action steps that take the user's emotions into account. In particular, there are insufficient means to provide personalized video selection and feedback by utilizing the user's viewing history and real-time emotional responses.

[0514] 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 means for receiving and storing user profile information, means for selecting optimal lecture videos using a generative AI model based on the user profile information, means for creating summaries from the selected lecture videos using the generative AI model and providing specific action steps that the user can take in real life, means for receiving and storing user progress data, means for generating customized feedback using the generative AI model based on the progress data and providing it to the user, and means for analyzing the user's emotional data using an emotion engine to improve the quality of video selection, summaries, and action steps. This enables personalized lecture video selection and summaries and action plans to be provided based on the user's profile information and emotional data. It also enables optimal feedback and next action steps to be provided based on the user's viewing history and real-time emotional reactions.

[0515] "User profile information" is information that includes personal attributes such as a user's interests, goals, and life stage.

[0516] A "generative AI model" is an artificial intelligence model that learns patterns from large datasets and generates optimal solutions to perform specific tasks.

[0517] A "lecture video" is a recorded video of a lecture given for educational, enlightening, or motivational purposes.

[0518] A "summary" is text or audio information that concisely summarizes the main points and content of a lecture video.

[0519] "Concrete action steps" are clear, practical action plans that users can implement in their real lives.

[0520] "Progress Data" means information about the specific actions a user takes based on an action plan and the results of those actions.

[0521] "Feedback" is information that includes evaluations and advice regarding actions taken by users.

[0522] "Emotion engine" is a general term for algorithms and software that analyze and evaluate users' emotions and provide the results to the system.

[0523] "Analysis" is the process of dissecting data and extracting meaning and patterns.

[0524] "Real-time" means that information processing and data analysis are carried out simultaneously with real time.

[0525] "Viewing history" is a record of videos of lectures that a user has viewed in the past.

[0526] "Customized Feedback" means feedback that is provided to you individually based on your individual profile information and progress data.

[0527] This invention is a system that personalizes lecture videos based on a user's profile information, summarizes the content, and provides a concrete action plan. Furthermore, it aims to provide feedback based on the user's progress, promoting sustainable growth. It also incorporates an emotion engine to improve the quality of video selection, summarization, action steps, and feedback based on the user's emotions.

[0528] System Overview

[0529] Entering User Profile Information

[0530] Users enter information about their interests, goals, and life stages into a dedicated form. This information is sent to a server via a device such as a smartphone. The server stores the received information in a database and uses it as material for implementing generative AI models.

[0531] Video selection using emotion engine

[0532] The server runs a generative AI model based on the stored user profile information to select the most suitable lecture videos, while using an emotion engine to analyze the emotional reactions from the user's viewing history and prioritize videos that elicit positive reactions.

[0533] Generate a summary and action plan

[0534] The selected videos are analyzed by the server, and a summary is created using a generative AI model. The emotion engine analyzes the user's emotional data in real time to improve the quality of the summary and action plan. For example, points to which the user responded positively can be highlighted in the summary and reflected in the action steps.

[0535] Progress tracking and feedback

[0536] Users input the specific actions they took based on the action plan and their results into their device and send them to the server. This progress data, along with emotional data, is stored on the server. The server then runs a generative AI model based on this data to provide customized feedback and next steps. This allows users to check their progress and plan their next actions.

[0537] Hardware and software used

[0538] Hardware: Smartphones, servers

[0539] Software: Python, JSON library

[0540] The data is sent from the smartphone to a server where it is analyzed and calculated. The generative AI model runs on the server, and the emotion engine analyzes the emotion data in real time. This allows for smooth personalized video selection and action plans.

[0541] Specific examples

[0542] For example, if a user selects the areas of interest "health" and "career" and sets the goal of "improving leadership skills," they input this information and send it to the server. The server uses this information to select TED Talks related to "leadership," prioritizing videos that have generated positive reactions based on past viewing history. It generates summaries of the selected videos and provides specific action plans, such as "hold one-on-one discussions with team members once a week."

[0543] Prompt Sentence Examples

[0544] "Profile Information:"

[0545] "Interests: Health, career"

[0546] "Goal: Improve leadership skills"

[0547] "Life Stage: Mid-Career"

[0548] "Selected TED Talks: Leadership Development Talks"

[0549] "Summary: Core Principles of Leadership"

[0550] "Specific action plan: Hold one-on-one discussions with team members once a week."

[0551] "Feedback: The importance of creating a relaxing environment"

[0552] "Emotional data: Positive"

[0553] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0554] Step 1:

[0555] The user enters information about their interests, goals, and life stages into a dedicated form on their smartphone and submits it, generating a user profile that is then sent from the device to a server, which stores the received information in a database.

[0556] Input: User interests, goals, and life stage information

[0557] Output: User profile information stored in a database

[0558] Specific operation: The terminal receives user input and sends the data to the server via a POST request. The server stores the received JSON data in a database.

[0559] Step 2:

[0560] The server uses a generative AI model to select the most suitable lecture video based on the user profile information stored on the server. It also uses an emotion engine to analyze the user's viewing history and prioritizes videos that have generated positive reactions.

[0561] Input: User profile information stored in the database

[0562] Output: List of selected lecture videos

[0563] How it works: The server runs the generative AI model and uses an algorithm that takes user profile information as input to filter and select the most suitable videos. The emotion engine analyzes viewing history and optimizes the selection results.

[0564] Step 3:

[0565] The server analyzes the selected lecture videos and generates a summary of the video using a generative AI model, utilizing an emotion engine to analyze the user's real-time emotional data and reflect it in the summary.

[0566] Input: Selected lecture videos

[0567] Output: Generated summary

[0568] How it works: The server analyzes the selected videos with a natural language processing algorithm and creates summaries using a generative AI model, while the emotion engine monitors users' real-time emotional data and reflects positive reactions in the summaries.

[0569] Step 4:

[0570] The server then uses the generated summary to provide specific action steps that the user can take in real life, customized based on the user's profile information and analysis results.

[0571] Input: Generated summary

[0572] Output: Specific action steps

[0573] How it works: Based on the summary, the server uses a generative AI model to create an action plan, with action steps customized based on the user's profile information and previous viewing history.

[0574] Step 5:

[0575] The user inputs the specific actions they took based on the action plan and the results into the device, which then sends the data to the server. The server receives the progress data and stores it in a database along with the emotion data.

[0576] Input: User action result data

[0577] Output: Progress and emotion data stored in a database

[0578] Specific operation: The user inputs the action result into the terminal, and the terminal sends the data to the server, which then stores the received data in a database.

[0579] Step 6:

[0580] The server uses a generative AI model to generate customized feedback and next action steps based on the progress and emotion data, and the generated feedback is sent to the device and displayed to the user.

[0581] Input: Progress data, emotion data

[0582] Output: Customized feedback and next action steps

[0583] Specific operation: The server analyzes the progress data and emotion data and generates customized feedback using a generative AI model. The generated feedback and next action steps are sent to the device and displayed to the user.

[0584] 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.

[0585] 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.

[0586] 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.

[0587] [Second embodiment]

[0588] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0589] 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.

[0590] 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).

[0591] 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.

[0592] 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.

[0593] 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).

[0594] 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.

[0595] 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.

[0596] 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.

[0597] 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.

[0598] 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.

[0599] 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."

[0600] This invention relates to a system that personalizes lecture videos based on a user's profile information, summarizes the content, and provides a concrete action plan. It also aims to provide feedback based on the user's progress and promote sustainable growth. This system is realized using a user terminal, a server, and a generative AI model.

[0601] System Overview

[0602] Entering User Profile Information

[0603] Terminal

[0604] Users access a dedicated form to enter information about their interests, goals, and life stages, which the device receives and transmits to the server.

[0605] server

[0606] The server receives the user profile information sent from the device and stores it in a database.

[0607] Selected TED Talks

[0608] server

[0609] The server runs a generative AI model based on the stored user profile information, which analyzes a large database of lecture videos and selects the most relevant videos for the user.

[0610] Terminal

[0611] The selection results sent from the server are displayed on the device, allowing the user to select the video to watch.

[0612] Generate a summary and action plan

[0613] server

[0614] The server analyzes the selected lecture videos and uses a generative AI model to summarize the content, then generates specific action steps that users can implement in their real lives based on the summarized information.

[0615] Terminal

[0616] The summary and action plan sent from the server are displayed to the user, who then confirms and executes the action plan.

[0617] Progress tracking and feedback

[0618] Terminal

[0619] The user inputs the specific actions taken based on the action plan and their results into the device, which generates progress data.

[0620] server

[0621] The server receives the progress data sent from the device and stores it in a database, where it runs a generative AI model to generate customized feedback and next steps for the user.

[0622] Terminal

[0623] The feedback sent from the server and next steps of action are displayed to the user, which the user can use as a reference for continuous improvement.

[0624] Specific examples

[0625] Entering User Profile Information

[0626] Terminal

[0627] For example, if a user selects the areas of interest "health" and "career" and sets the goal of "improving leadership skills," they fill out this information in an input form and submit it.

[0628] server

[0629] The server receives this information and stores it in a database.

[0630] Selected TED Talks

[0631] server

[0632] The generative AI model analyzes the user's profile information and selects TED Talks related to "leadership," such as "Talks to improve leadership skills," and sends them to the user's device.

[0633] Terminal

[0634] A list of lecture videos sent from the server is displayed to the user, and the user can watch the videos from the options provided.

[0635] Generate a summary and action plan

[0636] server

[0637] It analyzes "lectures to improve leadership skills," generates summaries, and provides action steps such as "hold one-on-one discussions with team members once a week."

[0638] Terminal

[0639] A summary and action plan is presented to the user, who then follows through.

[0640] Progress tracking and feedback

[0641] Terminal

[0642] The user inputs the action they performed (e.g., "Had a one-on-one discussion").

[0643] server

[0644] The server receives the progress data, stores it in a database, and runs the generative AI model to generate feedback for the user (e.g., "Advice on how to further refine the discussion next time").

[0645] Terminal

[0646] It displays feedback and next steps to the user, allowing them to plan their next actions.

[0647] This allows users to achieve continuous growth and effectively apply the knowledge gained from lectures to real life.

[0648] The processing flow will be explained below.

[0649] Step 1:

[0650] Terminal

[0651] Present users with a form to input their interests, goals, and life stages. Users select their interests using checkboxes and enter their goals in text boxes. Ask them to select their life stage using a drop-down menu.

[0652] Step 2:

[0653] User

[0654] Enter the required information and click the submit button.

[0655] Step 3:

[0656] server

[0657] Receives user profile information (interests, goals, life stage) submitted through the form and stores it in a database.

[0658] Step 4:

[0659] server

[0660] The generative AI model is run based on the saved user profile information to select the most suitable lecture videos. For example, if a user's goal is to "improve leadership," the generative AI model will select lecture videos related to "leadership."

[0661] Step 5:

[0662] server

[0663] The generated list of lecture videos is sent to the user's device.

[0664] Step 6:

[0665] Terminal

[0666] The list of lecture videos sent from the server is displayed to the user, who then selects the video they wish to watch from the presented options.

[0667] Step 7:

[0668] User

[0669] Select the video you want to watch from the list of lecture videos displayed.

[0670] Step 8:

[0671] server

[0672] Selected lecture videos are analyzed and summaries are created using a generative AI model.

[0673] Step 9:

[0674] server

[0675] Based on the summary, the system generates concrete action steps that users can implement in their real lives, such as "Have one-on-one discussions with team members once a week."

[0676] Step 10:

[0677] server

[0678] A summary and action steps are sent to the user's device.

[0679] Step 11:

[0680] Terminal

[0681] The summary and action steps sent from the server are displayed to the user, who then confirms and executes the proposed action plan.

[0682] Step 12:

[0683] User

[0684] The user enters the actions they have taken (e.g., having a one-on-one discussion) into the device, which generates progress data.

[0685] Step 13:

[0686] Terminal

[0687] Sends progress data to the server.

[0688] Step 14:

[0689] server

[0690] Save the received progress data in a database.

[0691] Step 15:

[0692] server

[0693] Based on the progress data, generative AI models are run to generate customized feedback and next action steps for the user, such as advice to "provide specific feedback in the next discussion."

[0694] Step 16:

[0695] server

[0696] The generated feedback and next action steps are sent to the user's device.

[0697] Step 17:

[0698] Terminal

[0699] The feedback and next steps sent from the server are displayed to the user, allowing the user to plan their next action.

[0700] This allows users to watch the most relevant lecture videos, apply the content to their real lives, and receive feedback and advice to achieve sustainable growth.

[0701] Example 1

[0702] 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."

[0703] Current lecture videos and other video content make it difficult for users to find content that matches their interests and goals, and to obtain specific action plans for sustainable growth. As a result, users are overwhelmed with information and are unable to take effective action. Furthermore, there is insufficient provision of progress and feedback to individual users, and a lack of mechanisms to support sustainable growth.

[0704] 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.

[0705] In this invention, the server includes means for receiving and storing user profile information, means for selecting optimal video content using a generative AI model based on the user profile information, means for creating a summary from the selected video content using the generative AI model and providing a specific action plan that the user can implement in real life, means for receiving and storing user progress data, means for generating customized feedback using the generative AI model based on the progress data and providing it to the user, means for executing the generative AI model based on the stored user profile information to analyze and select relevant video content, means for analyzing the selected video content and generating a summary and an action plan, and means for generating customized feedback and next action steps. This allows users to easily find relevant content that aligns with their interests and goals, and to receive effective action plans and continuous feedback.

[0706] "User profile information" is information about a user that includes data such as their interests, goals, and life stage.

[0707] A "generative AI model" is an artificial intelligence algorithm that analyzes large amounts of data and generates optimal results based on specific conditions.

[0708] "Video Content" refers to lecture videos and other viewable video materials.

[0709] A "summary" is information that briefly summarizes the contents of the video content.

[0710] An "action plan" refers to specific action steps that users can take in their real lives based on the summarized information.

[0711] "Progress Data" is information including the specific actions taken by the user based on the action plan and the results of those actions.

[0712] "Feedback" refers to customized advice and next steps of action generated based on progress data.

[0713] "Server" means the computer system that receives and stores user profile information and progress data and runs the generative AI model.

[0714] "Terminal" refers to a device through which a user inputs information and displays information sent from a server.

[0715] This invention is a system that personalizes video content based on a user's profile information, summarizes the content, and provides a concrete action plan that the user can actually take. It also promotes sustainable growth by providing customized feedback based on the user's progress. The details are described below.

[0716] The system is realized using a user terminal, a server, and a generative AI model.

[0717] Entering User Profile Information

[0718] Terminal

[0719] Users enter information about their interests, goals, and life stages using a dedicated input form. For example, they can select areas of interest such as "health" or "career" and set a goal of "improving leadership skills." The device then sends this information to the server.

[0720] Store user profile information

[0721] server

[0722] The server receives the user profile information sent from the device and stores it in a database, allowing detailed profile information for each user to be accumulated.

[0723] Selected TED Talks

[0724] server

[0725] The server runs a generative AI model based on the stored user profile information. The generative AI model analyzes a large database of lecture videos and selects videos that are highly relevant to the user, such as a TED Talk on "Improving Leadership Skills."

[0726] Terminal

[0727] The selection results sent from the server are displayed on the device, and the user can select the video they want to watch. The user can then click on the video they are interested in from the displayed options to watch it.

[0728] Generate summaries and action plans

[0729] server

[0730] The server analyzes the selected lecture videos and summarizes their content using a generative AI model. Based on the summarized information, the server then provides users with a concrete action plan that they can implement in their daily lives. For example, it suggests specific action steps such as "Have one-on-one discussions with team members once a week."

[0731] Terminal

[0732] The summary and action plan sent from the server are displayed to the user, who then plans and executes specific actions based on the summary and action plan.

[0733] Tracking your progress

[0734] Terminal

[0735] The user inputs the specific actions they took based on the action plan and the results into the device. For example, they input the result of "having a one-on-one discussion." The device then sends this data to the server.

[0736] Providing feedback

[0737] server

[0738] The server receives the progress data and stores it in a database, then uses a generative AI model to analyze the user's progress and generate customized feedback and next action steps, such as "advice on how to further refine the discussion next time."

[0739] Terminal

[0740] The device displays feedback and next steps sent from the server to the user, allowing the user to plan their next actions and achieve continuous growth.

[0741] Examples of concrete examples and prompts

[0742] Specific examples

[0743] The user selects their areas of interest, "health" and "career," and sets the goal of "improving leadership skills." Then, they enter this information into a dedicated form and click the submit button. The server receives this information and stores it in a database.

[0744] The generative AI model analyzes the user's profile information and selects TED Talks related to "improving leadership skills." For example, it selects "lectures for improving leadership skills." The selection results sent from the server are displayed on the device, and the user selects the video to watch.

[0745] It analyzes the "Lecture for Improving Leadership Skills" and generates a summary. It then suggests specific action steps, such as "Have one-on-one discussions with team members once a week." The summary and action plan are displayed to the user, who then follows them.

[0746] Prompt Sentence Examples

[0747] "My areas of interest are health and career, and I am looking to improve my leadership skills."

[0748] "Please recommend a TED Talk related to leadership."

[0749] "Generate an action plan to help improve your leadership skills."

[0750] "Please suggest next steps of action after the discussion."

[0751] The system allows users to easily find relevant video content that aligns with their interests and goals, and provides effective action plans and continuous feedback.

[0752] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0753] Step 1:

[0754] Entering User Profile Information

[0755] Terminal

[0756] A user enters information about their interests, goals, and life stage into a dedicated input form. For example, they can select the areas of interest "health" and "career" and set the goal of "improving leadership skills." The entered information (input) is sent from the device to the server (output). The specific action performed by the device is for the user to fill in the information in the input form and click the submit button.

[0757] Step 2:

[0758] Store user profile information

[0759] server

[0760] The server receives the user profile information sent from the device (input) and stores it in a database (output). Specific operations include sorting the data received by the server and storing it in the corresponding database table.

[0761] Step 3:

[0762] Selected TED Talks

[0763] server

[0764] The server runs a generative AI model based on the stored user profile information. Using the user profile information as input, the generative AI model analyzes a large-scale lecture video database (data processing) and selects videos that are highly relevant to the user (output). Specifically, the AI ​​model filters out videos that best fit the user's interests and goals and outputs them as a list.

[0765] Terminal

[0766] The selection results (input) sent from the server are displayed on the terminal (output). The user selects the video they want to watch from the displayed video list. Specifically, the selected video list is displayed on the user's screen, allowing the user to make a selection.

[0767] Step 4:

[0768] Generate summaries and action plans

[0769] server

[0770] The server analyzes the selected lecture videos and uses a generative AI model to summarize their content. Using the selected video data as input, the generative AI model generates a summary of the content (data processing) and then generates an action plan that the user can implement in real life (output). Specifically, the AI ​​model extracts key points from the videos and devise action steps based on them.

[0771] Terminal

[0772] The summary and action plan (input) sent from the server are displayed to the user (output). The user uses this information to plan and execute specific actions. Specifically, the summarized information and action steps are displayed on the user's screen, allowing the user to understand and act.

[0773] Step 5:

[0774] Tracking your progress

[0775] Terminal

[0776] The user fills in an input form with the specific actions they took based on the action plan and the results. For example, they might enter "I had a one-on-one discussion" (input). The device then sends this data to the server (output). Specific actions include the user entering their progress and clicking the submit button.

[0777] Step 6:

[0778] Providing feedback

[0779] server

[0780] The server receives the progress data (input) and stores it in a database. It then uses a generative AI model to analyze the user's progress and generate customized feedback and next action steps (output). Specifically, the AI ​​model evaluates the user's progress and suggests the next action to take.

[0781] Terminal

[0782] The feedback sent from the server and the next action steps (input) are displayed to the user (output). The user uses this information to plan their next actions and aim for continuous growth. Specifically, the feedback information and next action plan are displayed on the user's screen so that the user can understand it and take the next step.

[0783] The above is the specific processing flow of this system.

[0784] (Application example 1)

[0785] 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."

[0786] Conventional lecture video delivery systems lacked personalization tailored to individual users' interests and goals, and did not clearly explain how the provided information could be applied to real life. Furthermore, they lacked the ability to provide feedback based on the user's progress or next steps of action, creating a need for a system that could support sustainable growth.

[0787] 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.

[0788] In this invention, the server includes means for receiving and storing user profile information, means for selecting an optimal lecture video using a generative AI model based on the user profile information, means for creating a summary from the selected lecture video using the generative AI model and providing the user with specific action steps that can be taken in real life, means for receiving and storing user progress data, means for generating customized feedback using the generative AI model based on the progress data and providing it to the user, and means for the user to wear a head-mounted display and watch the personalized video. This makes it possible to provide users with an individually optimized lecture video viewing experience and promote sustainable growth through the provision of specific action steps and feedback.

[0789] "User profile information" refers to individual information entered by a user, such as interests, goals, and life stage.

[0790] A "generative AI model" is an artificial intelligence model that performs generative tasks based on provided data, such as generating text, summarizing, and proposing action plans.

[0791] "Lecture videos" refers to video data of lectures or presentations intended to provide information.

[0792] A "summary" is a concise summary of a long lecture video.

[0793] "Specific action steps" refer to specific action items that users can carry out in their real lives based on the summarized content.

[0794] "Progress Data" refers to information about actions taken by a User and their results.

[0795] "Feedback" includes advice and suggestions for next actions provided to users based on progress data.

[0796] A "head-mounted display" is a display device worn by the user on the head, providing an immersive viewing experience.

[0797] This invention is a system for head-mounted displays (HMDs) that personalizes lecture videos based on the user's profile information, provides summaries and specific action plans, and provides feedback based on progress.

[0798] System Overview

[0799] Entering User Profile Information

[0800] Device:

[0801] Users access a dedicated form to input information such as interests, goals, and life stages, and then enter this information. The information is then sent to the server.

[0802] server:

[0803] The server receives the user profile information sent from the terminal and stores it in a database.

[0804] Selected TED Talks

[0805] server:

[0806] The server runs a generative AI model based on the stored user profile information. The generative AI model analyzes a database of lecture videos and selects the most relevant videos for the user. To do this, it uses a generative AI model such as OpenAI's GPT-3.

[0807] Device:

[0808] The selection results sent from the server are displayed on the device, and the user can select the video to watch.

[0809] Generate a summary and action plan

[0810] server:

[0811] The server analyzes the selected lecture videos and summarizes their content using a generative AI model. It then generates specific action steps that users can take in real life based on the summarized information. To achieve this, it uses the summarization function in Hugging Face's transformers package.

[0812] Device:

[0813] The summary and action plan sent from the server are displayed to the user, who then confirms the summary and takes action according to the action plan.

[0814] Progress tracking and feedback

[0815] Device:

[0816] The user inputs the specific actions taken based on the action plan and their results into the device, which generates progress data.

[0817] server:

[0818] The server receives the progress data sent from the device and stores it in a database, where it runs a generative AI model to generate customized feedback and next steps for the user.

[0819] Device:

[0820] The feedback and next action steps sent from the server are displayed to the user, who can use this to plan their next action.

[0821] Specific examples

[0822] Enter your user profile information:

[0823] For example, if a user selects the areas of interest "health" and "career" and sets "improving leadership skills" as a goal, the user inputs this information and transmits it to the server.

[0824] Selected TED Talks:

[0825] The server uses a generative AI model to analyze the user's profile information and select TED Talks related to "leadership," resulting in videos such as "lectures to improve leadership skills."

[0826] Generate a summary and action plan:

[0827] For example, a "lecture to improve leadership skills" could be analyzed and a generative AI model could generate a summary, providing specific action steps such as "hold one-on-one discussions with team members once a week."

[0828] Progress tracking and feedback:

[0829] When a user inputs "I had a one-on-one discussion," the server generates the next feedback (for example, "Advice on how to make the discussion more specific next time") based on the progress data.

[0830] Prompt Sentence Examples

[0831] "Find relevant TED Talks based on your profile: {Interests: 'Health, Career', Goal: 'Improve leadership skills', Life stage: '30s, Manager'}"

[0832] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0833] Step 1:

[0834] Entering User Profile Information

[0835] Device: The user enters profile information such as interests, goals, and life stage into a dedicated form. For example, they enter information such as "health," "career," and "improving leadership skills." The entered information is sent from the device to the server.

[0836] Input: Interests, goals, life stage

[0837] Output: User profile information data

[0838] Step 2:

[0839] Storing User Profile Information

[0840] Server: The server receives the user profile information sent from the device and stores it in a database.

[0841] Input: User profile information data

[0842] Output: User profile information stored in a database

[0843] Step 3:

[0844] Selected TED Talks

[0845] Server: The server runs a generative AI model (e.g., OpenAI's GPT-3) based on the stored user profile information. It sends prompts to the generative AI model to select relevant TED Talks. This process aims to select the best talk videos that correspond to the user's interests and goals.

[0846] Input: User profile information stored in the database

[0847] Output: The best TED Talk link for the user

[0848] Step 4:

[0849] Display of selection results

[0850] Terminal: Receives the selection results sent from the server and displays them to the user, who can then select the TED Talks that interest them.

[0851] Input: Link to the best TED Talk

[0852] Output: A link to the TED Talk displayed on the user's device.

[0853] Step 5:

[0854] Generate a summary and action plan

[0855] Server: The server analyzes selected TED Talk videos, creates summaries using a generative AI model (e.g., the summarization function in Hugging Face's transformers package), and generates specific action steps based on the summaries using the generative AI model.

[0856] Input: Video link of selected TED Talk

[0857] Output: Summary and concrete action plan

[0858] Step 6:

[0859] View summary and action plan

[0860] Terminal: Receives the summary and action plan sent from the server and displays it to the user. The user confirms the presented action plan and puts it into action.

[0861] Input: Summary and specific action plan data

[0862] Output: Summary and action plan displayed on user's device

[0863] Step 7:

[0864] Tracking your progress

[0865] Terminal: The user inputs the specific actions taken based on the action plan and their results into the terminal, which generates progress data and sends it to the server.

[0866] Input: User action result

[0867] Output: Progress data

[0868] Step 8:

[0869] Saving progress data

[0870] Server: The server receives the progress data sent from the terminal and stores it in a database.

[0871] Input: Progress data

[0872] Output: Progress data stored in a database

[0873] Step 9:

[0874] Generate feedback

[0875] Server: The server runs a generative AI model based on the stored progress data to generate customized feedback and next action steps for the user.

[0876] Input: Progress data stored in a database

[0877] Output: Customized feedback and next action steps

[0878] Step 10:

[0879] View Feedback

[0880] Terminal: Receives feedback and next action steps sent from the server and displays them to the user, who can then plan and execute their next action.

[0881] Input: Customized feedback and next action steps

[0882] Output: Feedback and next action steps displayed on the user's device

[0883] 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.

[0884] This invention relates to a system that personalizes lecture videos based on a user's profile information, summarizes the content, and provides a concrete action plan. It also aims to provide feedback based on the user's progress, promoting sustainable growth. Furthermore, the invention incorporates an emotion engine to improve the quality of TED Talk selection, summarization, action steps, and feedback based on the user's emotions. This system is implemented using a user device, a server, a generative AI model, and an emotion engine.

[0885] System Overview

[0886] Entering User Profile Information

[0887] Terminal

[0888] Users access a dedicated form to enter information about their interests, goals, and life stages, which the device receives and transmits to the server.

[0889] server

[0890] The server receives the user profile information sent from the device and stores it in a database.

[0891] Using an Emotion Engine to Select TED Talks

[0892] server

[0893] The server runs a generative AI model based on the user's saved profile information to select the most suitable lecture video. It also uses an emotion engine to analyze the user's emotional responses based on their past viewing history and optimizes the selection results based on their emotions. For example, if a user previously showed positive emotions toward videos related to "improving motivation," the server will prioritize videos with similar themes.

[0894] Terminal

[0895] The selection results sent from the server are displayed on the device, allowing the user to select the video to watch.

[0896] Generate a summary and action plan

[0897] server

[0898] The server analyzes the selected lecture videos and uses a generative AI model to summarize their content. It utilizes an emotion engine to analyze the user's real-time emotions and improve the applicability of the generated summaries and action plans. For example, it prioritizes content that the user expressed positive emotions about while watching and includes it in the summary. It also generates specific action steps that the user can implement in their real life based on the summary content.

[0899] Terminal

[0900] The summary and action plan sent from the server are displayed to the user, who then confirms and executes the action plan.

[0901] Progress tracking and feedback

[0902] Terminal

[0903] The user inputs the specific actions they took based on the action plan and their results into the device, which generates progress data. The emotion engine also collects emotional data during the action.

[0904] server

[0905] The server receives the progress and emotion data sent from the device and stores it in a database. Based on this data, it runs a generative AI model to generate customized feedback and next steps for the user. For example, based on the emotion data, it might provide advice such as "Create a relaxing environment for the next discussion."

[0906] Terminal

[0907] The feedback and next steps sent from the server are displayed to the user, allowing the user to plan their next action.

[0908] Specific examples

[0909] Entering User Profile Information

[0910] Terminal

[0911] For example, if a user selects the areas of interest "health" and "career" and sets the goal of "improving leadership skills," they fill out this information in an input form and submit it.

[0912] server

[0913] The server receives this information and stores it in a database.

[0914] Using an Emotion Engine to Select TED Talks

[0915] server

[0916] The generative AI model analyzes a user's profile information to select TED Talks related to "leadership." The emotion engine analyzes emotional data based on the user's viewing history and prioritizes leadership videos that elicit positive reactions. For example, if a user has previously shown high motivation from "leadership" videos, the model will select similar videos.

[0917] Terminal

[0918] A list of lecture videos sent from the server is displayed to the user, and the user can watch the videos from the options provided.

[0919] Generate a summary and action plan

[0920] server

[0921] The "Lecture for Improving Leadership Skills" is analyzed and a summary is generated. The emotion engine analyzes the user's emotional data in real time as they watch and reflects this in the summary. For example, points that elicit positive reactions are particularly emphasized. Action steps are also created, such as "Have one-on-one discussions with team members once a week."

[0922] Terminal

[0923] A summary and action plan is presented to the user, who then follows through.

[0924] Progress tracking and feedback

[0925] Terminal

[0926] Users input the actions they have taken (e.g., having a one-on-one discussion), and the device also collects emotional data during the action using an emotion engine.

[0927] server

[0928] The server receives the progress and emotion data, stores it in a database, and uses a generative AI model to generate customized feedback based on this data, such as "Create a relaxing environment for the next discussion."

[0929] Terminal

[0930] It displays feedback and next steps to the user so they can plan their next action.

[0931] This allows users to watch the most suitable lecture videos, receive support in applying the content to their real lives, taking into account their motivations and emotions, and receive emotionally-based feedback and advice to achieve continuous growth.

[0932] The processing flow will be explained below.

[0933] Step 1:

[0934] Terminal

[0935] Present users with a form to input their interests, goals, and life stages. Users select their interests using checkboxes and enter their goals in text boxes. Ask them to select their life stage using a drop-down menu.

[0936] Step 2:

[0937] User

[0938] Enter the required information and click the submit button.

[0939] Step 3:

[0940] server

[0941] Receives user profile information (interests, goals, life stage) submitted through the form and stores it in a database.

[0942] Step 4:

[0943] server

[0944] A generative AI model is run based on the saved user profile information to select the most suitable lecture video.

[0945] Step 5:

[0946] server

[0947] The emotional engine is used to analyze a user's emotional reactions based on their past viewing history and optimize the list of selected lecture videos. For example, if a user previously showed positive emotions from videos related to "motivation," videos on similar themes will be prioritized.

[0948] Step 6:

[0949] server

[0950] The generated list of lecture videos is sent to the user's device.

[0951] Step 7:

[0952] Terminal

[0953] The list of lecture videos sent from the server is displayed to the user, who then selects the video they wish to watch from the presented options.

[0954] Step 8:

[0955] User

[0956] Select the video you want to watch from the list of lecture videos displayed.

[0957] Step 9:

[0958] server

[0959] Selected lecture videos are analyzed and summaries are created using a generative AI model.

[0960] Step 10:

[0961] server

[0962] Based on the summary, the system generates specific action steps that users can take in real life. It uses an emotion engine to analyze the user's real-time emotions and reflect them in the summary. For example, it will emphasize content that the user expressed positive emotions about while watching.

[0963] Step 11:

[0964] server

[0965] A summary and action steps are sent to the user's device.

[0966] Step 12:

[0967] Terminal

[0968] The summary and action steps sent from the server are displayed to the user, who then confirms and executes the proposed action plan.

[0969] Step 13:

[0970] User

[0971] The user inputs the actions they have taken (e.g., having a one-on-one discussion) into the device, which generates progress data. The emotion engine also collects emotional data during the action.

[0972] Step 14:

[0973] Terminal

[0974] Send progress and emotion data to the server.

[0975] Step 15:

[0976] server

[0977] The received progress data and emotion data are stored in a database, and the emotion information is added to the progress data and run through a generative AI model to generate customized feedback and next action steps for the user.

[0978] Step 16:

[0979] server

[0980] The generated feedback and next steps are sent to the user's device, providing advice such as "Create a relaxing environment for your next discussion."

[0981] Step 17:

[0982] Terminal

[0983] The feedback sent from the server and next action steps are displayed to the user, allowing the user to plan their next action.

[0984] This allows users to watch the most suitable lecture videos, receive support in applying the content to their real lives, taking into account their motivations and emotions, and receive emotionally-based feedback and advice to achieve continuous growth.

[0985] Example 2

[0986] 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."

[0987] Conventional video content platforms lack personalization based on users' interests and goals, making it difficult to generate specific action plans after watching videos or provide emotional feedback. Furthermore, they lack support for continuous growth that takes into account users' progress and emotional data, making it difficult for users to apply these platforms in their real lives.

[0988] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving and storing user information, means for selecting optimal videos using a generative AI model based on the user's profile information, means for creating summaries from the selected videos using the generative AI model and providing specific action steps that the user can take in real life, means for analyzing the user's past viewing history using an emotion engine and optimizing the selection results based on emotions, means for receiving and storing user progress data and emotion data, and means for generating customized feedback using the generative AI model based on the progress data and emotion data and providing it to the user. This makes it possible to provide personalized video content that takes into account the user's profile information and emotion data, generate specific action plans, and provide feedback based on the user's progress.

[0989] "Your Information" refers to personal data you enter, such as your interests, goals, and life stage.

[0990] "Profile Information" refers to eclectic data about a user's interests, goals, and life stage.

[0991] "Generative AI models" refer to artificial intelligence algorithms that use collected data to select the most suitable videos, generate summaries, and provide action plans and feedback.

[0992] "Optimal videos" refer to video content that is determined to be most suitable and beneficial for an individual user based on the user's profile information and emotional data.

[0993] "Summary" refers to text information that briefly summarizes the content of the selected video.

[0994] "Action steps" refer to specific action plans that users can implement in their real lives based on the summarized video content.

[0995] The "emotion engine" refers to a function that analyzes users' viewing history and real-time emotional responses to improve the accuracy of video selection and feedback.

[0996] "Progress Data" refers to data regarding the specific actions a User takes based on an Action Plan and the results of those actions.

[0997] "Emotional data" refers to data that quantitatively or qualitatively evaluates the emotional responses shown by users while viewing or performing certain activities.

[0998] "Customized feedback" refers to advice and next steps that are individually tailored based on the user's progress and emotional data.

[0999] "System" refers to a collection of devices or software that includes a set of means for receiving user information, selecting videos, generating summaries, providing action plans, storing data, and providing feedback.

[1000] Entering User Profile Information

[1001] Terminal

[1002] Users enter information about their interests, goals, and life stages through a dedicated form. For example, if they select the areas of interest "health" and "career" and set "improving leadership skills" as their goal, they fill out the information in the input form and submit it. The device receives this information and sends it to the server.

[1003] server

[1004] The server receives the user profile information sent from the device and stores it in a database, which is used for subsequent processing to help select the most suitable TED Talk videos and generate summaries.

[1005] Using an Emotion Engine to Select TED Talks

[1006] server

[1007] The server runs a generative AI model based on the user's saved profile information to select the most suitable TED Talk video. During this process, the generative AI model lists multiple candidate videos that match the user's interests and goals. Next, an emotion engine analyzes the user's emotional response based on their past viewing history and prioritizes videos that elicit positive emotions. For example, if a user has previously expressed high motivation through videos related to "leadership," similar videos will be selected.

[1008] Terminal

[1009] The server sends the selection results to the device and displays them to the user, who can then select the video they want to watch from this list.

[1010] Generate a summary and action plan

[1011] server

[1012] The server analyzes selected TED Talk videos and uses a generative AI model to summarize their content. It also uses an emotion engine to analyze the user's real-time emotional responses and highlight parts that elicit positive reactions. Based on this, it generates specific action steps that the user can implement in their daily lives. For example, the server suggests specific actions based on the summary, such as "hold one-on-one discussions with team members once a week."

[1013] Terminal

[1014] The summary and action plan sent from the server are displayed on the terminal, allowing the user to confirm and put into action.

[1015] Progress tracking and feedback

[1016] Terminal

[1017] The user inputs specific actions based on the action plan and their results into the device. For example, they input information such as "I had a one-on-one discussion." The emotion engine also collects emotional data during the action and sends it to the server.

[1018] server

[1019] The server receives the progress and emotion data sent from the device and stores it in a database. Based on this data, it runs a generative AI model to generate customized feedback and next steps. For example, specific feedback such as "Create a relaxing environment for the next discussion" may be provided to the user.

[1020] Terminal

[1021] Feedback and next steps are displayed on the device, allowing users to plan their next actions.

[1022] Examples of concrete examples and prompts

[1023] Examples of entering user profile information

[1024] The user selects the areas of interest, "health" and "career," sets the goal as "learning leadership," and presses the "send" button.

[1025] A concrete example of using the Emotion Engine to select TED Talks

[1026] The generative AI model selects TED Talks related to "leadership," while the emotion engine prioritizes videos that have a positive response to "motivation" based on viewing history.

[1027] Example of generating a summary and action plan

[1028] The generative AI model summarizes "leadership skill improvement videos," highlights positive responses, and provides action steps such as "have a weekly discussion."

[1029] Prompt Sentence Examples

[1030] "Please enter your interests and goals below. Interests: Health, Career. Goal: Improve leadership skills."

[1031] "Select TED Talks related to leadership and prioritize videos that have shown high motivation in the past with your emotion engine."

[1032] "Summarize a TED Talk on improving leadership skills, highlight the points that generate positive responses, and generate action steps."

[1033] "Collect user behavior and their emotions, and provide feedback to recommend improvements to the next relaxing environment."

[1034] This allows the system to select the best TED Talk for each user, generate a summary, provide a specific action plan, and provide personalized feedback based on progress.

[1035] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1036] Step 1: Enter your user profile information

[1037] Terminal

[1038] Users access a dedicated form and enter information such as their areas of interest (e.g., "health" or "career"), goals (e.g., "improving leadership skills"), and life stage (e.g., "student" or "working adult"). The input data is converted into JSON format and sent to the server when the "Submit" button is pressed.

[1039] Input: Profile information entered by the user

[1040] Output: User profile information in JSON format sent to the server

[1041] server

[1042] The server receives the user profile information sent from the device, analyzes the received data with a parser, and stores it in a database.

[1043] Input: User profile information in JSON format

[1044] Output: User information is saved in the database

[1045] Step 2: Using the Emotion Engine to Select TED Talks

[1046] server

[1047] The server reads the user's profile information from the database and runs a generative AI model to select the most suitable TED Talk video. During this process, the generative AI model lists videos that match the user's interests and goals. Next, an emotion engine analyzes the user's past viewing history and prioritizes videos that show positive emotions based on the user's emotional response.

[1048] Input: User profile information stored in the database

[1049] Output: A list of selected TED Talk videos in JSON format

[1050] Terminal

[1051] The video list sent from the server is displayed on the device, and the user selects the video to watch from this list.

[1052] Input: A list of selected TED Talk videos in JSON format

[1053] Output: The ID of the video selected by the user.

[1054] Step 3: Generate a summary and action plan

[1055] server

[1056] Based on the video ID of the TED Talk selected by the user, the server uses a generative AI model to analyze the video content and generate a summary. An emotion engine analyzes the user's emotional data in real time and highlights parts that elicited positive reactions. Based on this, it generates specific action steps that the user can implement in their daily lives. For example, it generates an action step such as "Have one-on-one discussions with team members once a week."

[1057] Input: The ID of the video selected by the user

[1058] Output: JSON summary with specific action steps

[1059] Terminal

[1060] The summary and action plan sent from the server are displayed on the device, and the user confirms and carries out the plan.

[1061] Input: JSON summary and specific action steps

[1062] Output: A summary and action plan displayed to the user

[1063] Step 4: Progress tracking and feedback

[1064] Terminal

[1065] The user inputs the actions they performed based on the action plan and their results into the device. For example, they input information such as "I held a one-on-one discussion." The emotion engine also collects emotional data during the action and sends it to the server in JSON format.

[1066] Input: User actions and results, emotional data

[1067] Output: Progress and emotion data in JSON format is sent to the server.

[1068] server

[1069] The server receives the progress and emotion data sent from the device and stores it in a database. Based on this, it uses a generative AI model to generate customized feedback and next action steps, such as "Create a relaxing environment for the next discussion."

[1070] Input: User progress and emotion data in JSON format

[1071] Output: Customized feedback and next action steps in JSON format

[1072] Terminal

[1073] Feedback and next steps are displayed on the device, allowing users to plan their next actions.

[1074] Input: Customized feedback and next action steps in JSON format

[1075] Output: Feedback and next action steps displayed to the user

[1076] (Application example 2)

[1077] 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."

[1078] Conventional lecture video delivery systems often fail to adequately select optimal videos, summaries, and action plans based on the user's interests and goals. It is also difficult to provide feedback and action steps that take the user's emotions into account. In particular, there are insufficient means to provide personalized video selection and feedback by utilizing the user's viewing history and real-time emotional responses.

[1079] 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 means for receiving and storing user profile information, means for selecting optimal lecture videos using a generative AI model based on the user profile information, means for creating summaries from the selected lecture videos using the generative AI model and providing specific action steps that the user can take in real life, means for receiving and storing user progress data, means for generating customized feedback using the generative AI model based on the progress data and providing it to the user, and means for analyzing the user's emotional data using an emotion engine to improve the quality of video selection, summaries, and action steps. This enables personalized lecture video selection and summaries and action plans to be provided based on the user's profile information and emotional data. It also enables optimal feedback and next action steps to be provided based on the user's viewing history and real-time emotional reactions.

[1080] "User profile information" is information that includes personal attributes such as a user's interests, goals, and life stage.

[1081] A "generative AI model" is an artificial intelligence model that learns patterns from large datasets and generates optimal solutions to perform specific tasks.

[1082] A "lecture video" is a recorded video of a lecture given for educational, enlightening, or motivational purposes.

[1083] A "summary" is text or audio information that concisely summarizes the main points and content of a lecture video.

[1084] "Concrete action steps" are clear, practical action plans that users can implement in their real lives.

[1085] "Progress Data" means information about the specific actions a user takes based on an action plan and the results of those actions.

[1086] "Feedback" is information that includes evaluations and advice regarding actions taken by users.

[1087] "Emotion engine" is a general term for algorithms and software that analyze and evaluate users' emotions and provide the results to the system.

[1088] "Analysis" is the process of dissecting data and extracting meaning and patterns.

[1089] "Real-time" means that information processing and data analysis are carried out simultaneously with real time.

[1090] "Viewing history" is a record of videos of lectures that a user has viewed in the past.

[1091] "Customized Feedback" means feedback that is provided to you individually based on your individual profile information and progress data.

[1092] This invention is a system that personalizes lecture videos based on a user's profile information, summarizes the content, and provides a concrete action plan. Furthermore, it aims to provide feedback based on the user's progress, promoting sustainable growth. It also incorporates an emotion engine to improve the quality of video selection, summarization, action steps, and feedback based on the user's emotions.

[1093] System Overview

[1094] Entering User Profile Information

[1095] Users enter information about their interests, goals, and life stages into a dedicated form. This information is sent to a server via a device such as a smartphone. The server stores the received information in a database and uses it as material for implementing generative AI models.

[1096] Video selection using emotion engine

[1097] The server runs a generative AI model based on the stored user profile information to select the most suitable lecture videos, while using an emotion engine to analyze the emotional reactions from the user's viewing history and prioritize videos that elicit positive reactions.

[1098] Generate a summary and action plan

[1099] The selected videos are analyzed by the server, and a summary is created using a generative AI model. The emotion engine analyzes the user's emotional data in real time to improve the quality of the summary and action plan. For example, points to which the user responded positively can be highlighted in the summary and reflected in the action steps.

[1100] Progress tracking and feedback

[1101] Users input the specific actions they took based on the action plan and their results into their device and send them to the server. This progress data, along with emotional data, is stored on the server. The server then runs a generative AI model based on this data to provide customized feedback and next steps. This allows users to check their progress and plan their next actions.

[1102] Hardware and software used

[1103] Hardware: Smartphones, servers

[1104] Software: Python, JSON library

[1105] The data is sent from the smartphone to a server where it is analyzed and calculated. The generative AI model runs on the server, and the emotion engine analyzes the emotion data in real time. This allows for smooth personalized video selection and action plans.

[1106] Specific examples

[1107] For example, if a user selects the areas of interest "health" and "career" and sets the goal of "improving leadership skills," they input this information and send it to the server. The server uses this information to select TED Talks related to "leadership," prioritizing videos that have generated positive reactions based on past viewing history. It generates summaries of the selected videos and provides specific action plans, such as "hold one-on-one discussions with team members once a week."

[1108] Prompt Sentence Examples

[1109] "Profile Information:"

[1110] "Interests: Health, career"

[1111] "Goal: Improve leadership skills"

[1112] "Life Stage: Mid-Career"

[1113] "Selected TED Talks: Leadership Development Talks"

[1114] "Summary: Core Principles of Leadership"

[1115] "Specific action plan: Hold one-on-one discussions with team members once a week."

[1116] "Feedback: The importance of creating a relaxing environment"

[1117] "Emotional data: Positive"

[1118] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1119] Step 1:

[1120] The user enters information about their interests, goals, and life stages into a dedicated form on their smartphone and submits it, generating a user profile that is then sent from the device to a server, which stores the received information in a database.

[1121] Input: User interests, goals, and life stage information

[1122] Output: User profile information stored in a database

[1123] Specific operation: The terminal receives user input and sends the data to the server via a POST request. The server stores the received JSON data in a database.

[1124] Step 2:

[1125] The server uses a generative AI model to select the most suitable lecture video based on the user profile information stored on the server. It also uses an emotion engine to analyze the user's viewing history and prioritizes videos that have generated positive reactions.

[1126] Input: User profile information stored in the database

[1127] Output: List of selected lecture videos

[1128] How it works: The server runs the generative AI model and uses an algorithm that takes user profile information as input to filter and select the most suitable videos. The emotion engine analyzes viewing history and optimizes the selection results.

[1129] Step 3:

[1130] The server analyzes the selected lecture videos and generates a summary of the video using a generative AI model, utilizing an emotion engine to analyze the user's real-time emotional data and reflect it in the summary.

[1131] Input: Selected lecture videos

[1132] Output: Generated summary

[1133] How it works: The server analyzes the selected videos with a natural language processing algorithm and creates summaries using a generative AI model, while the emotion engine monitors users' real-time emotional data and reflects positive reactions in the summaries.

[1134] Step 4:

[1135] The server then uses the generated summary to provide specific action steps that the user can take in real life, customized based on the user's profile information and analysis results.

[1136] Input: Generated summary

[1137] Output: Specific action steps

[1138] How it works: Based on the summary, the server uses a generative AI model to create an action plan, with action steps customized based on the user's profile information and previous viewing history.

[1139] Step 5:

[1140] The user inputs the specific actions they took based on the action plan and the results into the device, which then sends the data to the server. The server receives the progress data and stores it in a database along with the emotion data.

[1141] Input: User action result data

[1142] Output: Progress and emotion data stored in a database

[1143] Specific operation: The user inputs the action result into the terminal, and the terminal sends the data to the server, which then stores the received data in a database.

[1144] Step 6:

[1145] The server uses a generative AI model to generate customized feedback and next action steps based on the progress and emotion data, and the generated feedback is sent to the device and displayed to the user.

[1146] Input: Progress data, emotion data

[1147] Output: Customized feedback and next action steps

[1148] Specific operation: The server analyzes the progress data and emotion data and generates customized feedback using a generative AI model. The generated feedback and next action steps are sent to the device and displayed to the user.

[1149] 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.

[1150] 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.

[1151] 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.

[1152] [Third embodiment]

[1153] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1154] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1155] 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).

[1156] 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.

[1157] 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.

[1158] 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).

[1159] 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.

[1160] 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.

[1161] 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.

[1162] 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.

[1163] 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.

[1164] 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."

[1165] This invention relates to a system that personalizes lecture videos based on a user's profile information, summarizes the content, and provides a concrete action plan. It also aims to provide feedback based on the user's progress and promote sustainable growth. This system is realized using a user terminal, a server, and a generative AI model.

[1166] System Overview

[1167] Entering User Profile Information

[1168] Terminal

[1169] Users access a dedicated form to enter information about their interests, goals, and life stages, which the device receives and transmits to the server.

[1170] server

[1171] The server receives the user profile information sent from the device and stores it in a database.

[1172] Selected TED Talks

[1173] server

[1174] The server runs a generative AI model based on the stored user profile information, which analyzes a large database of lecture videos and selects the most relevant videos for the user.

[1175] Terminal

[1176] The selection results sent from the server are displayed on the device, allowing the user to select the video to watch.

[1177] Generate a summary and action plan

[1178] server

[1179] The server analyzes the selected lecture videos and uses a generative AI model to summarize the content, then generates specific action steps that users can implement in their real lives based on the summarized information.

[1180] Terminal

[1181] The summary and action plan sent from the server are displayed to the user, who then confirms and executes the action plan.

[1182] Progress tracking and feedback

[1183] Terminal

[1184] The user inputs the specific actions taken based on the action plan and their results into the device, which generates progress data.

[1185] server

[1186] The server receives the progress data sent from the device and stores it in a database, where it runs a generative AI model to generate customized feedback and next steps for the user.

[1187] Terminal

[1188] The feedback sent from the server and next steps of action are displayed to the user, which the user can use as a reference for continuous improvement.

[1189] Specific examples

[1190] Entering User Profile Information

[1191] Terminal

[1192] For example, if a user selects the areas of interest "health" and "career" and sets the goal of "improving leadership skills," they fill out this information in an input form and submit it.

[1193] server

[1194] The server receives this information and stores it in a database.

[1195] Selected TED Talks

[1196] server

[1197] The generative AI model analyzes the user's profile information and selects TED Talks related to "leadership," such as "Talks to improve leadership skills," and sends them to the user's device.

[1198] Terminal

[1199] A list of lecture videos sent from the server is displayed to the user, and the user can watch the videos from the options provided.

[1200] Generate a summary and action plan

[1201] server

[1202] It analyzes "lectures to improve leadership skills," generates summaries, and provides action steps such as "hold one-on-one discussions with team members once a week."

[1203] Terminal

[1204] A summary and action plan is presented to the user, who then follows through.

[1205] Progress tracking and feedback

[1206] Terminal

[1207] The user inputs the action they performed (e.g., "Had a one-on-one discussion").

[1208] server

[1209] The server receives the progress data, stores it in a database, and runs the generative AI model to generate feedback for the user (e.g., "Advice on how to further refine the discussion next time").

[1210] Terminal

[1211] It displays feedback and next steps to the user, allowing them to plan their next actions.

[1212] This allows users to achieve continuous growth and effectively apply the knowledge gained from lectures to real life.

[1213] The processing flow will be explained below.

[1214] Step 1:

[1215] Terminal

[1216] Present users with a form to input their interests, goals, and life stages. Users select their interests using checkboxes and enter their goals in text boxes. Ask them to select their life stage using a drop-down menu.

[1217] Step 2:

[1218] User

[1219] Enter the required information and click the submit button.

[1220] Step 3:

[1221] server

[1222] Receives user profile information (interests, goals, life stage) submitted through the form and stores it in a database.

[1223] Step 4:

[1224] server

[1225] The generative AI model is run based on the saved user profile information to select the most suitable lecture videos. For example, if a user's goal is to "improve leadership," the generative AI model will select lecture videos related to "leadership."

[1226] Step 5:

[1227] server

[1228] The generated list of lecture videos is sent to the user's device.

[1229] Step 6:

[1230] Terminal

[1231] The list of lecture videos sent from the server is displayed to the user, who then selects the video they wish to watch from the presented options.

[1232] Step 7:

[1233] User

[1234] Select the video you want to watch from the list of lecture videos displayed.

[1235] Step 8:

[1236] server

[1237] Selected lecture videos are analyzed and summaries are created using a generative AI model.

[1238] Step 9:

[1239] server

[1240] Based on the summary, the system generates concrete action steps that users can implement in their real lives, such as "Have one-on-one discussions with team members once a week."

[1241] Step 10:

[1242] server

[1243] A summary and action steps are sent to the user's device.

[1244] Step 11:

[1245] Terminal

[1246] The summary and action steps sent from the server are displayed to the user, who then confirms and executes the proposed action plan.

[1247] Step 12:

[1248] User

[1249] The user enters the actions they have taken (e.g., having a one-on-one discussion) into the device, which generates progress data.

[1250] Step 13:

[1251] Terminal

[1252] Sends progress data to the server.

[1253] Step 14:

[1254] server

[1255] Save the received progress data in a database.

[1256] Step 15:

[1257] server

[1258] Based on the progress data, generative AI models are run to generate customized feedback and next action steps for the user, such as advice to "provide specific feedback in the next discussion."

[1259] Step 16:

[1260] server

[1261] The generated feedback and next action steps are sent to the user's device.

[1262] Step 17:

[1263] Terminal

[1264] The feedback and next steps sent from the server are displayed to the user, allowing the user to plan their next action.

[1265] This allows users to watch the most relevant lecture videos, apply the content to their real lives, and receive feedback and advice to achieve sustainable growth.

[1266] Example 1

[1267] 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."

[1268] Current lecture videos and other video content make it difficult for users to find content that matches their interests and goals, and to obtain specific action plans for sustainable growth. As a result, users are overwhelmed with information and are unable to take effective action. Furthermore, there is insufficient provision of progress and feedback to individual users, and a lack of mechanisms to support sustainable growth.

[1269] 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.

[1270] In this invention, the server includes means for receiving and storing user profile information, means for selecting optimal video content using a generative AI model based on the user profile information, means for creating a summary from the selected video content using the generative AI model and providing a specific action plan that the user can implement in real life, means for receiving and storing user progress data, means for generating customized feedback using the generative AI model based on the progress data and providing it to the user, means for executing the generative AI model based on the stored user profile information to analyze and select relevant video content, means for analyzing the selected video content and generating a summary and an action plan, and means for generating customized feedback and next action steps. This allows users to easily find relevant content that aligns with their interests and goals, and to receive effective action plans and continuous feedback.

[1271] "User profile information" is information about a user that includes data such as their interests, goals, and life stage.

[1272] A "generative AI model" is an artificial intelligence algorithm that analyzes large amounts of data and generates optimal results based on specific conditions.

[1273] "Video Content" refers to lecture videos and other viewable video materials.

[1274] A "summary" is information that briefly summarizes the contents of the video content.

[1275] An "action plan" refers to specific action steps that users can take in their real lives based on the summarized information.

[1276] "Progress Data" is information including the specific actions taken by the user based on the action plan and the results of those actions.

[1277] "Feedback" refers to customized advice and next steps of action generated based on progress data.

[1278] "Server" means the computer system that receives and stores user profile information and progress data and runs the generative AI model.

[1279] "Terminal" refers to a device through which a user inputs information and displays information sent from a server.

[1280] This invention is a system that personalizes video content based on a user's profile information, summarizes the content, and provides a concrete action plan that the user can actually take. It also promotes sustainable growth by providing customized feedback based on the user's progress. The details are described below.

[1281] The system is realized using a user terminal, a server, and a generative AI model.

[1282] Entering User Profile Information

[1283] Terminal

[1284] Users enter information about their interests, goals, and life stages using a dedicated input form. For example, they can select areas of interest such as "health" or "career" and set a goal of "improving leadership skills." The device then sends this information to the server.

[1285] Store user profile information

[1286] server

[1287] The server receives the user profile information sent from the device and stores it in a database, allowing detailed profile information for each user to be accumulated.

[1288] Selected TED Talks

[1289] server

[1290] The server runs a generative AI model based on the stored user profile information. The generative AI model analyzes a large database of lecture videos and selects videos that are highly relevant to the user, such as a TED Talk on "Improving Leadership Skills."

[1291] Terminal

[1292] The selection results sent from the server are displayed on the device, and the user can select the video they want to watch. The user can then click on the video they are interested in from the displayed options to watch it.

[1293] Generate summaries and action plans

[1294] server

[1295] The server analyzes the selected lecture videos and summarizes their content using a generative AI model. Based on the summarized information, the server then provides users with a concrete action plan that they can implement in their daily lives. For example, it suggests specific action steps such as "Have one-on-one discussions with team members once a week."

[1296] Terminal

[1297] The summary and action plan sent from the server are displayed to the user, who then plans and executes specific actions based on the summary and action plan.

[1298] Tracking your progress

[1299] Terminal

[1300] The user inputs the specific actions they took based on the action plan and the results into the device. For example, they input the result of "having a one-on-one discussion." The device then sends this data to the server.

[1301] Providing feedback

[1302] server

[1303] The server receives the progress data and stores it in a database, then uses a generative AI model to analyze the user's progress and generate customized feedback and next action steps, such as "advice on how to further refine the discussion next time."

[1304] Terminal

[1305] The device displays feedback and next steps sent from the server to the user, allowing the user to plan their next actions and achieve continuous growth.

[1306] Examples of concrete examples and prompts

[1307] Specific examples

[1308] The user selects their areas of interest, "health" and "career," and sets the goal of "improving leadership skills." Then, they enter this information into a dedicated form and click the submit button. The server receives this information and stores it in a database.

[1309] The generative AI model analyzes the user's profile information and selects TED Talks related to "improving leadership skills." For example, it selects "lectures for improving leadership skills." The selection results sent from the server are displayed on the device, and the user selects the video to watch.

[1310] It analyzes the "Lecture for Improving Leadership Skills" and generates a summary. It then suggests specific action steps, such as "Have one-on-one discussions with team members once a week." The summary and action plan are displayed to the user, who then follows them.

[1311] Prompt Sentence Examples

[1312] "My areas of interest are health and career, and I am looking to improve my leadership skills."

[1313] "Please recommend a TED Talk related to leadership."

[1314] "Generate an action plan to help improve your leadership skills."

[1315] "Please suggest next steps of action after the discussion."

[1316] The system allows users to easily find relevant video content that aligns with their interests and goals, and provides effective action plans and continuous feedback.

[1317] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1318] Step 1:

[1319] Entering User Profile Information

[1320] Terminal

[1321] A user enters information about their interests, goals, and life stage into a dedicated input form. For example, they can select the areas of interest "health" and "career" and set the goal of "improving leadership skills." The entered information (input) is sent from the device to the server (output). The specific action performed by the device is for the user to fill in the information in the input form and click the submit button.

[1322] Step 2:

[1323] Store user profile information

[1324] server

[1325] The server receives the user profile information sent from the device (input) and stores it in a database (output). Specific operations include sorting the data received by the server and storing it in the corresponding database table.

[1326] Step 3:

[1327] Selected TED Talks

[1328] server

[1329] The server runs a generative AI model based on the stored user profile information. Using the user profile information as input, the generative AI model analyzes a large-scale lecture video database (data processing) and selects videos that are highly relevant to the user (output). Specifically, the AI ​​model filters out videos that best fit the user's interests and goals and outputs them as a list.

[1330] Terminal

[1331] The selection results (input) sent from the server are displayed on the terminal (output). The user selects the video they want to watch from the displayed video list. Specifically, the selected video list is displayed on the user's screen, allowing the user to make a selection.

[1332] Step 4:

[1333] Generate summaries and action plans

[1334] server

[1335] The server analyzes the selected lecture videos and uses a generative AI model to summarize their content. Using the selected video data as input, the generative AI model generates a summary of the content (data processing) and then generates an action plan that the user can implement in real life (output). Specifically, the AI ​​model extracts key points from the videos and devise action steps based on them.

[1336] Terminal

[1337] The summary and action plan (input) sent from the server are displayed to the user (output). The user uses this information to plan and execute specific actions. Specifically, the summarized information and action steps are displayed on the user's screen, allowing the user to understand and act.

[1338] Step 5:

[1339] Tracking your progress

[1340] Terminal

[1341] The user fills in an input form with the specific actions they took based on the action plan and the results. For example, they might enter "I had a one-on-one discussion" (input). The device then sends this data to the server (output). Specific actions include the user entering their progress and clicking the submit button.

[1342] Step 6:

[1343] Providing feedback

[1344] server

[1345] The server receives the progress data (input) and stores it in a database. It then uses a generative AI model to analyze the user's progress and generate customized feedback and next action steps (output). Specifically, the AI ​​model evaluates the user's progress and suggests the next action to take.

[1346] Terminal

[1347] The feedback sent from the server and the next action steps (input) are displayed to the user (output). The user uses this information to plan their next actions and aim for continuous growth. Specifically, the feedback information and next action plan are displayed on the user's screen so that the user can understand it and take the next step.

[1348] The above is the specific processing flow of this system.

[1349] (Application example 1)

[1350] 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."

[1351] Conventional lecture video delivery systems lacked personalization tailored to individual users' interests and goals, and did not clearly explain how the provided information could be applied to real life. Furthermore, they lacked the ability to provide feedback based on the user's progress or next steps of action, creating a need for a system that could support sustainable growth.

[1352] 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.

[1353] In this invention, the server includes means for receiving and storing user profile information, means for selecting an optimal lecture video using a generative AI model based on the user profile information, means for creating a summary from the selected lecture video using the generative AI model and providing the user with specific action steps that can be taken in real life, means for receiving and storing user progress data, means for generating customized feedback using the generative AI model based on the progress data and providing it to the user, and means for the user to wear a head-mounted display and watch the personalized video. This makes it possible to provide users with an individually optimized lecture video viewing experience and promote sustainable growth through the provision of specific action steps and feedback.

[1354] "User profile information" refers to individual information entered by a user, such as interests, goals, and life stage.

[1355] A "generative AI model" is an artificial intelligence model that performs generative tasks based on provided data, such as generating text, summarizing, and proposing action plans.

[1356] "Lecture videos" refers to video data of lectures or presentations intended to provide information.

[1357] A "summary" is a concise summary of a long lecture video.

[1358] "Specific action steps" refer to specific action items that users can carry out in their real lives based on the summarized content.

[1359] "Progress Data" refers to information about actions taken by a User and their results.

[1360] "Feedback" includes advice and suggestions for next actions provided to users based on progress data.

[1361] A "head-mounted display" is a display device worn by the user on the head, providing an immersive viewing experience.

[1362] This invention is a system for head-mounted displays (HMDs) that personalizes lecture videos based on the user's profile information, provides summaries and specific action plans, and provides feedback based on progress.

[1363] System Overview

[1364] Entering User Profile Information

[1365] Device:

[1366] Users access a dedicated form to input information such as interests, goals, and life stages, and then enter this information. The information is then sent to the server.

[1367] server:

[1368] The server receives the user profile information sent from the terminal and stores it in a database.

[1369] Selected TED Talks

[1370] server:

[1371] The server runs a generative AI model based on the stored user profile information. The generative AI model analyzes a database of lecture videos and selects the most relevant videos for the user. To do this, it uses a generative AI model such as OpenAI's GPT-3.

[1372] Device:

[1373] The selection results sent from the server are displayed on the device, and the user can select the video to watch.

[1374] Generate a summary and action plan

[1375] server:

[1376] The server analyzes the selected lecture videos and summarizes their content using a generative AI model. It then generates specific action steps that users can take in real life based on the summarized information. To achieve this, it uses the summarization function in Hugging Face's transformers package.

[1377] Device:

[1378] The summary and action plan sent from the server are displayed to the user, who then confirms the summary and takes action according to the action plan.

[1379] Progress tracking and feedback

[1380] Device:

[1381] The user inputs the specific actions taken based on the action plan and their results into the device, which generates progress data.

[1382] server:

[1383] The server receives the progress data sent from the device and stores it in a database, where it runs a generative AI model to generate customized feedback and next steps for the user.

[1384] Device:

[1385] The feedback and next action steps sent from the server are displayed to the user, who can use this to plan their next action.

[1386] Specific examples

[1387] Enter your user profile information:

[1388] For example, if a user selects the areas of interest "health" and "career" and sets "improving leadership skills" as a goal, the user inputs this information and transmits it to the server.

[1389] Selected TED Talks:

[1390] The server uses a generative AI model to analyze the user's profile information and select TED Talks related to "leadership," resulting in videos such as "lectures to improve leadership skills."

[1391] Generate a summary and action plan:

[1392] For example, a "lecture to improve leadership skills" could be analyzed and a generative AI model could generate a summary, providing specific action steps such as "hold one-on-one discussions with team members once a week."

[1393] Progress tracking and feedback:

[1394] When a user inputs "I had a one-on-one discussion," the server generates the next feedback (for example, "Advice on how to make the discussion more specific next time") based on the progress data.

[1395] Prompt Sentence Examples

[1396] "Find relevant TED Talks based on your profile: {Interests: 'Health, Career', Goal: 'Improve leadership skills', Life stage: '30s, Manager'}"

[1397] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1398] Step 1:

[1399] Entering User Profile Information

[1400] Device: The user enters profile information such as interests, goals, and life stage into a dedicated form. For example, they enter information such as "health," "career," and "improving leadership skills." The entered information is sent from the device to the server.

[1401] Input: Interests, goals, life stage

[1402] Output: User profile information data

[1403] Step 2:

[1404] Storing User Profile Information

[1405] Server: The server receives the user profile information sent from the device and stores it in a database.

[1406] Input: User profile information data

[1407] Output: User profile information stored in a database

[1408] Step 3:

[1409] Selected TED Talks

[1410] Server: The server runs a generative AI model (e.g., OpenAI's GPT-3) based on the stored user profile information. It sends prompts to the generative AI model to select relevant TED Talks. This process aims to select the best talk videos that correspond to the user's interests and goals.

[1411] Input: User profile information stored in the database

[1412] Output: The best TED Talk link for the user

[1413] Step 4:

[1414] Display of selection results

[1415] Terminal: Receives the selection results sent from the server and displays them to the user, who can then select the TED Talks that interest them.

[1416] Input: Link to the best TED Talk

[1417] Output: A link to the TED Talk displayed on the user's device.

[1418] Step 5:

[1419] Generate a summary and action plan

[1420] Server: The server analyzes selected TED Talk videos, creates summaries using a generative AI model (e.g., the summarization function in Hugging Face's transformers package), and generates specific action steps based on the summaries using the generative AI model.

[1421] Input: Video link of selected TED Talk

[1422] Output: Summary and concrete action plan

[1423] Step 6:

[1424] View summary and action plan

[1425] Terminal: Receives the summary and action plan sent from the server and displays it to the user. The user confirms the presented action plan and puts it into action.

[1426] Input: Summary and specific action plan data

[1427] Output: Summary and action plan displayed on user's device

[1428] Step 7:

[1429] Tracking your progress

[1430] Terminal: The user inputs the specific actions taken based on the action plan and their results into the terminal, which generates progress data and sends it to the server.

[1431] Input: User action result

[1432] Output: Progress data

[1433] Step 8:

[1434] Saving progress data

[1435] Server: The server receives the progress data sent from the terminal and stores it in a database.

[1436] Input: Progress data

[1437] Output: Progress data stored in a database

[1438] Step 9:

[1439] Generate feedback

[1440] Server: The server runs a generative AI model based on the stored progress data to generate customized feedback and next action steps for the user.

[1441] Input: Progress data stored in a database

[1442] Output: Customized feedback and next action steps

[1443] Step 10:

[1444] View Feedback

[1445] Terminal: Receives feedback and next action steps sent from the server and displays them to the user, who can then plan and execute their next action.

[1446] Input: Customized feedback and next action steps

[1447] Output: Feedback and next action steps displayed on the user's device

[1448] 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.

[1449] This invention relates to a system that personalizes lecture videos based on a user's profile information, summarizes the content, and provides a concrete action plan. It also aims to provide feedback based on the user's progress, promoting sustainable growth. Furthermore, the invention incorporates an emotion engine to improve the quality of TED Talk selection, summarization, action steps, and feedback based on the user's emotions. This system is implemented using a user device, a server, a generative AI model, and an emotion engine.

[1450] System Overview

[1451] Entering User Profile Information

[1452] Terminal

[1453] Users access a dedicated form to enter information about their interests, goals, and life stages, which the device receives and transmits to the server.

[1454] server

[1455] The server receives the user profile information sent from the device and stores it in a database.

[1456] Using an Emotion Engine to Select TED Talks

[1457] server

[1458] The server runs a generative AI model based on the user's saved profile information to select the most suitable lecture video. It also uses an emotion engine to analyze the user's emotional responses based on their past viewing history and optimizes the selection results based on their emotions. For example, if a user previously showed positive emotions toward videos related to "improving motivation," the server will prioritize videos with similar themes.

[1459] Terminal

[1460] The selection results sent from the server are displayed on the device, allowing the user to select the video to watch.

[1461] Generate a summary and action plan

[1462] server

[1463] The server analyzes the selected lecture videos and uses a generative AI model to summarize their content. It utilizes an emotion engine to analyze the user's real-time emotions and improve the applicability of the generated summaries and action plans. For example, it prioritizes content that the user expressed positive emotions about while watching and includes it in the summary. It also generates specific action steps that the user can implement in their real life based on the summary content.

[1464] Terminal

[1465] The summary and action plan sent from the server are displayed to the user, who then confirms and executes the action plan.

[1466] Progress tracking and feedback

[1467] Terminal

[1468] The user inputs the specific actions they took based on the action plan and their results into the device, which generates progress data. The emotion engine also collects emotional data during the action.

[1469] server

[1470] The server receives the progress and emotion data sent from the device and stores it in a database. Based on this data, it runs a generative AI model to generate customized feedback and next steps for the user. For example, based on the emotion data, it might provide advice such as "Create a relaxing environment for the next discussion."

[1471] Terminal

[1472] The feedback and next steps sent from the server are displayed to the user, allowing the user to plan their next action.

[1473] Specific examples

[1474] Entering User Profile Information

[1475] Terminal

[1476] For example, if a user selects the areas of interest "health" and "career" and sets the goal of "improving leadership skills," they fill out this information in an input form and submit it.

[1477] server

[1478] The server receives this information and stores it in a database.

[1479] Using an Emotion Engine to Select TED Talks

[1480] server

[1481] The generative AI model analyzes a user's profile information to select TED Talks related to "leadership." The emotion engine analyzes emotional data based on the user's viewing history and prioritizes leadership videos that elicit positive reactions. For example, if a user has previously shown high motivation from "leadership" videos, the model will select similar videos.

[1482] Terminal

[1483] A list of lecture videos sent from the server is displayed to the user, and the user can watch the videos from the options provided.

[1484] Generate a summary and action plan

[1485] server

[1486] The "Lecture for Improving Leadership Skills" is analyzed and a summary is generated. The emotion engine analyzes the user's emotional data in real time as they watch and reflects this in the summary. For example, points that elicit positive reactions are particularly emphasized. Action steps are also created, such as "Have one-on-one discussions with team members once a week."

[1487] Terminal

[1488] A summary and action plan is presented to the user, who then follows through.

[1489] Progress tracking and feedback

[1490] Terminal

[1491] Users input the actions they have taken (e.g., having a one-on-one discussion), and the device also collects emotional data during the action using an emotion engine.

[1492] server

[1493] The server receives the progress and emotion data, stores it in a database, and uses a generative AI model to generate customized feedback based on this data, such as "Create a relaxing environment for the next discussion."

[1494] Terminal

[1495] It displays feedback and next steps to the user so they can plan their next action.

[1496] This allows users to watch the most suitable lecture videos, receive support in applying the content to their real lives, taking into account their motivations and emotions, and receive emotionally-based feedback and advice to achieve continuous growth.

[1497] The processing flow will be explained below.

[1498] Step 1:

[1499] Terminal

[1500] Present users with a form to input their interests, goals, and life stages. Users select their interests using checkboxes and enter their goals in text boxes. Ask them to select their life stage using a drop-down menu.

[1501] Step 2:

[1502] User

[1503] Enter the required information and click the submit button.

[1504] Step 3:

[1505] server

[1506] Receives user profile information (interests, goals, life stage) submitted through the form and stores it in a database.

[1507] Step 4:

[1508] server

[1509] A generative AI model is run based on the saved user profile information to select the most suitable lecture video.

[1510] Step 5:

[1511] server

[1512] The emotional engine is used to analyze a user's emotional reactions based on their past viewing history and optimize the list of selected lecture videos. For example, if a user previously showed positive emotions from videos related to "motivation," videos on similar themes will be prioritized.

[1513] Step 6:

[1514] server

[1515] The generated list of lecture videos is sent to the user's device.

[1516] Step 7:

[1517] Terminal

[1518] The list of lecture videos sent from the server is displayed to the user, who then selects the video they wish to watch from the presented options.

[1519] Step 8:

[1520] User

[1521] Select the video you want to watch from the list of lecture videos displayed.

[1522] Step 9:

[1523] server

[1524] Selected lecture videos are analyzed and summaries are created using a generative AI model.

[1525] Step 10:

[1526] server

[1527] Based on the summary, the system generates specific action steps that users can take in real life. It uses an emotion engine to analyze the user's real-time emotions and reflect them in the summary. For example, it will emphasize content that the user expressed positive emotions about while watching.

[1528] Step 11:

[1529] server

[1530] A summary and action steps are sent to the user's device.

[1531] Step 12:

[1532] Terminal

[1533] The summary and action steps sent from the server are displayed to the user, who then confirms and executes the proposed action plan.

[1534] Step 13:

[1535] User

[1536] The user inputs the actions they have taken (e.g., having a one-on-one discussion) into the device, which generates progress data. The emotion engine also collects emotional data during the action.

[1537] Step 14:

[1538] Terminal

[1539] Send progress and emotion data to the server.

[1540] Step 15:

[1541] server

[1542] The received progress data and emotion data are stored in a database, and the emotion information is added to the progress data and run through a generative AI model to generate customized feedback and next action steps for the user.

[1543] Step 16:

[1544] server

[1545] The generated feedback and next steps are sent to the user's device, providing advice such as "Create a relaxing environment for your next discussion."

[1546] Step 17:

[1547] Terminal

[1548] The feedback sent from the server and next action steps are displayed to the user, allowing the user to plan their next action.

[1549] This allows users to watch the most suitable lecture videos, receive support in applying the content to their real lives, taking into account their motivations and emotions, and receive emotionally-based feedback and advice to achieve continuous growth.

[1550] Example 2

[1551] 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."

[1552] Conventional video content platforms lack personalization based on users' interests and goals, making it difficult to generate specific action plans after watching videos or provide emotional feedback. Furthermore, they lack support for continuous growth that takes into account users' progress and emotional data, making it difficult for users to apply these platforms in their real lives.

[1553] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving and storing user information, means for selecting optimal videos using a generative AI model based on the user's profile information, means for creating summaries from the selected videos using the generative AI model and providing specific action steps that the user can take in real life, means for analyzing the user's past viewing history using an emotion engine and optimizing the selection results based on emotions, means for receiving and storing user progress data and emotion data, and means for generating customized feedback using the generative AI model based on the progress data and emotion data and providing it to the user. This makes it possible to provide personalized video content that takes into account the user's profile information and emotion data, generate specific action plans, and provide feedback based on the user's progress.

[1554] "Your Information" refers to personal data you enter, such as your interests, goals, and life stage.

[1555] "Profile Information" refers to eclectic data about a user's interests, goals, and life stage.

[1556] "Generative AI models" refer to artificial intelligence algorithms that use collected data to select the most suitable videos, generate summaries, and provide action plans and feedback.

[1557] "Optimal videos" refer to video content that is determined to be most suitable and beneficial for an individual user based on the user's profile information and emotional data.

[1558] "Summary" refers to text information that briefly summarizes the content of the selected video.

[1559] "Action steps" refer to specific action plans that users can implement in their real lives based on the summarized video content.

[1560] The "emotion engine" refers to a function that analyzes users' viewing history and real-time emotional responses to improve the accuracy of video selection and feedback.

[1561] "Progress Data" refers to data regarding the specific actions a User takes based on an Action Plan and the results of those actions.

[1562] "Emotional data" refers to data that quantitatively or qualitatively evaluates the emotional responses shown by users while viewing or performing certain activities.

[1563] "Customized feedback" refers to advice and next steps that are individually tailored based on the user's progress and emotional data.

[1564] "System" refers to a collection of devices or software that includes a set of means for receiving user information, selecting videos, generating summaries, providing action plans, storing data, and providing feedback.

[1565] Entering User Profile Information

[1566] Terminal

[1567] Users enter information about their interests, goals, and life stages through a dedicated form. For example, if they select the areas of interest "health" and "career" and set "improving leadership skills" as their goal, they fill out the information in the input form and submit it. The device receives this information and sends it to the server.

[1568] server

[1569] The server receives the user profile information sent from the device and stores it in a database, which is used for subsequent processing to help select the most suitable TED Talk videos and generate summaries.

[1570] Using an Emotion Engine to Select TED Talks

[1571] server

[1572] The server runs a generative AI model based on the user's saved profile information to select the most suitable TED Talk video. During this process, the generative AI model lists multiple candidate videos that match the user's interests and goals. Next, an emotion engine analyzes the user's emotional response based on their past viewing history and prioritizes videos that elicit positive emotions. For example, if a user has previously expressed high motivation through videos related to "leadership," similar videos will be selected.

[1573] Terminal

[1574] The server sends the selection results to the device and displays them to the user, who can then select the video they want to watch from this list.

[1575] Generate a summary and action plan

[1576] server

[1577] The server analyzes selected TED Talk videos and uses a generative AI model to summarize their content. It also uses an emotion engine to analyze the user's real-time emotional responses and highlight parts that elicit positive reactions. Based on this, it generates specific action steps that the user can implement in their daily lives. For example, the server suggests specific actions based on the summary, such as "hold one-on-one discussions with team members once a week."

[1578] Terminal

[1579] The summary and action plan sent from the server are displayed on the terminal, allowing the user to confirm and put into action.

[1580] Progress tracking and feedback

[1581] Terminal

[1582] The user inputs specific actions based on the action plan and their results into the device. For example, they input information such as "I had a one-on-one discussion." The emotion engine also collects emotional data during the action and sends it to the server.

[1583] server

[1584] The server receives the progress and emotion data sent from the device and stores it in a database. Based on this data, it runs a generative AI model to generate customized feedback and next steps. For example, specific feedback such as "Create a relaxing environment for the next discussion" may be provided to the user.

[1585] Terminal

[1586] Feedback and next steps are displayed on the device, allowing users to plan their next actions.

[1587] Examples of concrete examples and prompts

[1588] Examples of entering user profile information

[1589] The user selects the areas of interest, "health" and "career," sets the goal as "learning leadership," and presses the "send" button.

[1590] A concrete example of using the Emotion Engine to select TED Talks

[1591] The generative AI model selects TED Talks related to "leadership," while the emotion engine prioritizes videos that have a positive response to "motivation" based on viewing history.

[1592] Example of generating a summary and action plan

[1593] The generative AI model summarizes "leadership skill improvement videos," highlights positive responses, and provides action steps such as "have a weekly discussion."

[1594] Prompt Sentence Examples

[1595] "Please enter your interests and goals below. Interests: Health, Career. Goal: Improve leadership skills."

[1596] "Select TED Talks related to leadership and prioritize videos that have shown high motivation in the past with your emotion engine."

[1597] "Summarize a TED Talk on improving leadership skills, highlight the points that generate positive responses, and generate action steps."

[1598] "Collect user behavior and their emotions, and provide feedback to recommend improvements to the next relaxing environment."

[1599] This allows the system to select the best TED Talk for each user, generate a summary, provide a specific action plan, and provide personalized feedback based on progress.

[1600] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1601] Step 1: Enter your user profile information

[1602] Terminal

[1603] Users access a dedicated form and enter information such as their areas of interest (e.g., "health" or "career"), goals (e.g., "improving leadership skills"), and life stage (e.g., "student" or "working adult"). The input data is converted into JSON format and sent to the server when the "Submit" button is pressed.

[1604] Input: Profile information entered by the user

[1605] Output: User profile information in JSON format sent to the server

[1606] server

[1607] The server receives the user profile information sent from the device, analyzes the received data with a parser, and stores it in a database.

[1608] Input: User profile information in JSON format

[1609] Output: User information is saved in the database

[1610] Step 2: Using the Emotion Engine to Select TED Talks

[1611] server

[1612] The server reads the user's profile information from the database and runs a generative AI model to select the most suitable TED Talk video. During this process, the generative AI model lists videos that match the user's interests and goals. Next, an emotion engine analyzes the user's past viewing history and prioritizes videos that show positive emotions based on the user's emotional response.

[1613] Input: User profile information stored in the database

[1614] Output: A list of selected TED Talk videos in JSON format

[1615] Terminal

[1616] The video list sent from the server is displayed on the device, and the user selects the video to watch from this list.

[1617] Input: A list of selected TED Talk videos in JSON format

[1618] Output: The ID of the video selected by the user.

[1619] Step 3: Generate a summary and action plan

[1620] server

[1621] Based on the video ID of the TED Talk selected by the user, the server uses a generative AI model to analyze the video content and generate a summary. An emotion engine analyzes the user's emotional data in real time and highlights parts that elicited positive reactions. Based on this, it generates specific action steps that the user can implement in their daily lives. For example, it generates an action step such as "Have one-on-one discussions with team members once a week."

[1622] Input: The ID of the video selected by the user

[1623] Output: JSON summary with specific action steps

[1624] Terminal

[1625] The summary and action plan sent from the server are displayed on the device, and the user confirms and carries out the plan.

[1626] Input: JSON summary and specific action steps

[1627] Output: A summary and action plan displayed to the user

[1628] Step 4: Progress tracking and feedback

[1629] Terminal

[1630] The user inputs the actions they performed based on the action plan and their results into the device. For example, they input information such as "I held a one-on-one discussion." The emotion engine also collects emotional data during the action and sends it to the server in JSON format.

[1631] Input: User actions and results, emotional data

[1632] Output: Progress and emotion data in JSON format is sent to the server.

[1633] server

[1634] The server receives the progress and emotion data sent from the device and stores it in a database. Based on this, it uses a generative AI model to generate customized feedback and next action steps, such as "Create a relaxing environment for the next discussion."

[1635] Input: User progress and emotion data in JSON format

[1636] Output: Customized feedback and next action steps in JSON format

[1637] Terminal

[1638] Feedback and next steps are displayed on the device, allowing users to plan their next actions.

[1639] Input: Customized feedback and next action steps in JSON format

[1640] Output: Feedback and next action steps displayed to the user

[1641] (Application example 2)

[1642] 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."

[1643] Conventional lecture video delivery systems often fail to adequately select optimal videos, summaries, and action plans based on the user's interests and goals. It is also difficult to provide feedback and action steps that take the user's emotions into account. In particular, there are insufficient means to provide personalized video selection and feedback by utilizing the user's viewing history and real-time emotional responses.

[1644] 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 means for receiving and storing user profile information, means for selecting optimal lecture videos using a generative AI model based on the user profile information, means for creating summaries from the selected lecture videos using the generative AI model and providing specific action steps that the user can take in real life, means for receiving and storing user progress data, means for generating customized feedback using the generative AI model based on the progress data and providing it to the user, and means for analyzing the user's emotional data using an emotion engine to improve the quality of video selection, summaries, and action steps. This enables personalized lecture video selection and summaries and action plans to be provided based on the user's profile information and emotional data. It also enables optimal feedback and next action steps to be provided based on the user's viewing history and real-time emotional reactions.

[1645] "User profile information" is information that includes personal attributes such as a user's interests, goals, and life stage.

[1646] A "generative AI model" is an artificial intelligence model that learns patterns from large datasets and generates optimal solutions to perform specific tasks.

[1647] A "lecture video" is a recorded video of a lecture given for educational, enlightening, or motivational purposes.

[1648] A "summary" is text or audio information that concisely summarizes the main points and content of a lecture video.

[1649] "Concrete action steps" are clear, practical action plans that users can implement in their real lives.

[1650] "Progress Data" means information about the specific actions a user takes based on an action plan and the results of those actions.

[1651] "Feedback" is information that includes evaluations and advice regarding actions taken by users.

[1652] "Emotion engine" is a general term for algorithms and software that analyze and evaluate users' emotions and provide the results to the system.

[1653] "Analysis" is the process of dissecting data and extracting meaning and patterns.

[1654] "Real-time" means that information processing and data analysis are carried out simultaneously with real time.

[1655] "Viewing history" is a record of videos of lectures that a user has viewed in the past.

[1656] "Customized Feedback" means feedback that is provided to you individually based on your individual profile information and progress data.

[1657] This invention is a system that personalizes lecture videos based on a user's profile information, summarizes the content, and provides a concrete action plan. Furthermore, it aims to provide feedback based on the user's progress, promoting sustainable growth. It also incorporates an emotion engine to improve the quality of video selection, summarization, action steps, and feedback based on the user's emotions.

[1658] System Overview

[1659] Entering User Profile Information

[1660] Users enter information about their interests, goals, and life stages into a dedicated form. This information is sent to a server via a device such as a smartphone. The server stores the received information in a database and uses it as material for implementing generative AI models.

[1661] Video selection using emotion engine

[1662] The server runs a generative AI model based on the stored user profile information to select the most suitable lecture videos, while using an emotion engine to analyze the emotional reactions from the user's viewing history and prioritize videos that elicit positive reactions.

[1663] Generate a summary and action plan

[1664] The selected videos are analyzed by the server, and a summary is created using a generative AI model. The emotion engine analyzes the user's emotional data in real time to improve the quality of the summary and action plan. For example, points to which the user responded positively can be highlighted in the summary and reflected in the action steps.

[1665] Progress tracking and feedback

[1666] Users input the specific actions they took based on the action plan and their results into their device and send them to the server. This progress data, along with emotional data, is stored on the server. The server then runs a generative AI model based on this data to provide customized feedback and next steps. This allows users to check their progress and plan their next actions.

[1667] Hardware and software used

[1668] Hardware: Smartphones, servers

[1669] Software: Python, JSON library

[1670] The data is sent from the smartphone to a server where it is analyzed and calculated. The generative AI model runs on the server, and the emotion engine analyzes the emotion data in real time. This allows for smooth personalized video selection and action plans.

[1671] Specific examples

[1672] For example, if a user selects the areas of interest "health" and "career" and sets the goal of "improving leadership skills," they input this information and send it to the server. The server uses this information to select TED Talks related to "leadership," prioritizing videos that have generated positive reactions based on past viewing history. It generates summaries of the selected videos and provides specific action plans, such as "hold one-on-one discussions with team members once a week."

[1673] Prompt Sentence Examples

[1674] "Profile Information:"

[1675] "Interests: Health, career"

[1676] "Goal: Improve leadership skills"

[1677] "Life Stage: Mid-Career"

[1678] "Selected TED Talks: Leadership Development Talks"

[1679] "Summary: Core Principles of Leadership"

[1680] "Specific action plan: Hold one-on-one discussions with team members once a week."

[1681] "Feedback: The importance of creating a relaxing environment"

[1682] "Emotional data: Positive"

[1683] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1684] Step 1:

[1685] The user enters information about their interests, goals, and life stages into a dedicated form on their smartphone and submits it, generating a user profile that is then sent from the device to a server, which stores the received information in a database.

[1686] Input: User interests, goals, and life stage information

[1687] Output: User profile information stored in a database

[1688] Specific operation: The terminal receives user input and sends the data to the server via a POST request. The server stores the received JSON data in a database.

[1689] Step 2:

[1690] The server uses a generative AI model to select the most suitable lecture video based on the user profile information stored on the server. It also uses an emotion engine to analyze the user's viewing history and prioritizes videos that have generated positive reactions.

[1691] Input: User profile information stored in the database

[1692] Output: List of selected lecture videos

[1693] How it works: The server runs the generative AI model and uses an algorithm that takes user profile information as input to filter and select the most suitable videos. The emotion engine analyzes viewing history and optimizes the selection results.

[1694] Step 3:

[1695] The server analyzes the selected lecture videos and generates a summary of the video using a generative AI model, utilizing an emotion engine to analyze the user's real-time emotional data and reflect it in the summary.

[1696] Input: Selected lecture videos

[1697] Output: Generated summary

[1698] How it works: The server analyzes the selected videos with a natural language processing algorithm and creates summaries using a generative AI model, while the emotion engine monitors users' real-time emotional data and reflects positive reactions in the summaries.

[1699] Step 4:

[1700] The server then uses the generated summary to provide specific action steps that the user can take in real life, customized based on the user's profile information and analysis results.

[1701] Input: Generated summary

[1702] Output: Specific action steps

[1703] How it works: Based on the summary, the server uses a generative AI model to create an action plan, with action steps customized based on the user's profile information and previous viewing history.

[1704] Step 5:

[1705] The user inputs the specific actions they took based on the action plan and the results into the device, which then sends the data to the server. The server receives the progress data and stores it in a database along with the emotion data.

[1706] Input: User action result data

[1707] Output: Progress and emotion data stored in a database

[1708] Specific operation: The user inputs the action result into the terminal, and the terminal sends the data to the server, which then stores the received data in a database.

[1709] Step 6:

[1710] The server uses a generative AI model to generate customized feedback and next action steps based on the progress and emotion data, and the generated feedback is sent to the device and displayed to the user.

[1711] Input: Progress data, emotion data

[1712] Output: Customized feedback and next action steps

[1713] Specific operation: The server analyzes the progress data and emotion data and generates customized feedback using a generative AI model. The generated feedback and next action steps are sent to the device and displayed to the user.

[1714] 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.

[1715] 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.

[1716] 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.

[1717] [Fourth embodiment]

[1718] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1719] 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.

[1720] 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).

[1721] 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.

[1722] 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.

[1723] 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).

[1724] 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.

[1725] 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.

[1726] 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.

[1727] 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.

[1728] 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.

[1729] 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.

[1730] 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."

[1731] This invention relates to a system that personalizes lecture videos based on a user's profile information, summarizes the content, and provides a concrete action plan. It also aims to provide feedback based on the user's progress and promote sustainable growth. This system is realized using a user terminal, a server, and a generative AI model.

[1732] System Overview

[1733] Entering User Profile Information

[1734] Terminal

[1735] Users access a dedicated form to enter information about their interests, goals, and life stages, which the device receives and transmits to the server.

[1736] server

[1737] The server receives the user profile information sent from the device and stores it in a database.

[1738] Selected TED Talks

[1739] server

[1740] The server runs a generative AI model based on the stored user profile information, which analyzes a large database of lecture videos and selects the most relevant videos for the user.

[1741] Terminal

[1742] The selection results sent from the server are displayed on the device, allowing the user to select the video to watch.

[1743] Generate a summary and action plan

[1744] server

[1745] The server analyzes the selected lecture videos and uses a generative AI model to summarize the content, then generates specific action steps that users can implement in their real lives based on the summarized information.

[1746] Terminal

[1747] The summary and action plan sent from the server are displayed to the user, who then confirms and executes the action plan.

[1748] Progress tracking and feedback

[1749] Terminal

[1750] The user inputs the specific actions taken based on the action plan and their results into the device, which generates progress data.

[1751] server

[1752] The server receives the progress data sent from the device and stores it in a database, where it runs a generative AI model to generate customized feedback and next steps for the user.

[1753] Terminal

[1754] The feedback sent from the server and next steps of action are displayed to the user, which the user can use as a reference for continuous improvement.

[1755] Specific examples

[1756] Entering User Profile Information

[1757] Terminal

[1758] For example, if a user selects the areas of interest "health" and "career" and sets the goal of "improving leadership skills," they fill out this information in an input form and submit it.

[1759] server

[1760] The server receives this information and stores it in a database.

[1761] Selected TED Talks

[1762] server

[1763] The generative AI model analyzes the user's profile information and selects TED Talks related to "leadership," such as "Talks to improve leadership skills," and sends them to the user's device.

[1764] Terminal

[1765] A list of lecture videos sent from the server is displayed to the user, and the user can watch the videos from the options provided.

[1766] Generate a summary and action plan

[1767] server

[1768] It analyzes "lectures to improve leadership skills," generates summaries, and provides action steps such as "hold one-on-one discussions with team members once a week."

[1769] Terminal

[1770] A summary and action plan is presented to the user, who then follows through.

[1771] Progress tracking and feedback

[1772] Terminal

[1773] The user inputs the action they performed (e.g., "Had a one-on-one discussion").

[1774] server

[1775] The server receives the progress data, stores it in a database, and runs the generative AI model to generate feedback for the user (e.g., "Advice on how to further refine the discussion next time").

[1776] Terminal

[1777] It displays feedback and next steps to the user, allowing them to plan their next actions.

[1778] This allows users to achieve continuous growth and effectively apply the knowledge gained from lectures to real life.

[1779] The processing flow will be explained below.

[1780] Step 1:

[1781] Terminal

[1782] Present users with a form to input their interests, goals, and life stages. Users select their interests using checkboxes and enter their goals in text boxes. Ask them to select their life stage using a drop-down menu.

[1783] Step 2:

[1784] User

[1785] Enter the required information and click the submit button.

[1786] Step 3:

[1787] server

[1788] Receives user profile information (interests, goals, life stage) submitted through the form and stores it in a database.

[1789] Step 4:

[1790] server

[1791] The generative AI model is run based on the saved user profile information to select the most suitable lecture videos. For example, if a user's goal is to "improve leadership," the generative AI model will select lecture videos related to "leadership."

[1792] Step 5:

[1793] server

[1794] The generated list of lecture videos is sent to the user's device.

[1795] Step 6:

[1796] Terminal

[1797] The list of lecture videos sent from the server is displayed to the user, who then selects the video they wish to watch from the presented options.

[1798] Step 7:

[1799] User

[1800] Select the video you want to watch from the list of lecture videos displayed.

[1801] Step 8:

[1802] server

[1803] Selected lecture videos are analyzed and summaries are created using a generative AI model.

[1804] Step 9:

[1805] server

[1806] Based on the summary, the system generates concrete action steps that users can implement in their real lives, such as "Have one-on-one discussions with team members once a week."

[1807] Step 10:

[1808] server

[1809] A summary and action steps are sent to the user's device.

[1810] Step 11:

[1811] Terminal

[1812] The summary and action steps sent from the server are displayed to the user, who then confirms and executes the proposed action plan.

[1813] Step 12:

[1814] User

[1815] The user enters the actions they have taken (e.g., having a one-on-one discussion) into the device, which generates progress data.

[1816] Step 13:

[1817] Terminal

[1818] Sends progress data to the server.

[1819] Step 14:

[1820] server

[1821] Save the received progress data in a database.

[1822] Step 15:

[1823] server

[1824] Based on the progress data, generative AI models are run to generate customized feedback and next action steps for the user, such as advice to "provide specific feedback in the next discussion."

[1825] Step 16:

[1826] server

[1827] The generated feedback and next action steps are sent to the user's device.

[1828] Step 17:

[1829] Terminal

[1830] The feedback and next steps sent from the server are displayed to the user, allowing the user to plan their next action.

[1831] This allows users to watch the most relevant lecture videos, apply the content to their real lives, and receive feedback and advice to achieve sustainable growth.

[1832] Example 1

[1833] 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."

[1834] Current lecture videos and other video content make it difficult for users to find content that matches their interests and goals, and to obtain specific action plans for sustainable growth. As a result, users are overwhelmed with information and are unable to take effective action. Furthermore, there is insufficient provision of progress and feedback to individual users, and a lack of mechanisms to support sustainable growth.

[1835] 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.

[1836] In this invention, the server includes means for receiving and storing user profile information, means for selecting optimal video content using a generative AI model based on the user profile information, means for creating a summary from the selected video content using the generative AI model and providing a specific action plan that the user can implement in real life, means for receiving and storing user progress data, means for generating customized feedback using the generative AI model based on the progress data and providing it to the user, means for executing the generative AI model based on the stored user profile information to analyze and select relevant video content, means for analyzing the selected video content and generating a summary and an action plan, and means for generating customized feedback and next action steps. This allows users to easily find relevant content that aligns with their interests and goals, and to receive effective action plans and continuous feedback.

[1837] "User profile information" is information about a user that includes data such as their interests, goals, and life stage.

[1838] A "generative AI model" is an artificial intelligence algorithm that analyzes large amounts of data and generates optimal results based on specific conditions.

[1839] "Video Content" refers to lecture videos and other viewable video materials.

[1840] A "summary" is information that briefly summarizes the contents of the video content.

[1841] An "action plan" refers to specific action steps that users can take in their real lives based on the summarized information.

[1842] "Progress Data" is information including the specific actions taken by the user based on the action plan and the results of those actions.

[1843] "Feedback" refers to customized advice and next steps of action generated based on progress data.

[1844] "Server" means the computer system that receives and stores user profile information and progress data and runs the generative AI model.

[1845] "Terminal" refers to a device through which a user inputs information and displays information sent from a server.

[1846] This invention is a system that personalizes video content based on a user's profile information, summarizes the content, and provides a concrete action plan that the user can actually take. It also promotes sustainable growth by providing customized feedback based on the user's progress. The details are described below.

[1847] The system is realized using a user terminal, a server, and a generative AI model.

[1848] Entering User Profile Information

[1849] Terminal

[1850] Users enter information about their interests, goals, and life stages using a dedicated input form. For example, they can select areas of interest such as "health" or "career" and set a goal of "improving leadership skills." The device then sends this information to the server.

[1851] Store user profile information

[1852] server

[1853] The server receives the user profile information sent from the device and stores it in a database, allowing detailed profile information for each user to be accumulated.

[1854] Selected TED Talks

[1855] server

[1856] The server runs a generative AI model based on the stored user profile information. The generative AI model analyzes a large database of lecture videos and selects videos that are highly relevant to the user, such as a TED Talk on "Improving Leadership Skills."

[1857] Terminal

[1858] The selection results sent from the server are displayed on the device, and the user can select the video they want to watch. The user can then click on the video they are interested in from the displayed options to watch it.

[1859] Generate summaries and action plans

[1860] server

[1861] The server analyzes the selected lecture videos and summarizes their content using a generative AI model. Based on the summarized information, the server then provides users with a concrete action plan that they can implement in their daily lives. For example, it suggests specific action steps such as "Have one-on-one discussions with team members once a week."

[1862] Terminal

[1863] The summary and action plan sent from the server are displayed to the user, who then plans and executes specific actions based on the summary and action plan.

[1864] Tracking your progress

[1865] Terminal

[1866] The user inputs the specific actions they took based on the action plan and the results into the device. For example, they input the result of "having a one-on-one discussion." The device then sends this data to the server.

[1867] Providing feedback

[1868] server

[1869] The server receives the progress data and stores it in a database, then uses a generative AI model to analyze the user's progress and generate customized feedback and next action steps, such as "advice on how to further refine the discussion next time."

[1870] Terminal

[1871] The device displays feedback and next steps sent from the server to the user, allowing the user to plan their next actions and achieve continuous growth.

[1872] Examples of concrete examples and prompts

[1873] Specific examples

[1874] The user selects their areas of interest, "health" and "career," and sets the goal of "improving leadership skills." Then, they enter this information into a dedicated form and click the submit button. The server receives this information and stores it in a database.

[1875] The generative AI model analyzes the user's profile information and selects TED Talks related to "improving leadership skills." For example, it selects "lectures for improving leadership skills." The selection results sent from the server are displayed on the device, and the user selects the video to watch.

[1876] It analyzes the "Lecture for Improving Leadership Skills" and generates a summary. It then suggests specific action steps, such as "Have one-on-one discussions with team members once a week." The summary and action plan are displayed to the user, who then follows them.

[1877] Prompt Sentence Examples

[1878] "My areas of interest are health and career, and I am looking to improve my leadership skills."

[1879] "Please recommend a TED Talk related to leadership."

[1880] "Generate an action plan to help improve your leadership skills."

[1881] "Please suggest next steps of action after the discussion."

[1882] The system allows users to easily find relevant video content that aligns with their interests and goals, and provides effective action plans and continuous feedback.

[1883] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1884] Step 1:

[1885] Entering User Profile Information

[1886] Terminal

[1887] A user enters information about their interests, goals, and life stage into a dedicated input form. For example, they can select the areas of interest "health" and "career" and set the goal of "improving leadership skills." The entered information (input) is sent from the device to the server (output). The specific action performed by the device is for the user to fill in the information in the input form and click the submit button.

[1888] Step 2:

[1889] Store user profile information

[1890] server

[1891] The server receives the user profile information sent from the device (input) and stores it in a database (output). Specific operations include sorting the data received by the server and storing it in the corresponding database table.

[1892] Step 3:

[1893] Selected TED Talks

[1894] server

[1895] The server runs a generative AI model based on the stored user profile information. Using the user profile information as input, the generative AI model analyzes a large-scale lecture video database (data processing) and selects videos that are highly relevant to the user (output). Specifically, the AI ​​model filters out videos that best fit the user's interests and goals and outputs them as a list.

[1896] Terminal

[1897] The selection results (input) sent from the server are displayed on the terminal (output). The user selects the video they want to watch from the displayed video list. Specifically, the selected video list is displayed on the user's screen, allowing the user to make a selection.

[1898] Step 4:

[1899] Generate summaries and action plans

[1900] server

[1901] The server analyzes the selected lecture videos and uses a generative AI model to summarize their content. Using the selected video data as input, the generative AI model generates a summary of the content (data processing) and then generates an action plan that the user can implement in real life (output). Specifically, the AI ​​model extracts key points from the videos and devise action steps based on them.

[1902] Terminal

[1903] The summary and action plan (input) sent from the server are displayed to the user (output). The user uses this information to plan and execute specific actions. Specifically, the summarized information and action steps are displayed on the user's screen, allowing the user to understand and act.

[1904] Step 5:

[1905] Tracking your progress

[1906] Terminal

[1907] The user fills in an input form with the specific actions they took based on the action plan and the results. For example, they might enter "I had a one-on-one discussion" (input). The device then sends this data to the server (output). Specific actions include the user entering their progress and clicking the submit button.

[1908] Step 6:

[1909] Providing feedback

[1910] server

[1911] The server receives the progress data (input) and stores it in a database. It then uses a generative AI model to analyze the user's progress and generate customized feedback and next action steps (output). Specifically, the AI ​​model evaluates the user's progress and suggests the next action to take.

[1912] Terminal

[1913] The feedback sent from the server and the next action steps (input) are displayed to the user (output). The user uses this information to plan their next actions and aim for continuous growth. Specifically, the feedback information and next action plan are displayed on the user's screen so that the user can understand it and take the next step.

[1914] The above is the specific processing flow of this system.

[1915] (Application example 1)

[1916] 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."

[1917] Conventional lecture video delivery systems lacked personalization tailored to individual users' interests and goals, and did not clearly explain how the provided information could be applied to real life. Furthermore, they lacked the ability to provide feedback based on the user's progress or next steps of action, creating a need for a system that could support sustainable growth.

[1918] 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.

[1919] In this invention, the server includes means for receiving and storing user profile information, means for selecting an optimal lecture video using a generative AI model based on the user profile information, means for creating a summary from the selected lecture video using the generative AI model and providing the user with specific action steps that can be taken in real life, means for receiving and storing user progress data, means for generating customized feedback using the generative AI model based on the progress data and providing it to the user, and means for the user to wear a head-mounted display and watch the personalized video. This makes it possible to provide users with an individually optimized lecture video viewing experience and promote sustainable growth through the provision of specific action steps and feedback.

[1920] "User profile information" refers to individual information entered by a user, such as interests, goals, and life stage.

[1921] A "generative AI model" is an artificial intelligence model that performs generative tasks based on provided data, such as generating text, summarizing, and proposing action plans.

[1922] "Lecture videos" refers to video data of lectures or presentations intended to provide information.

[1923] A "summary" is a concise summary of a long lecture video.

[1924] "Specific action steps" refer to specific action items that users can carry out in their real lives based on the summarized content.

[1925] "Progress Data" refers to information about actions taken by a User and their results.

[1926] "Feedback" includes advice and suggestions for next actions provided to users based on progress data.

[1927] A "head-mounted display" is a display device worn by the user on the head, providing an immersive viewing experience.

[1928] This invention is a system for head-mounted displays (HMDs) that personalizes lecture videos based on the user's profile information, provides summaries and specific action plans, and provides feedback based on progress.

[1929] System Overview

[1930] Entering User Profile Information

[1931] Device:

[1932] Users access a dedicated form to input information such as interests, goals, and life stages, and then enter this information. The information is then sent to the server.

[1933] server:

[1934] The server receives the user profile information sent from the terminal and stores it in a database.

[1935] Selected TED Talks

[1936] server:

[1937] The server runs a generative AI model based on the stored user profile information. The generative AI model analyzes a database of lecture videos and selects the most relevant videos for the user. To do this, it uses a generative AI model such as OpenAI's GPT-3.

[1938] Device:

[1939] The selection results sent from the server are displayed on the device, and the user can select the video to watch.

[1940] Generate a summary and action plan

[1941] server:

[1942] The server analyzes the selected lecture videos and summarizes their content using a generative AI model. It then generates specific action steps that users can take in real life based on the summarized information. To achieve this, it uses the summarization function in Hugging Face's transformers package.

[1943] Device:

[1944] The summary and action plan sent from the server are displayed to the user, who then confirms the summary and takes action according to the action plan.

[1945] Progress tracking and feedback

[1946] Device:

[1947] The user inputs the specific actions taken based on the action plan and their results into the device, which generates progress data.

[1948] server:

[1949] The server receives the progress data sent from the device and stores it in a database, where it runs a generative AI model to generate customized feedback and next steps for the user.

[1950] Device:

[1951] The feedback and next action steps sent from the server are displayed to the user, who can use this to plan their next action.

[1952] Specific examples

[1953] Enter your user profile information:

[1954] For example, if a user selects the areas of interest "health" and "career" and sets "improving leadership skills" as a goal, the user inputs this information and transmits it to the server.

[1955] Selected TED Talks:

[1956] The server uses a generative AI model to analyze the user's profile information and select TED Talks related to "leadership," resulting in videos such as "lectures to improve leadership skills."

[1957] Generate a summary and action plan:

[1958] For example, a "lecture to improve leadership skills" could be analyzed and a generative AI model could generate a summary, providing specific action steps such as "hold one-on-one discussions with team members once a week."

[1959] Progress tracking and feedback:

[1960] When a user inputs "I had a one-on-one discussion," the server generates the next feedback (for example, "Advice on how to make the discussion more specific next time") based on the progress data.

[1961] Prompt Sentence Examples

[1962] "Find relevant TED Talks based on your profile: {Interests: 'Health, Career', Goal: 'Improve leadership skills', Life stage: '30s, Manager'}"

[1963] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1964] Step 1:

[1965] Entering User Profile Information

[1966] Device: The user enters profile information such as interests, goals, and life stage into a dedicated form. For example, they enter information such as "health," "career," and "improving leadership skills." The entered information is sent from the device to the server.

[1967] Input: Interests, goals, life stage

[1968] Output: User profile information data

[1969] Step 2:

[1970] Storing User Profile Information

[1971] Server: The server receives the user profile information sent from the device and stores it in a database.

[1972] Input: User profile information data

[1973] Output: User profile information stored in a database

[1974] Step 3:

[1975] Selected TED Talks

[1976] Server: The server runs a generative AI model (e.g., OpenAI's GPT-3) based on the stored user profile information. It sends prompts to the generative AI model to select relevant TED Talks. This process aims to select the best talk videos that correspond to the user's interests and goals.

[1977] Input: User profile information stored in the database

[1978] Output: The best TED Talk link for the user

[1979] Step 4:

[1980] Display of selection results

[1981] Terminal: Receives the selection results sent from the server and displays them to the user, who can then select the TED Talks that interest them.

[1982] Input: Link to the best TED Talk

[1983] Output: A link to the TED Talk displayed on the user's device.

[1984] Step 5:

[1985] Generate a summary and action plan

[1986] Server: The server analyzes selected TED Talk videos, creates summaries using a generative AI model (e.g., the summarization function in Hugging Face's transformers package), and generates specific action steps based on the summaries using the generative AI model.

[1987] Input: Video link of selected TED Talk

[1988] Output: Summary and concrete action plan

[1989] Step 6:

[1990] View summary and action plan

[1991] Terminal: Receives the summary and action plan sent from the server and displays it to the user. The user confirms the presented action plan and puts it into action.

[1992] Input: Summary and specific action plan data

[1993] Output: Summary and action plan displayed on user's device

[1994] Step 7:

[1995] Tracking your progress

[1996] Terminal: The user inputs the specific actions taken based on the action plan and their results into the terminal, which generates progress data and sends it to the server.

[1997] Input: User action result

[1998] Output: Progress data

[1999] Step 8:

[2000] Saving progress data

[2001] Server: The server receives the progress data sent from the terminal and stores it in a database.

[2002] Input: Progress data

[2003] Output: Progress data stored in a database

[2004] Step 9:

[2005] Generate feedback

[2006] Server: The server runs a generative AI model based on the stored progress data to generate customized feedback and next action steps for the user.

[2007] Input: Progress data stored in a database

[2008] Output: Customized feedback and next action steps

[2009] Step 10:

[2010] View Feedback

[2011] Terminal: Receives feedback and next action steps sent from the server and displays them to the user, who can then plan and execute their next action.

[2012] Input: Customized feedback and next action steps

[2013] Output: Feedback and next action steps displayed on the user's device

[2014] 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.

[2015] This invention relates to a system that personalizes lecture videos based on a user's profile information, summarizes the content, and provides a concrete action plan. It also aims to provide feedback based on the user's progress, promoting sustainable growth. Furthermore, the invention incorporates an emotion engine to improve the quality of TED Talk selection, summarization, action steps, and feedback based on the user's emotions. This system is implemented using a user device, a server, a generative AI model, and an emotion engine.

[2016] System Overview

[2017] Entering User Profile Information

[2018] Terminal

[2019] Users access a dedicated form to enter information about their interests, goals, and life stages, which the device receives and transmits to the server.

[2020] server

[2021] The server receives the user profile information sent from the device and stores it in a database.

[2022] Using an Emotion Engine to Select TED Talks

[2023] server

[2024] The server runs a generative AI model based on the user's saved profile information to select the most suitable lecture video. It also uses an emotion engine to analyze the user's emotional responses based on their past viewing history and optimizes the selection results based on their emotions. For example, if a user previously showed positive emotions toward videos related to "improving motivation," the server will prioritize videos with similar themes.

[2025] Terminal

[2026] The selection results sent from the server are displayed on the device, allowing the user to select the video to watch.

[2027] Generate a summary and action plan

[2028] server

[2029] The server analyzes the selected lecture videos and uses a generative AI model to summarize their content. It utilizes an emotion engine to analyze the user's real-time emotions and improve the applicability of the generated summaries and action plans. For example, it prioritizes content that the user expressed positive emotions about while watching and includes it in the summary. It also generates specific action steps that the user can implement in their real life based on the summary content.

[2030] Terminal

[2031] The summary and action plan sent from the server are displayed to the user, who then confirms and executes the action plan.

[2032] Progress tracking and feedback

[2033] Terminal

[2034] The user inputs the specific actions they took based on the action plan and their results into the device, which generates progress data. The emotion engine also collects emotional data during the action.

[2035] server

[2036] The server receives the progress and emotion data sent from the device and stores it in a database. Based on this data, it runs a generative AI model to generate customized feedback and next steps for the user. For example, based on the emotion data, it might provide advice such as "Create a relaxing environment for the next discussion."

[2037] Terminal

[2038] The feedback and next steps sent from the server are displayed to the user, allowing the user to plan their next action.

[2039] Specific examples

[2040] Entering User Profile Information

[2041] Terminal

[2042] For example, if a user selects the areas of interest "health" and "career" and sets the goal of "improving leadership skills," they fill out this information in an input form and submit it.

[2043] server

[2044] The server receives this information and stores it in a database.

[2045] Using an Emotion Engine to Select TED Talks

[2046] server

[2047] The generative AI model analyzes a user's profile information to select TED Talks related to "leadership." The emotion engine analyzes emotional data based on the user's viewing history and prioritizes leadership videos that elicit positive reactions. For example, if a user has previously shown high motivation from "leadership" videos, the model will select similar videos.

[2048] Terminal

[2049] A list of lecture videos sent from the server is displayed to the user, and the user can watch the videos from the options provided.

[2050] Generate a summary and action plan

[2051] server

[2052] The "Lecture for Improving Leadership Skills" is analyzed and a summary is generated. The emotion engine analyzes the user's emotional data in real time as they watch and reflects this in the summary. For example, points that elicit positive reactions are particularly emphasized. Action steps are also created, such as "Have one-on-one discussions with team members once a week."

[2053] Terminal

[2054] A summary and action plan is presented to the user, who then follows through.

[2055] Progress tracking and feedback

[2056] Terminal

[2057] Users input the actions they have taken (e.g., having a one-on-one discussion), and the device also collects emotional data during the action using an emotion engine.

[2058] server

[2059] The server receives the progress and emotion data, stores it in a database, and uses a generative AI model to generate customized feedback based on this data, such as "Create a relaxing environment for the next discussion."

[2060] Terminal

[2061] It displays feedback and next steps to the user so they can plan their next action.

[2062] This allows users to watch the most suitable lecture videos, receive support in applying the content to their real lives, taking into account their motivations and emotions, and receive emotionally-based feedback and advice to achieve continuous growth.

[2063] The processing flow will be explained below.

[2064] Step 1:

[2065] Terminal

[2066] Present users with a form to input their interests, goals, and life stages. Users select their interests using checkboxes and enter their goals in text boxes. Ask them to select their life stage using a drop-down menu.

[2067] Step 2:

[2068] User

[2069] Enter the required information and click the submit button.

[2070] Step 3:

[2071] server

[2072] Receives user profile information (interests, goals, life stage) submitted through the form and stores it in a database.

[2073] Step 4:

[2074] server

[2075] A generative AI model is run based on the saved user profile information to select the most suitable lecture video.

[2076] Step 5:

[2077] server

[2078] The emotional engine is used to analyze a user's emotional reactions based on their past viewing history and optimize the list of selected lecture videos. For example, if a user previously showed positive emotions from videos related to "motivation," videos on similar themes will be prioritized.

[2079] Step 6:

[2080] server

[2081] The generated list of lecture videos is sent to the user's device.

[2082] Step 7:

[2083] Terminal

[2084] The list of lecture videos sent from the server is displayed to the user, who then selects the video they wish to watch from the presented options.

[2085] Step 8:

[2086] User

[2087] Select the video you want to watch from the list of lecture videos displayed.

[2088] Step 9:

[2089] server

[2090] Selected lecture videos are analyzed and summaries are created using a generative AI model.

[2091] Step 10:

[2092] server

[2093] Based on the summary, the system generates specific action steps that users can take in real life. It uses an emotion engine to analyze the user's real-time emotions and reflect them in the summary. For example, it will emphasize content that the user expressed positive emotions about while watching.

[2094] Step 11:

[2095] server

[2096] A summary and action steps are sent to the user's device.

[2097] Step 12:

[2098] Terminal

[2099] The summary and action steps sent from the server are displayed to the user, who then confirms and executes the proposed action plan.

[2100] Step 13:

[2101] User

[2102] The user inputs the actions they have taken (e.g., having a one-on-one discussion) into the device, which generates progress data. The emotion engine also collects emotional data during the action.

[2103] Step 14:

[2104] Terminal

[2105] Send progress and emotion data to the server.

[2106] Step 15:

[2107] server

[2108] The received progress data and emotion data are stored in a database, and the emotion information is added to the progress data and run through a generative AI model to generate customized feedback and next action steps for the user.

[2109] Step 16:

[2110] server

[2111] The generated feedback and next steps are sent to the user's device, providing advice such as "Create a relaxing environment for your next discussion."

[2112] Step 17:

[2113] Terminal

[2114] The feedback sent from the server and next action steps are displayed to the user, allowing the user to plan their next action.

[2115] This allows users to watch the most suitable lecture videos, receive support in applying the content to their real lives, taking into account their motivations and emotions, and receive emotionally-based feedback and advice to achieve continuous growth.

[2116] Example 2

[2117] 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."

[2118] Conventional video content platforms lack personalization based on users' interests and goals, making it difficult to generate specific action plans after watching videos or provide emotional feedback. Furthermore, they lack support for continuous growth that takes into account users' progress and emotional data, making it difficult for users to apply these platforms in their real lives.

[2119] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving and storing user information, means for selecting optimal videos using a generative AI model based on the user's profile information, means for creating summaries from the selected videos using the generative AI model and providing specific action steps that the user can take in real life, means for analyzing the user's past viewing history using an emotion engine and optimizing the selection results based on emotions, means for receiving and storing user progress data and emotion data, and means for generating customized feedback using the generative AI model based on the progress data and emotion data and providing it to the user. This makes it possible to provide personalized video content that takes into account the user's profile information and emotion data, generate specific action plans, and provide feedback based on the user's progress.

[2120] "Your Information" refers to personal data you enter, such as your interests, goals, and life stage.

[2121] "Profile Information" refers to eclectic data about a user's interests, goals, and life stage.

[2122] "Generative AI models" refer to artificial intelligence algorithms that use collected data to select the most suitable videos, generate summaries, and provide action plans and feedback.

[2123] "Optimal videos" refer to video content that is determined to be most suitable and beneficial for an individual user based on the user's profile information and emotional data.

[2124] "Summary" refers to text information that briefly summarizes the content of the selected video.

[2125] "Action steps" refer to specific action plans that users can implement in their real lives based on the summarized video content.

[2126] The "emotion engine" refers to a function that analyzes users' viewing history and real-time emotional responses to improve the accuracy of video selection and feedback.

[2127] "Progress Data" refers to data regarding the specific actions a User takes based on an Action Plan and the results of those actions.

[2128] "Emotional data" refers to data that quantitatively or qualitatively evaluates the emotional responses shown by users while viewing or performing certain activities.

[2129] "Customized feedback" refers to advice and next steps that are individually tailored based on the user's progress and emotional data.

[2130] "System" refers to a collection of devices or software that includes a set of means for receiving user information, selecting videos, generating summaries, providing action plans, storing data, and providing feedback.

[2131] Entering User Profile Information

[2132] Terminal

[2133] Users enter information about their interests, goals, and life stages through a dedicated form. For example, if they select the areas of interest "health" and "career" and set "improving leadership skills" as their goal, they fill out the information in the input form and submit it. The device receives this information and sends it to the server.

[2134] server

[2135] The server receives the user profile information sent from the device and stores it in a database, which is used for subsequent processing to help select the most suitable TED Talk videos and generate summaries.

[2136] Using an Emotion Engine to Select TED Talks

[2137] server

[2138] The server runs a generative AI model based on the user's saved profile information to select the most suitable TED Talk video. During this process, the generative AI model lists multiple candidate videos that match the user's interests and goals. Next, an emotion engine analyzes the user's emotional response based on their past viewing history and prioritizes videos that elicit positive emotions. For example, if a user has previously expressed high motivation through videos related to "leadership," similar videos will be selected.

[2139] Terminal

[2140] The server sends the selection results to the device and displays them to the user, who can then select the video they want to watch from this list.

[2141] Generate a summary and action plan

[2142] server

[2143] The server analyzes selected TED Talk videos and uses a generative AI model to summarize their content. It also uses an emotion engine to analyze the user's real-time emotional responses and highlight parts that elicit positive reactions. Based on this, it generates specific action steps that the user can implement in their daily lives. For example, the server suggests specific actions based on the summary, such as "hold one-on-one discussions with team members once a week."

[2144] Terminal

[2145] The summary and action plan sent from the server are displayed on the terminal, allowing the user to confirm and put into action.

[2146] Progress tracking and feedback

[2147] Terminal

[2148] The user inputs specific actions based on the action plan and their results into the device. For example, they input information such as "I had a one-on-one discussion." The emotion engine also collects emotional data during the action and sends it to the server.

[2149] server

[2150] The server receives the progress and emotion data sent from the device and stores it in a database. Based on this data, it runs a generative AI model to generate customized feedback and next steps. For example, specific feedback such as "Create a relaxing environment for the next discussion" may be provided to the user.

[2151] Terminal

[2152] Feedback and next steps are displayed on the device, allowing users to plan their next actions.

[2153] Examples of concrete examples and prompts

[2154] Examples of entering user profile information

[2155] The user selects the areas of interest, "health" and "career," sets the goal as "learning leadership," and presses the "send" button.

[2156] A concrete example of using the Emotion Engine to select TED Talks

[2157] The generative AI model selects TED Talks related to "leadership," while the emotion engine prioritizes videos that have a positive response to "motivation" based on viewing history.

[2158] Example of generating a summary and action plan

[2159] The generative AI model summarizes "leadership skill improvement videos," highlights positive responses, and provides action steps such as "have a weekly discussion."

[2160] Prompt Sentence Examples

[2161] "Please enter your interests and goals below. Interests: Health, Career. Goal: Improve leadership skills."

[2162] "Select TED Talks related to leadership and prioritize videos that have shown high motivation in the past with your emotion engine."

[2163] "Summarize a TED Talk on improving leadership skills, highlight the points that generate positive responses, and generate action steps."

[2164] "Collect user behavior and their emotions, and provide feedback to recommend improvements to the next relaxing environment."

[2165] This allows the system to select the best TED Talk for each user, generate a summary, provide a specific action plan, and provide personalized feedback based on progress.

[2166] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2167] Step 1: Enter your user profile information

[2168] Terminal

[2169] Users access a dedicated form and enter information such as their areas of interest (e.g., "health" or "career"), goals (e.g., "improving leadership skills"), and life stage (e.g., "student" or "working adult"). The input data is converted into JSON format and sent to the server when the "Submit" button is pressed.

[2170] Input: Profile information entered by the user

[2171] Output: User profile information in JSON format sent to the server

[2172] server

[2173] The server receives the user profile information sent from the device, analyzes the received data with a parser, and stores it in a database.

[2174] Input: User profile information in JSON format

[2175] Output: User information is saved in the database

[2176] Step 2: Using the Emotion Engine to Select TED Talks

[2177] server

[2178] The server reads the user's profile information from the database and runs a generative AI model to select the most suitable TED Talk video. During this process, the generative AI model lists videos that match the user's interests and goals. Next, an emotion engine analyzes the user's past viewing history and prioritizes videos that show positive emotions based on the user's emotional response.

[2179] Input: User profile information stored in the database

[2180] Output: A list of selected TED Talk videos in JSON format

[2181] Terminal

[2182] The video list sent from the server is displayed on the device, and the user selects the video to watch from this list.

[2183] Input: A list of selected TED Talk videos in JSON format

[2184] Output: The ID of the video selected by the user.

[2185] Step 3: Generate a summary and action plan

[2186] server

[2187] Based on the video ID of the TED Talk selected by the user, the server uses a generative AI model to analyze the video content and generate a summary. An emotion engine analyzes the user's emotional data in real time and highlights parts that elicited positive reactions. Based on this, it generates specific action steps that the user can implement in their daily lives. For example, it generates an action step such as "Have one-on-one discussions with team members once a week."

[2188] Input: The ID of the video selected by the user

[2189] Output: JSON summary with specific action steps

[2190] Terminal

[2191] The summary and action plan sent from the server are displayed on the device, and the user confirms and carries out the plan.

[2192] Input: JSON summary and specific action steps

[2193] Output: A summary and action plan displayed to the user

[2194] Step 4: Progress tracking and feedback

[2195] Terminal

[2196] The user inputs the actions they performed based on the action plan and their results into the device. For example, they input information such as "I held a one-on-one discussion." The emotion engine also collects emotional data during the action and sends it to the server in JSON format.

[2197] Input: User actions and results, emotional data

[2198] Output: Progress and emotion data in JSON format is sent to the server.

[2199] server

[2200] The server receives the progress and emotion data sent from the device and stores it in a database. Based on this, it uses a generative AI model to generate customized feedback and next action steps, such as "Create a relaxing environment for the next discussion."

[2201] Input: User progress and emotion data in JSON format

[2202] Output: Customized feedback and next action steps in JSON format

[2203] Terminal

[2204] Feedback and next steps are displayed on the device, allowing users to plan their next actions.

[2205] Input: Customized feedback and next action steps in JSON format

[2206] Output: Feedback and next action steps displayed to the user

[2207] (Application example 2)

[2208] 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."

[2209] Conventional lecture video delivery systems often fail to adequately select optimal videos, summaries, and action plans based on the user's interests and goals. It is also difficult to provide feedback and action steps that take the user's emotions into account. In particular, there are insufficient means to provide personalized video selection and feedback by utilizing the user's viewing history and real-time emotional responses.

[2210] 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 means for receiving and storing user profile information, means for selecting optimal lecture videos using a generative AI model based on the user profile information, means for creating summaries from the selected lecture videos using the generative AI model and providing specific action steps that the user can take in real life, means for receiving and storing user progress data, means for generating customized feedback using the generative AI model based on the progress data and providing it to the user, and means for analyzing the user's emotional data using an emotion engine to improve the quality of video selection, summaries, and action steps. This enables personalized lecture video selection and summaries and action plans to be provided based on the user's profile information and emotional data. It also enables optimal feedback and next action steps to be provided based on the user's viewing history and real-time emotional reactions.

[2211] "User profile information" is information that includes personal attributes such as a user's interests, goals, and life stage.

[2212] A "generative AI model" is an artificial intelligence model that learns patterns from large datasets and generates optimal solutions to perform specific tasks.

[2213] A "lecture video" is a recorded video of a lecture given for educational, enlightening, or motivational purposes.

[2214] A "summary" is text or audio information that concisely summarizes the main points and content of a lecture video.

[2215] "Concrete action steps" are clear, practical action plans that users can implement in their real lives.

[2216] "Progress Data" means information about the specific actions a user takes based on an action plan and the results of those actions.

[2217] "Feedback" is information that includes evaluations and advice regarding actions taken by users.

[2218] "Emotion engine" is a general term for algorithms and software that analyze and evaluate users' emotions and provide the results to the system.

[2219] "Analysis" is the process of dissecting data and extracting meaning and patterns.

[2220] "Real-time" means that information processing and data analysis are carried out simultaneously with real time.

[2221] "Viewing history" is a record of videos of lectures that a user has viewed in the past.

[2222] "Customized Feedback" means feedback that is provided to you individually based on your individual profile information and progress data.

[2223] This invention is a system that personalizes lecture videos based on a user's profile information, summarizes the content, and provides a concrete action plan. Furthermore, it aims to provide feedback based on the user's progress, promoting sustainable growth. It also incorporates an emotion engine to improve the quality of video selection, summarization, action steps, and feedback based on the user's emotions.

[2224] System Overview

[2225] Entering User Profile Information

[2226] Users enter information about their interests, goals, and life stages into a dedicated form. This information is sent to a server via a device such as a smartphone. The server stores the received information in a database and uses it as material for implementing generative AI models.

[2227] Video selection using emotion engine

[2228] The server runs a generative AI model based on the stored user profile information to select the most suitable lecture videos, while using an emotion engine to analyze the emotional reactions from the user's viewing history and prioritize videos that elicit positive reactions.

[2229] Generate a summary and action plan

[2230] The selected videos are analyzed by the server, and a summary is created using a generative AI model. The emotion engine analyzes the user's emotional data in real time to improve the quality of the summary and action plan. For example, points to which the user responded positively can be highlighted in the summary and reflected in the action steps.

[2231] Progress tracking and feedback

[2232] Users input the specific actions they took based on the action plan and their results into their device and send them to the server. This progress data, along with emotional data, is stored on the server. The server then runs a generative AI model based on this data to provide customized feedback and next steps. This allows users to check their progress and plan their next actions.

[2233] Hardware and software used

[2234] Hardware: Smartphones, servers

[2235] Software: Python, JSON library

[2236] The data is sent from the smartphone to a server where it is analyzed and calculated. The generative AI model runs on the server, and the emotion engine analyzes the emotion data in real time. This allows for smooth personalized video selection and action plans.

[2237] Specific examples

[2238] For example, if a user selects the areas of interest "health" and "career" and sets the goal of "improving leadership skills," they input this information and send it to the server. The server uses this information to select TED Talks related to "leadership," prioritizing videos that have generated positive reactions based on past viewing history. It generates summaries of the selected videos and provides specific action plans, such as "hold one-on-one discussions with team members once a week."

[2239] Prompt Sentence Examples

[2240] "Profile Information:"

[2241] "Interests: Health, career"

[2242] "Goal: Improve leadership skills"

[2243] "Life Stage: Mid-Career"

[2244] "Selected TED Talks: Leadership Development Talks"

[2245] "Summary: Core Principles of Leadership"

[2246] "Specific action plan: Hold one-on-one discussions with team members once a week."

[2247] "Feedback: The importance of creating a relaxing environment"

[2248] "Emotional data: Positive"

[2249] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2250] Step 1:

[2251] The user enters information about their interests, goals, and life stages into a dedicated form on their smartphone and submits it, generating a user profile that is then sent from the device to a server, which stores the received information in a database.

[2252] Input: User interests, goals, and life stage information

[2253] Output: User profile information stored in a database

[2254] Specific operation: The terminal receives user input and sends the data to the server via a POST request. The server stores the received JSON data in a database.

[2255] Step 2:

[2256] The server uses a generative AI model to select the most suitable lecture video based on the user profile information stored on the server. It also uses an emotion engine to analyze the user's viewing history and prioritizes videos that have generated positive reactions.

[2257] Input: User profile information stored in the database

[2258] Output: List of selected lecture videos

[2259] How it works: The server runs the generative AI model and uses an algorithm that takes user profile information as input to filter and select the most suitable videos. The emotion engine analyzes viewing history and optimizes the selection results.

[2260] Step 3:

[2261] The server analyzes the selected lecture videos and generates a summary of the video using a generative AI model, utilizing an emotion engine to analyze the user's real-time emotional data and reflect it in the summary.

[2262] Input: Selected lecture videos

[2263] Output: Generated summary

[2264] How it works: The server analyzes the selected videos with a natural language processing algorithm and creates summaries using a generative AI model, while the emotion engine monitors users' real-time emotional data and reflects positive reactions in the summaries.

[2265] Step 4:

[2266] The server then uses the generated summary to provide specific action steps that the user can take in real life, customized based on the user's profile information and analysis results.

[2267] Input: Generated summary

[2268] Output: Specific action steps

[2269] How it works: Based on the summary, the server uses a generative AI model to create an action plan, with action steps customized based on the user's profile information and previous viewing history.

[2270] Step 5:

[2271] The user inputs the specific actions they took based on the action plan and the results into the device, which then sends the data to the server. The server receives the progress data and stores it in a database along with the emotion data.

[2272] Input: User action result data

[2273] Output: Progress and emotion data stored in a database

[2274] Specific operation: The user inputs the action result into the terminal, and the terminal sends the data to the server, which then stores the received data in a database.

[2275] Step 6:

[2276] The server uses a generative AI model to generate customized feedback and next action steps based on the progress and emotion data, and the generated feedback is sent to the device and displayed to the user.

[2277] Input: Progress data, emotion data

[2278] Output: Customized feedback and next action steps

[2279] Specific operation: The server analyzes the progress data and emotion data and generates customized feedback using a generative AI model. The generated feedback and next action steps are sent to the device and displayed to the user.

[2280] 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.

[2281] 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.

[2282] 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 robot 414.

[2283] 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.

[2284] 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.

[2285] 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.

[2286] 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).

[2287] 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.

[2288] 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."

[2289] 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.

[2290] 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).

[2291] 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.

[2292] 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.

[2293] 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.

[2294] 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.

[2295] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[2296] 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.

[2297] 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.

[2298] 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.

[2299] 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.

[2300] 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.

[2301] The following is further disclosed regarding the above embodiment.

[2302] (Claim 1)

[2303] A means for receiving and storing user profile information;

[2304] A means to select the most suitable lecture video using a generative AI model based on the user's profile information;

[2305] A means to create summaries from selected lecture videos using a generative AI model and provide users with concrete action steps they can take in real life; and

[2306] means for receiving and storing user progress data;

[2307] a means of generating and providing customized feedback to the user using a generative AI model based on the progress data;

[2308] A system including:

[2309] (Claim 2)

[2310] 10. The system of claim 1, further comprising means for generating customized feedback based on the progress data and providing specific next action steps to the user.

[2311] (Claim 3)

[2312] 10. The system of claim 1, further comprising means for identifying the user's interests, goals, and life stages based on the user's profile information.

[2313] "Example 1"

[2314] (Claim 1)

[2315] means for receiving and storing user profile information;

[2316] A means of selecting optimal video content using a generative AI model based on user profile information; and

[2317] A means to create summaries from selected video content using a generative AI model and provide users with concrete action plans that they can implement in their real lives; and

[2318] means for receiving and storing user progress data;

[2319] a means of generating and providing customized feedback to the user using a generative AI model based on the progress data;

[2320] A means for executing a generative AI model based on stored user profile information to analyze and select relevant video content; and

[2321] means for analyzing the selected video content and generating a summary and action plan;

[2322] a means of generating customized feedback and next action steps;

[2323] A system including:

[2324] (Claim 2)

[2325] 10. The system of claim 1, further comprising means for generating customized feedback based on the progress data and providing the user with a specific next course of action.

[2326] (Claim 3)

[2327] 10. The system of claim 1, further comprising means for identifying the user's interests, goals, and life stages based on the user's profile information.

[2328] "Application Example 1"

[2329] (Claim 1)

[2330] A means for receiving and storing user profile information;

[2331] A means to select the most suitable lecture video using a generative AI model based on the user's profile information;

[2332] A means to create summaries from selected lecture videos using a generative AI model and provide users with concrete action steps they can take in real life; and

[2333] means for receiving and storing user progress data;

[2334] a means of generating and providing customized feedback to the user using a generative AI model based on the progress data;

[2335] A means for users to view personalized videos while wearing a head-mounted display;

[2336] A system including:

[2337] (Claim 2)

[2338] 10. The system of claim 1, further comprising means for generating customized feedback based on the progress data and providing specific next action steps to the user.

[2339] (Claim 3)

[2340] 10. The system of claim 1, further comprising means for identifying the user's interests, goals, and life stages based on the user's profile information.

[2341] "Example 2: Combining Emotion Engines"

[2342] (Claim 1)

[2343] A means of receiving and storing your information;

[2344] A means to select the best videos using a generative AI model based on the user's profile information;

[2345] A means to create summaries from selected videos using a generative AI model to provide users with concrete actionable steps they can take in their real lives; and

[2346] A means of analyzing users' past viewing history using an emotion engine and optimizing selection results based on emotions;

[2347] means for receiving and storing user progress and emotion data;

[2348] a means for generating and providing customized feedback to the user using a generative AI model based on the progress data and sentiment data;

[2349] A system including:

[2350] (Claim 2)

[2351] 10. The system of claim 1, further comprising means for generating customized feedback based on the progress data and the emotion data and providing specific next action steps to the user.

[2352] (Claim 3)

[2353] 10. The system of claim 1, further comprising means for identifying the user's interests, goals, and life stages based on the user's profile information.

[2354] "Application example 2 when combining emotion engines"

[2355] New invention claims

[2356] (Claim 1)

[2357] A means for receiving and storing user profile information;

[2358] A means to select the most suitable lecture video using a generative AI model based on the user's profile information;

[2359] A means to create summaries from selected lecture videos using a generative AI model and provide users with concrete action steps they can take in real life; and

[2360] means for receiving and storing user progress data;

[2361] a means of generating and providing customized feedback to the user using a generative AI model based on the progress data;

[2362] A means for analyzing user sentiment data using an emotion engine to improve the quality of video selection, summarization, and action steps;

[2363] A system including:

[2364] (Claim 2)

[2365] 10. The system of claim 1, further comprising means for generating customized feedback based on the progress data and providing specific next action steps to the user.

[2366] (Claim 3)

[2367] 10. The system of claim 1, further comprising means for identifying the user's interests, goals, and life stages based on the user's profile information.

[2368] (Claim 4)

[2369] The system according to claim 1, further comprising means for analyzing emotional data based on viewing history and preferentially selecting videos that have generated positive reactions.

[2370] (Claim 5)

[2371] 5. The system according to claim 4, further comprising means for analyzing emotion data in real time and reflecting the data in the summary and the action plan.

[2372] Commentary

[2373] This includes new technologies such as:

[2374] Using an emotion engine to analyze user emotion data to improve the quality of video selection, summarization, and action steps.

[2375] It analyzes emotional data based on viewing history and prioritizes videos that have generated positive reactions.

[2376] Analyzing emotional data in real time and incorporating it into summaries and action plans.

[2377] This allows the entire system to be more personalized and provide an optimal experience based on the user's emotions. [Explanation of symbols]

[2378] 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 receiving and storing user profile information; A means to select the most suitable lecture video using a generative AI model based on the user's profile information; A means to create summaries from selected lecture videos using a generative AI model and provide users with concrete action steps they can take in real life; and means for receiving and storing user progress data; a means of generating and providing customized feedback to the user using a generative AI model based on the progress data; A system including:

2. 10. The system of claim 1, further comprising means for generating customized feedback based on the progress data and providing specific next action steps to the user.

3. 10. The system of claim 1, further comprising means for identifying the user's interests, goals, and life stages based on the user's profile information.

Images