system

Abstract

Provide a system. [Solution] means for accepting a generation request; a generating means for generating a surprise element based on a generation request; a distribution means for distributing the generated surprise element to a user terminal; a collection means for collecting user responses; an improvement means for analyzing the collected responses and improving the generation means; A system including:

Description

[Technical Field]

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

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

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

[0004] Conventional entertainment systems and business tools lack the functionality to surprise and delight users, making it difficult to capture their attention and refresh them. Furthermore, these systems lack a feedback loop to sustain the effect of a surprise once it has been delivered, making it difficult to improve the quality of the surprise elements they generate. Therefore, new methods for delivering sustained and effective surprise and delight in entertainment and business settings are needed. The present invention aims to solve these problems and provide a system that delivers unpredictable surprises to users. [Means for solving the problem]

[0005] The present invention solves the above problems by the following means. First, by providing a means for receiving a generation request, the system starts operating in response to a request from a user. Next, a generation means is provided for generating a surprise element based on the generation request. This generation means utilizes AI technology to generate surprise elements in various formats, such as audio, images, videos, or text. Furthermore, a distribution means is provided for distributing the generated surprise element to a user terminal, allowing the user to experience the generated surprise element in real time. In addition, a collection means is provided for collecting user reactions, and by combining this collection with the generation means, user reactions to the generated surprise element are collected in real time. Finally, an improvement means is provided for analyzing the collected reactions and improving the generation means. By forming this feedback loop, the system can continuously improve the quality of the surprise element and provide a more effective entertainment experience.

[0006] A "generation request" is an instruction for the system to generate a specific surprise element based on input or operation from the user.

[0007] "Surprise elements" are unpredictable content generated in a variety of formats, such as audio, images, video, and text, and are intended to surprise users.

[0008] The "generation means" is a component within the system that receives a generation request and creates a surprise element, and includes an AI engine, etc.

[0009] The "distribution means" is a component within the system for transmitting the generated surprise element to a user terminal.

[0010] A "collection means" is a component within the system for obtaining user reactions and feedback.

[0011] The "improvement means" is a component within the system that analyzes user response data obtained by the collection means and adjusts the algorithms and parameters of the generation means to improve the quality of the surprise element.

[0012] "User terminal" means the electronic device through which a user accesses the system and experiences the wow factor. [Brief explanation of the drawings]

[0013] [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

[0014] 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.

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

[0016] 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).

[0017] 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.

[0018] 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.

[0019] 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.

[0020] 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."

[0021] [First embodiment]

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

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0028] 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.

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

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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."

[0034] The present invention relates to a system that accepts a generation request, generates a surprise element, and delivers it to a user terminal. It also has a feedback function that collects user reactions and improves the generation means based on that data. A detailed description of an embodiment of this system is provided below.

[0035] System configuration

[0036] This system is broadly composed of three components: the server, the terminal, and the user.

[0037] server

[0038] The server is the central component that receives production requests, generates the wow factor, and distributes it. Specifically, it has the following functions:

[0039] 1. Generation request reception function: A function to accept generation requests from terminals.

[0040] 2. Generation function: A function that generates surprise elements based on generation requests. Using an AI engine, surprise elements are generated in various formats, including audio, images, videos, and text.

[0041] 3. Distribution function: The function to send the generated surprise element to the terminal.

[0042] 4. Reaction collection function: A function for receiving user reaction data.

[0043] 5. Improvement function: A function to analyze collected reaction data and improve the generation function.

[0044] Terminal

[0045] The terminal is the device through which the user accesses the system and experiences the wow factor. The terminal has the following functions:

[0046] 1. Generation request sending function: An interface for users to input generation requests. A function to send generation requests to the server.

[0047] 2. Display function: A function to display or play the surprise elements delivered from the server.

[0048] 3. Reaction input function: An interface for inputting user reactions. A function for sending reaction data to the server.

[0049] System Operation

[0050] The system of the present invention operates as follows.

[0051] 1. The user enters a generation request

[0052] User: Click the "Generate Surprise" button on the device.

[0053] Terminal: Detects the click event and sends a generation request to the server.

[0054] 2. Receive the generation request and generate the wow factor

[0055] Server: Receives the generation request and analyzes its contents.

[0056] Server: Uses the generation function to instruct the AI ​​engine to generate surprising elements (e.g., interesting images, audio, video, text).

[0057] 3. Deliver surprise elements to devices

[0058] Server: Sends the generated surprise element to the device.

[0059] Terminal: Display or play the received surprise element in an appropriate format.

[0060] 4. Collect user responses

[0061] User: Experience the surprise element and enter their thoughts and ratings through the reaction interface.

[0062] Terminal: Sends user reaction data to the server.

[0063] 5. Improve based on collected response data

[0064] Server: Receives reaction data and stores it for analysis.

[0065] Server: Use the collected data to improve the generation function and reflect it in the next surprise element generation.

[0066] Specific examples

[0067] For example, if you use this system while video chatting with a friend, it works as follows:

[0068] 1. The user enters a generation request

[0069] User: Click the "Generate Surprise Button" during a video chat.

[0070] 2. Receive the generation request and generate the wow factor

[0071] Server: Receives the generation request and generates an interesting GIF image using the generation function.

[0072] 3. Deliver surprise elements to devices

[0073] Server: Sends the generated GIF image to the device.

[0074] Device: Display GIF images in video chat apps.

[0075] 4. Collect user responses

[0076] User: Enters reactions through the reaction interface, such as surprise or laughter.

[0077] Device: Sends reaction data to the server.

[0078] 5. Improve based on collected response data

[0079] Server: Receives reaction data and stores it for analysis.

[0080] Server: Improve the generation function based on the data and use it for the next generation.

[0081] As described above, the system of the present invention not only generates a variety of surprise elements based on generation requests, providing users with new enjoyment and surprises, but also provides a more effective entertainment experience by continuously improving the system based on collected reaction data.

[0082] The processing flow will be explained below.

[0083] Step 1:

[0084] User: Click the "Generate Surprise" button on the device.

[0085] Step 2:

[0086] Terminal: Detects a click event and generates generation request data (e.g., user ID, current context information, parameters for generation, etc.).

[0087] Step 3:

[0088] Terminal: Sends the generation request data to the server.

[0089] Step 4:

[0090] Server: Receives the generation request data sent from the terminal.

[0091] Step 5:

[0092] Server: Analyzes the generation request data and determines what type of surprise element (e.g., audio, image, video, text, etc.) to generate.

[0093] Step 6:

[0094] Server: Calls the generation means and generates surprise elements based on the specified parameters. At this time, an AI engine is used to generate optimal surprise elements based on the user's past reaction data and generation request data.

[0095] Step 7:

[0096] Server: Temporarily stores the generated surprise elements and formats them for delivery to the device.

[0097] Step 8:

[0098] Server: Delivers the prepared surprise elements to the device.

[0099] Step 9:

[0100] Terminal: Receives the surprise element received from the server and displays or plays it in the specified format (e.g., displays an image on the screen, plays a sound).

[0101] Step 10:

[0102] User: Experience the surprise element and enter their thoughts and ratings through the reaction interface.

[0103] Step 11:

[0104] Terminal: Collects user reaction data and sends it to the server.

[0105] Step 12:

[0106] Server: Receives collected user response data and stores it in a database for analysis.

[0107] Step 13:

[0108] Server: Based on the response data, the algorithms and parameters of the generation method are adjusted, and improvements are made to create a better element of surprise for the next generation request.

[0109] Example 1

[0110] 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."

[0111] In conventional systems, the generation of elements to surprise and entertain users is monotonous, and the generation process is rarely improved based on individual user responses. Therefore, it is difficult to maintain user interest.

[0112] 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.

[0113] In this invention, the server includes means for receiving a generation request, means for generating a surprise element using a generative AI model based on the generation request, means for distributing the generated surprise element to a user terminal, means for collecting user responses, and means for analyzing the collected responses and improving the generation means. This makes it possible to provide individual surprise elements to users and improve the content of subsequent generations based on the responses.

[0114] A "generation request" is an action or content of a user requesting the system to generate a surprise element.

[0115] A "generative AI model" is an artificial intelligence engine that uses artificial intelligence technology to generate audio, images, videos, text, etc. based on input prompts.

[0116] A "prompt" is a sentence or text that gives specific instructions to the generative AI model on what to generate.

[0117] A "surprise element" is digital content such as audio, images, video, and text that is created to surprise and entertain users.

[0118] The "distribution means" is a function or process for transmitting the generated surprise element to the user terminal.

[0119] The "collection means" is a function or process for collecting user reaction data.

[0120] "Improvement means" refers to the function or process for analyzing collected response data and improving generative AI models or generative algorithms.

[0121] A "user terminal" is a device through which a user accesses the system and experiences the generated surprise elements.

[0122] This invention relates to a system that accepts generation requests, generates surprise elements, and delivers them to user terminals. It also has a feedback function that collects user responses and improves the generation method based on that data. This system consists of three entities: a server, a user terminal, and the user.

[0123] server

[0124] The server is the central player in receiving requests, generating surprise elements, and delivering them. Specifically, it has the following functions:

[0125] 1. Generation request reception function

[0126] The server receives a generation request from a user terminal. For example, when a user clicks the "surprise generation button" on a smartphone or PC application, the generation request is sent to the server.

[0127] Technologies used: HTTP requests and responses, RESTful APIs.

[0128] 2. Generation function

[0129] The server generates a prompt sentence based on the generation request and inputs it to a generative AI model, such as GPT-4 (registered trademark).

[0130] For example, the prompt sentence "Generate a GIF that will make my friends laugh" is input into the generative AI model.

[0131] Technologies used: Generative AI models (e.g., GPT-4 by OpenAI®), natural language processing (NLP).

[0132] 3. Distribution function

[0133] The server delivers the generated surprise element to the user terminal, for example, by sending the generated GIF image as an HTTP response.

[0134] Technologies used: HTTP protocol, data serialization (e.g. JSON).

[0135] 4. Response collection function

[0136] The server receives the user's reaction data and stores it in a database. The user enters the reaction data in the application and sends it to the server.

[0137] Technologies used: Database management (e.g., SQL, NoSQL), data analysis tools (e.g., Python pandas, scikit-learn).

[0138] 5. Improved features

[0139] The server analyzes the collected response data and improves the prompts and generation algorithms of the generative AI model, making the content generated more effective in the future.

[0140] Techniques used: Machine learning, data mining, feedback loops.

[0141] User terminal

[0142] The user terminal is the device through which the user accesses the system and experiences the wow factor, and has the following features:

[0143] 1. Generation request sending function

[0144] A function that allows the user to click the "surprise generate button" to send a generation request to the server.

[0145] For example, when you tap a button on a smartphone application, a generation request is sent to the server as an HTTP request.

[0146] 2. Display function

[0147] A function to display or play surprise elements delivered from the server.

[0148] For example, a GIF image received in a video chat application is displayed on the screen.

[0149] 3. Reaction input function

[0150] A function that provides an interface for users to input their responses and sends that data to the server.

[0151] For example, a user enters their thoughts in a reaction field and clicks a send button, whereby the reaction data is sent to the server.

[0152] Specific examples

[0153] For example, when a user uses this system during a video chat with a friend, the specific actions are as follows:

[0154] 1. The user enters a generation request

[0155] The user clicks the "Generate Surprise" button in the video chat app.

[0156] 2. Receive and parse the generation request

[0157] The server receives the generation request and generates the prompt "Generate a GIF that will make my friends laugh."

[0158] 3. Generate surprise elements using generative AI models

[0159] The server calls the GPT-4 API, inputs a prompt, and generates a funny GIF image.

[0160] 4. Deliver the generated surprise element to the device

[0161] The server sends the generated GIF image to the terminal as an HTTP response.

[0162] 5. Display or play the surprise element you received

[0163] The user's device displays the GIF image in a video chat app.

[0164] 6. Collect user feedback

[0165] The user enters a response such as "That's funny!" and the device sends it to the server.

[0166] 7. Improve the generation function based on the collected reaction data

[0167] The server analyzes the response data and improves the next prompt and generation algorithm.

[0168] As described above, this system generates a variety of surprise elements based on user requests, not only providing new enjoyment and surprises to users, but also continually improving based on collected reaction data, thereby enabling the provision of a more effective entertainment experience.

[0169] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0170] Step 1:

[0171] The user enters a generation request

[0172] Input: User clicks the "Generate Surprise Button".

[0173] Specific action: The user taps or clicks a button on an application on their smartphone or computer.

[0174] Data processing: The terminal detects this event and sends a generation request (including the user ID and request content) to the server as an HTTP request.

[0175] Output: A generate request is sent to the server.

[0176] Step 2:

[0177] The server receives and analyzes the request

[0178] Input: The generate request submitted in step 1.

[0179] Specific operation: Receives and analyzes the HTTP request received by the server.

[0180] Data processing: Extract and analyze the data in the generation request (user ID, request content). Generate a prompt sentence such as "Generate a GIF that will make my friends laugh."

[0181] Output: The prompt statement is generated.

[0182] Step 3:

[0183] The server generates surprise elements using generative AI models

[0184] Input: The prompt statement generated in step 2.

[0185] Specific operation: The server calls the API of the generative AI model (e.g., GPT-4) and sends the prompt sentence as input.

[0186] Data processing: The generative AI model performs data calculations based on the prompt text to generate a surprise element (e.g., a funny GIF image).

[0187] Output: Generated wow factor (GIF image).

[0188] Step 4:

[0189] The server delivers the generated surprise element to the device.

[0190] Input: The wow factor (GIF image) generated in step 3.

[0191] Specific operation: The server sends the generated data to the terminal as an HTTP response.

[0192] Data processing: The generated surprise data is serialized and converted into a format that can be sent.

[0193] Output: The surprise element is delivered to the device.

[0194] Step 5:

[0195] The device displays or plays a surprise element

[0196] Input: The surprise element (GIF image) delivered in step 4.

[0197] Specific behavior: The device's video chat application renders the received GIF image and displays it on the screen.

[0198] Data processing: Deserialize the received surprise element data and convert it into a displayable format.

[0199] Output: The wow factor is displayed to the user.

[0200] Step 6:

[0201] Collect user responses and send them to the server

[0202] Input: User reaction to seeing the surprise element.

[0203] Specific operation: The user enters their thoughts and evaluations in the reaction interface within the application and presses the send button.

[0204] Data processing: The device collects the user's reaction data and sends it to the server as an HTTP request.

[0205] Output: The user's reaction data is sent to the server.

[0206] Step 7:

[0207] The server receives and analyzes the reaction data.

[0208] Input: User response data submitted in step 6.

[0209] Specific operation: Receives the HTTP request received by the server and extracts the response data.

[0210] Data processing: Reaction data is stored in a database and analyzed using analytical tools.

[0211] Output: The analysis results are obtained.

[0212] Step 8:

[0213] Server generation improvements

[0214] Input: Analysis results obtained in step 7.

[0215] Specific operation: The server designs new prompt sentence patterns based on the analysis results and adjusts the parameters of the generative AI model.

[0216] Data processing: Change the parameters of the generation algorithm and update the prompt text.

[0217] Output: The improved generation functionality will be reflected in subsequent generation results.

[0218] (Application example 1)

[0219] 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."

[0220] Conventional factory work support systems lack effective means for maintaining worker motivation. Continuing monotonous work and accumulating mental fatigue can lead to a decline in work efficiency and quality, which can have a negative impact on overall productivity. The present invention aims to provide an effective means for improving worker motivation and maintaining and improving work efficiency.

[0221] 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.

[0222] In this invention, the server includes means for accepting a generation request, means for generating a surprise element based on the generation request, means for distributing the generated surprise element to a user terminal, means for collecting user responses, means for analyzing the collected responses and improving the generation means, means for supporting work at a workplace by accepting a refresh request, and means for displaying the surprise element to a worker. Thus, when a refresh request is input during work, a surprise element is generated and distributed, thereby improving the worker's motivation.

[0223] "Means for accepting a creation request" is a general term for interfaces and processes for receiving a creation request from a user or worker.

[0224] The "generation means for generating a surprise element based on a generation request" is software or hardware for generating a surprise element from a received generation request.

[0225] The "distribution means for distributing the generated surprise element to the user terminal" is a means for transmitting the generated surprise element to the user terminal via a network.

[0226] The "means for collecting user responses" is a general term for an interface or process for recording or collecting the responses that users have shown to surprise elements.

[0227] The "improvement means for analyzing collected responses and improving the generation means" is a means for analyzing collected user responses as data and improving the process for generating surprise elements based on the results.

[0228] The "work support means for accepting a refresh request at the work site" refers to an interface or process for transmitting a request to the system when a worker desires a refresh.

[0229] The "display means for displaying the surprise element to the worker" refers to a device or interface for providing the generated surprise element to the worker visually, audibly, or the like.

[0230] This invention provides a system that uses a generative AI model to provide surprises when factory workers want to take a break, thereby improving their motivation. This system is mainly composed of three entities: a server, a terminal, and a user.

[0231] server

[0232] The server plays a central role in the system. Specifically, it accepts generation requests, generates and distributes surprise elements based on those requests, and collects and analyzes user responses to improve the generation process. The server uses the following hardware and software:

[0233] Hardware: High-performance servers (e.g. cloud servers or dedicated servers)

[0234] Software: AI engines (e.g., TENSORFLOW (registered trademark), PyTorch), databases (e.g., MySQL (registered trademark), PostgreSQL), web frameworks (e.g., Flask, Django)

[0235] Terminal

[0236] The terminal is the part that the worker directly interfaces with. It inputs the generation request, inputs the response, and displays the generated surprise element. Specific devices include tablets and PCs with internet connectivity. It has the following functions:

[0237] Generation request sending function: When a worker inputs a refresh request, it is sent to the server.

[0238] Display function: The generated surprise elements are presented to workers visually, audibly, etc.

[0239] Reaction input function: Inputs the reactions of workers and sends the data to the server.

[0240] User

[0241] Users are primarily factory workers. When they want to refresh themselves while working, they access the system through their terminals. When a user inputs a refresh request, the data is sent to the server, and an AI engine is used to generate a surprise element. The generated surprise element is then delivered to the user's terminal, where the user can experience it and input their reaction.

[0242] Specific examples

[0243] For example, when a worker says, "I want to refresh myself," the device sends a generation request to the server. The server uses a generative AI model to generate a surprise element, such as a funny GIF image, an encouraging message, or a short video clip. The generated surprise element is then sent to the worker's device and displayed there. When the worker views the surprise element and enters their thoughts or reactions, the data is sent to the server, where it is collected and analyzed.

[0244] Based on this collected data, the server can improve its generative AI model and generate more effective surprise elements for subsequent refresh requests.

[0245] Prompt Sentence Examples

[0246] An example prompt for a generative AI model might look something like this:

[0247] "Generation request: Please generate a funny video. Example response: A video of a cat flipping."

[0248] "Generation Request: Generate an encouraging message. Example Response: You did a great job today!"

[0249] As described above, this system improves worker motivation and provides a means to increase factory productivity.

[0250] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0251] Step 1:

[0252] Entering and submitting a generation request

[0253] When a user wishes to refresh while working, they input a generation request through the terminal interface. For example, they input "I want to refresh" using voice recognition. When this input is received by the terminal, the generation request data (e.g., a generation request message and user ID) is sent to the server.

[0254] Input: User refresh request (e.g. voice input)

[0255] Output: Creation request data (e.g., creation request message and user ID)

[0256] Step 2:

[0257] Accepting and parsing creation requests

[0258] The server receives and analyzes the generation request data. This analysis includes converting the data into a format that matches the prompt of the generative AI model. Specifically, the server analyzes the received generation request message and determines the type of surprise element (e.g., a funny image, an encouraging message, etc.).

[0259] Input: Creation request data (e.g., creation request message and user ID)

[0260] Output: Analysis results (e.g., type of surprise element)

[0261] Step 3:

[0262] Creating an element of surprise

[0263] The server uses the generative AI model to generate surprise elements based on the analysis results. This is the process of inputting a prompt statement into the generative AI model and generating the corresponding surprise element. For example, video data generated based on the prompt statement "Please generate an interesting video" is output.

[0264] Input: Analysis result (e.g., type of surprise element)

[0265] Output: Generated surprise elements (e.g. video data, image data, messages, etc.)

[0266] Step 4:

[0267] Delivering surprise elements

[0268] The server distributes the generated surprise element to the terminal. The distribution means transmits the generated data to the terminal via the network. The terminal receives the surprise element and displays it in an appropriate format (e.g., display on the screen, play as audio).

[0269] Input: Generated surprise elements (e.g., video data, image data, messages, etc.)

[0270] Output: Device that receives and displays the surprise element

[0271] Step 5:

[0272] Collecting user responses

[0273] The user reacts to the displayed surprise element. The user inputs their reaction using the device's reaction input function (e.g., text input, impression input, evaluation input). The input reaction data is sent from the device to the server.

[0274] Input: User response (e.g., impressions and ratings)

[0275] Output: Response data (e.g., text data, evaluation data)

[0276] Step 6:

[0277] Analysis and storage of reaction data

[0278] The server analyzes the received reaction data and stores it in a database. This analysis includes categorizing reactions as positive or negative and analyzing specific impressions. The analysis results are used to improve the generative AI model in the future.

[0279] Input: Reaction data (e.g., text data, evaluation data)

[0280] Output: Analysis results, saved data

[0281] Step 7:

[0282] Improving generative AI models

[0283] The server uses the analysis results to improve the generative AI model, which includes retraining the model using machine learning algorithms and incorporating new data, allowing it to deliver a more effective wow factor for the next generation request.

[0284] Input: Analysis results, saved data

[0285] Output: An improved generative AI model

[0286] Through each of the above steps, this system can provide factory workers with a refreshing element and improve their motivation to work.

[0287] 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.

[0288] The present invention relates to a system that receives a generation request, generates surprise elements, delivers them to user terminals, collects user reactions, and improves the generation method based on the data. This system further combines an emotion engine to recognize user emotions and generate surprise elements with high accuracy.

[0289] System configuration

[0290] This system consists of three main components: a server, a terminal, and a user. In addition, an emotion engine analyzes the user's emotions and provides feedback to the generator.

[0291] server

[0292] The server is the central component of the system and includes the following functions:

[0293] 1. Generation request reception function: A function to accept generation requests from terminals.

[0294] 2. Generation function: A function that generates surprise elements based on generation requests. It uses an AI engine to generate surprise elements in various formats, including audio, images, videos, and text.

[0295] 3. Distribution function: The function to send the generated surprise element to the terminal.

[0296] 4. Reaction collection function: A function for receiving user reaction data.

[0297] 5. Improvement function: A function to analyze collected reaction data and improve the generation function.

[0298] 6. Emotion analysis function: A function that analyzes collected user voice tone, facial expressions, and text input to recognize the user's emotions.

[0299] Terminal

[0300] The terminal is the device through which the user accesses the system and experiences the wow factor. The terminal's role is to:

[0301] 1. Generation request sending function: An interface for users to input generation requests.

[0302] 2. Display function: A function to display or play the surprise elements delivered from the server.

[0303] 3. Reaction input function: An interface for inputting user reactions.

[0304] System Operation

[0305] The system of the present invention operates as follows.

[0306] 1. The user enters a generation request

[0307] User: Click the "Generate Surprise" button on the device.

[0308] Terminal: Detects a click event, generates generation request data, and sends it to the server.

[0309] 2. Receive the generation request and generate the wow factor

[0310] Server: Receives the generation request and analyzes its contents.

[0311] Server: Using the generation function, generate surprise elements (e.g., interesting images, audio, video, text) based on the AI ​​engine.

[0312] 3. Deliver surprise elements to devices

[0313] Server: Temporarily stores the generated surprise elements, formats them as data, and sends them to the device.

[0314] Terminal: Display or play the received surprise element in an appropriate format.

[0315] 4. Collect user responses

[0316] User: Experience the surprise element and enter their thoughts and ratings through the reaction interface.

[0317] Terminal: Collects user reaction data and sends it to the server.

[0318] 5. Improve based on collected response data

[0319] Server: Receives collected reaction data and stores it for analysis.

[0320] Server: Uses emotion analysis to recognize emotions based on the user's tone of voice, facial expressions, and text input.

[0321] Server: The emotion data recognized by the emotion engine is fed back to the generation means and reflected in future generation. This generates more accurate surprise elements.

[0322] Specific examples

[0323] For example, when using this system during a meeting, it works as follows.

[0324] 1. The user enters a generation request

[0325] User: Click the "Generate Surprise Button" during a meeting.

[0326] 2. Receive the generation request and generate the wow factor

[0327] Server: Receives the generation request and generates an interesting GIF image using the generation function.

[0328] 3. Deliver surprise elements to devices

[0329] Server: Sends the generated GIF image to the device.

[0330] Terminal: Display GIF images on the presentation screen in a meeting.

[0331] 4. Collect user responses

[0332] User: The whole meeting is laughing.

[0333] Terminal: Enter your reaction (e.g., "interesting" or "surprised") through the reaction interface.

[0334] Terminal: Sends collected reaction data to the server.

[0335] 5. Improve based on collected response data

[0336] Server: Receives reaction data and stores it for analysis.

[0337] Server: Uses emotion analysis to analyze the user's tone of voice, facial expressions, and text input to recognize emotions.

[0338] Server: Recognized emotion data is fed back to the generation means, and adjustments are made to maximize the effect of laughter the next time it is generated.

[0339] As described above, the system of the present invention uses an emotion engine to improve the accuracy of the surprise element experienced by the user and to continuously improve it, thereby providing the user with a deeper sense of satisfaction and surprise.

[0340] The processing flow will be explained below.

[0341] Step 1:

[0342] User: Click the "Generate Surprise" button on the device.

[0343] Step 2:

[0344] Terminal: Detects a click event and generates generation request data (e.g., user ID, current context information, parameters for generation, etc.).

[0345] Step 3:

[0346] Terminal: Sends the generation request data to the server.

[0347] Step 4:

[0348] Server: Receives the generation request data sent from the terminal.

[0349] Step 5:

[0350] Server: Analyzes the generation request data and determines what type of surprise element (e.g., audio, image, video, text, etc.) to generate.

[0351] Step 6:

[0352] Server: Calls the generation means and generates surprise elements based on the specified parameters. At this time, an AI engine is used to generate optimal surprise elements based on the user's past reaction data and generation request data.

[0353] Step 7:

[0354] Server: Temporarily stores the generated surprise elements and formats them for delivery to the device.

[0355] Step 8:

[0356] Server: Delivers the prepared surprise elements to the device.

[0357] Step 9:

[0358] Terminal: Receives the surprise element received from the server and displays or plays it in the specified format (e.g., displays an image on the screen, plays a sound).

[0359] Step 10:

[0360] User: Experience the surprise element and enter their thoughts and ratings through the reaction interface.

[0361] Step 11:

[0362] Terminal: Collects user reaction data and sends it to the server.

[0363] Step 12:

[0364] Server: Receives collected user reaction data.

[0365] Step 13:

[0366] Server: Using emotion analysis capabilities, the server analyzes the user's tone of voice, facial expressions, and text input to recognize the user's emotions.

[0367] Step 14:

[0368] Server: Recognized emotion data is fed back to the algorithms and parameters of the generation method, and improvements are made to generate better surprise elements.

[0369] Example 2

[0370] 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."

[0371] Conventional content generation systems lack the ability to accurately recognize user emotions and reactions and improve the generated content based on them. This has led to issues such as low user satisfaction and limited system effectiveness. Furthermore, it is difficult to analyze complex user emotions in real time, so a method to improve the quality of generated content is needed.

[0372] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0373] In this invention, the server includes means for accepting a generation request, means for generating a surprise element based on the generation request, means for distributing the generated surprise element to a user terminal, means for collecting user responses, means for analyzing the collected responses and improving the generation means, means for analyzing emotions that recognize the user's emotions, and means for feeding back the results of the emotion analysis to the generation means. This makes it possible to accurately analyze user emotions and improve the quality of the generated content based on the analysis.

[0374] The "means for accepting a generation request" is a device or program having the function of receiving and analyzing a request for content generation from a user.

[0375] A "generation means for generating a surprise element based on a generation request" is a device or program for generating content (e.g., audio, images, video, text) to surprise a user based on a received generation request.

[0376] The "distribution means for distributing the generated surprise element to the user terminal" is a device or program for transmitting the generated content to the user's device so that the user can experience it.

[0377] The "collection means for collecting user responses" is a device or program for collecting responses (e.g., impressions, evaluations, reactions) made by users to generated content.

[0378] The "improvement means for analyzing collected responses and improving the generation means" is a device or program for analyzing collected user response data and improving the algorithm or model of the generation means based on the analysis results.

[0379] The "emotion analysis means for recognizing user emotions" is a device or program for analyzing and identifying emotions from the user's tone of voice, facial expressions, text input, and the like.

[0380] The "feedback means for feeding back the result of emotion analysis to the generation means" is a device or program for providing the generation means with the user's emotion data recognized by the emotion analysis means and reflecting it in the generated content.

[0381] System Overview

[0382] The present invention is a system that receives generation requests from users, generates surprise elements, delivers them to user terminals, and collects and analyzes their reactions to improve the generation method. This system includes an emotion analysis function, making it possible to generate surprise elements with higher accuracy, thereby increasing the satisfaction of the user experience.

[0383] Hardware and software configuration

[0384] The main components of the system are:

[0385] Server: A central processing unit with the following functions:

[0386] Creation request reception function: Accepts creation requests.

[0387] Generation function: Generates the wow factor based on the generation request.

[0388] Distribution function: The generated surprise element is distributed to the device.

[0389] Reaction collection function: Collects user reaction data.

[0390] Improvement function: Analyze collected reaction data and improve the generation method.

[0391] Sentiment analysis function: Analyzes user emotions.

[0392] Feedback function: The results of sentiment analysis are fed back to the generation means.

[0393] Terminal: A device used by a user, with the following functions:

[0394] Generation request sending function: Sends a generation request.

[0395] Display function: Display or play the generated surprise element.

[0396] Reaction input function: Input reaction data and send it to the server.

[0397] Software used

[0398] Generative AI Models: Use advanced generative AI models such as OpenAI GPT-4 to generate various forms of surprise based on prompts.

[0399] Sentiment analysis engine: Software for analyzing a user's tone of voice, facial expressions, and text input. Some are offered as API services (e.g., EmotionAPI).

[0400] Example of operation process

[0401] Let's walk through the following scenario:

[0402] Use during meetings

[0403] 1. Enter the generation request

[0404] User: Click the "Generate Surprise" button during the meeting and enter a generation request. For example, enter a prompt such as "Generate a prank image of a cat."

[0405] 2. Sending a generation request

[0406] Terminal: Generates the generation request data and sends it to the server.

[0407] 3. Receiving and parsing the generation request

[0408] Server: Receives the generated request data and parses the prompt statement.

[0409] 4. Creating surprise

[0410] Server: Uses a generative AI model such as OpenAI GPT-4 to generate a surprise element (e.g., a funny cat GIF) based on the prompt.

[0411] 5. Deliver surprise elements

[0412] Server: Temporarily stores the generated surprise elements, formats them as data, and sends them to the device.

[0413] Terminal: The received surprise element is displayed on the presentation screen during the meeting.

[0414] 6. Collecting User Responses

[0415] User: Participants react by laughing out loud.

[0416] Terminal: Collects reaction data through reaction interfaces (e.g., reaction buttons and text fields) and sends them to the server.

[0417] 7. Analysis and Improvement of Reaction Data

[0418] Server: Analyzes the reaction data and recognizes the user's emotions using an emotion analysis engine.

[0419] Server: The recognized emotion data is fed back to the generation means and reflected in future generation. This makes it possible to generate more accurate surprise elements in the future.

[0420] Conclusion

[0421] By combining a generative AI model with an emotion analysis engine, this system can accurately analyze users' emotions and reactions and provide high-quality content based on that, significantly improving the satisfaction of the user experience.

[0422] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0423] Specific processing steps of the program

[0424] Step 1: Enter the generation request

[0425] User: Enters a generation request through the terminal interface. The user clicks a specific button (e.g., "Generate a Surprise" button) or enters a prompt statement in text. An example of input is the prompt statement "Generate a prank image of a cat."

[0426] Input: User actions (clicks and text input)

[0427] Output: Generate request data is generated

[0428] Specific operation: During a meeting, the user clicks the "Surprising Generate Button" to request a refresh.

[0429] Step 2: Submit a Generate Request

[0430] Terminal: Generates the generation request data and sends it to the server.

[0431] Input: Generation request data (including prompt statement)

[0432] Output: Generated request data sent to the server as an HTTP request

[0433] Specific operation: The terminal packets the generation request as an HTTP request and sends it to the server's generation request receiving endpoint.

[0434] Step 3: Receiving and parsing the generation request

[0435] Server: Receives the generation request data and analyzes its contents. It references the prompt text and the user's past response data.

[0436] Input: Generation request data

[0437] Output: Data formatted to be input to the AI ​​model

[0438] Specific operation: The server receives the HTTP request, analyzes the generation request, and formats it into data to input into the AI ​​model.

[0439] Step 4: Generate surprise

[0440] Server: Generates surprise elements using a generative AI model (e.g., OpenAI GPT-4) based on the analysis results. For example, generate a funny cat GIF image based on the prompt text.

[0441] Input: Data formatted for the AI ​​model (including prompts)

[0442] Output: Generated surprise element (GIF image, audio, text, etc.)

[0443] Specific operation: The server inputs a prompt sentence into the generative AI model, retrieves the generated content from the model, and temporarily stores it.

[0444] Step 5: Deliver the surprise element

[0445] Server: Formats the generated surprise elements appropriately and sends them to the device.

[0446] Terminal: Display or play the received surprise element.

[0447] Input: Generated wow factor

[0448] Output: Data sent to the device as an HTTP response

[0449] Specific operation: The server sends the generated surprise element to the device as an HTTP response. The device receives the data and displays it on the presentation screen at the conference.

[0450] Step 6: Gathering user responses

[0451] User: Experience the surprise element and enter their thoughts and ratings through the reaction interface.

[0452] Terminal: Collects user reaction data and sends it to the server.

[0453] Input: User response (text impressions, rating button clicks, etc.)

[0454] Output: Reaction data is generated and sent to the server

[0455] Specific operation: The user clicks the reaction button or enters their thoughts in the text field. The device collects the data and sends it to the server.

[0456] Step 7: Analyze and refine reaction data

[0457] Server: Receives the response data and uses an emotion analysis engine to analyze voice tone, facial expressions, and text input.

[0458] Server: Improve the generation method based on the analysis results and reflect them in subsequent generations.

[0459] Input: Reaction data

[0460] Output: Feedback on improving the generator

[0461] Specific operation: The server runs the data analysis engine and performs statistical analysis on the collected reaction data. Based on the analysis results, the parameters of the generative model are adjusted and reflected in the next generation of surprise elements.

[0462] Through these steps, the system generates surprise elements in response to user requests and can continuously improve the generation method based on user responses.

[0463] (Application example 2)

[0464] 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."

[0465] In modern manufacturing, improving employee efficiency and motivation is an important issue. In particular, monotonous work and long working hours can increase employee fatigue and stress, negatively impacting productivity. Conventional methods have made it difficult to properly understand employee emotions and reactions and make continuous improvements that are not disposable.

[0466] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0467] In this invention, the server includes means for receiving a generation request, means for generating a surprise element based on the generation request, means for distributing the generated surprise element to a terminal, means for collecting user responses, means for analyzing the collected responses and improving the generation means, and means for analyzing user emotions. This not only makes it possible to generate and provide surprise elements that reduce employee stress and increase motivation, but also to continuously improve the generation algorithm based on the collected data.

[0468] A "generation request" is a request that a user sends to a server to generate a particular wow factor.

[0469] A "generator" is a system or algorithm for generating a wow factor based on a generation request.

[0470] The "distribution means" refers to a function or method for transmitting the generated surprise element to the user terminal.

[0471] "Collection means" refers to the functions and technologies used to obtain user responses and store them as data.

[0472] An "improvement means" is a system or algorithm that analyzes collected reaction data and improves the performance of the generation means based on the results.

[0473] "Emotion analysis means" refers to technology or a system that analyzes a user's voice tone, facial expression, and text data to recognize emotions.

[0474] A "terminal" is a device that a user uses to access the system and receive generated surprise elements.

[0475] The "surprise element" is content such as audio, images, video, text, and mini-games that are generated to provide surprise and enjoyment to the user.

[0476] "Reaction" refers to the emotions and reactions that users show after experiencing a surprise element.

[0477] "Imaging means" refers to the camera or sensor used to capture the user's facial expressions and movements.

[0478] This invention relates to a system that generates and distributes surprise elements based on user requests, collects and analyzes user responses, and continuously improves the generation method based on the collected responses. This system is primarily composed of three main components: a server, a terminal, and a user. Furthermore, it uses an emotion analysis method to analyze user emotions and generate highly accurate surprise elements.

[0479] System configuration

[0480] server

[0481] Generation request receiving means: receives a generation request from a user. For example, when a user sends a generation request manually or by voice input, the request is received.

[0482] Generation method: Generate surprise elements based on generation requests. Using a generative AI model, surprise elements such as audio, images, videos, text, or mini-games are generated randomly or based on a specific algorithm.

[0483] Delivery means: The generated surprise element is sent to the user's device. The data is delivered in an appropriate format so that the user's device can display or play the surprise element in real time.

[0484] Collection method: Collect user reactions. A webcam and microphone are used to collect the user's facial expressions and voice tone in real time.

[0485] Improvement measures: Analyze the collected reaction data and improve the generation algorithm. For example, based on the collected smiley face data, adjust the next generation so that it will elicit more smiles.

[0486] Sentiment analysis methods: Techniques and software for identifying user emotions from collected data. Examples include facial expression analysis using OpenCV and text sentiment analysis using TextBlob.

[0487] Terminal

[0488] The terminal is the device that the user uses to access the system and receive the generated surprise element. The main functions of the terminal are as follows:

[0489] Generation request sending function: Provides an interface for users to input generation requests. For example, this can be achieved through a smartphone application or voice recognition function.

[0490] Display function: Displays or plays surprise elements distributed from the server. Audio messages are played from the device's speaker, and images and videos are displayed on the screen.

[0491] Reaction input function: An interface for collecting user reactions. The camera and microphone are used to record the user's reactions and send the data to the server.

[0492] Specific examples

[0493] For example, when a worker clicks the "Generate Surprise Button" during a break at the factory, the following occurs:

[0494] User: The worker taps the "surprise generation button" on their smartphone.

[0495] Server: Receives generation requests and generates fun GIFs and mini-games using generative AI models.

[0496] Terminal: The generated surprise element is delivered to the worker's smartphone and displayed on the screen.

[0497] User: The worker looks at it and laughs, and the camera captures the smile.

[0498] Server: Analyzes the collected smile data and improves the generation algorithm.

[0499] Prompt Sentence Examples

[0500] The prompt sentence used for the generative AI model is in the following format:

[0501] "Generate funny GIFs that will make your employees laugh. The content should be humorous and perfect for a break from work."

[0502] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0503] Step 1:

[0504] The user enters a generation request

[0505] The user taps the "surprise generation button" on the device and inputs a generation request.

[0506] Input: User taps

[0507] Output: Generated request data

[0508] Specific operation: The terminal detects a tap event, generates generation request data, and sends it to the server.

[0509] Step 2:

[0510] Receives a generation request and generates the wow factor

[0511] The server receives the generation request, parses it, and generates the wow factor.

[0512] Input: Generation request data

[0513] Output: Surprise element (audio, image, video, text, mini-game)

[0514] Specific operation: Input a prompt into the generative AI model, and generate surprise elements based on the prompt, such as creating funny GIF images or mini-games.

[0515] Step 3:

[0516] Delivering surprise to your device

[0517] The generated surprise element is sent to the user's terminal.

[0518] Input: Generated wow factor

[0519] Output: The wow factor that is played or displayed on the device

[0520] Specific operation: The server converts the generated surprise element into an appropriate format and sends it to the device. The device displays or plays the received data to the user.

[0521] Step 4:

[0522] Collect user responses

[0523] Users experience the surprise element and their reactions are collected.

[0524] Input: User's reaction (facial expression, voice)

[0525] Output: Reaction data

[0526] Specific operation: The device uses a camera and microphone to collect data on the user's facial expressions and voice, and sends it to the server.

[0527] Step 5:

[0528] Improve based on collected reaction data

[0529] The server analyzes the collected reaction data and improves the generation algorithm.

[0530] Input: Reaction data

[0531] Output: Improved generation algorithm

[0532] Specific operation: The server analyzes the reaction data and recognizes the user's emotions using the emotion analysis means. The recognized emotion data is fed back to the generation means and reflected in the next surprise element generation.

[0533] 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.

[0534] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0535] 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.

[0536] [Second embodiment]

[0537] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0538] 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.

[0539] 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).

[0540] 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.

[0541] 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.

[0542] 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).

[0543] 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.

[0544] 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.

[0545] 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.

[0546] 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.

[0547] 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.

[0548] 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."

[0549] The present invention relates to a system that accepts a generation request, generates a surprise element, and delivers it to a user terminal. It also has a feedback function that collects user reactions and improves the generation means based on that data. A detailed description of an embodiment of this system is provided below.

[0550] System configuration

[0551] This system is broadly composed of three components: the server, the terminal, and the user.

[0552] server

[0553] The server is the central component that receives production requests, generates the wow factor, and distributes it. Specifically, it has the following functions:

[0554] 1. Generation request reception function: A function to accept generation requests from terminals.

[0555] 2. Generation function: A function that generates surprise elements based on generation requests. Using an AI engine, surprise elements are generated in various formats, including audio, images, videos, and text.

[0556] 3. Distribution function: The function to send the generated surprise element to the terminal.

[0557] 4. Reaction collection function: A function for receiving user reaction data.

[0558] 5. Improvement function: A function to analyze collected reaction data and improve the generation function.

[0559] Terminal

[0560] The terminal is the device through which the user accesses the system and experiences the wow factor. The terminal has the following functions:

[0561] 1. Generation request sending function: An interface for users to input generation requests. A function to send generation requests to the server.

[0562] 2. Display function: A function to display or play the surprise elements delivered from the server.

[0563] 3. Reaction input function: An interface for inputting user reactions. A function for sending reaction data to the server.

[0564] System Operation

[0565] The system of the present invention operates as follows.

[0566] 1. The user enters a generation request

[0567] User: Click the "Generate Surprise" button on the device.

[0568] Terminal: Detects the click event and sends a generation request to the server.

[0569] 2. Receive the generation request and generate the wow factor

[0570] Server: Receives the generation request and analyzes its contents.

[0571] Server: Uses the generation function to instruct the AI ​​engine to generate surprising elements (e.g., interesting images, audio, video, text).

[0572] 3. Deliver surprise elements to devices

[0573] Server: Sends the generated surprise element to the device.

[0574] Terminal: Display or play the received surprise element in an appropriate format.

[0575] 4. Collect user responses

[0576] User: Experience the surprise element and enter their thoughts and ratings through the reaction interface.

[0577] Terminal: Sends user reaction data to the server.

[0578] 5. Improve based on collected response data

[0579] Server: Receives reaction data and stores it for analysis.

[0580] Server: Use the collected data to improve the generation function and reflect it in the next surprise element generation.

[0581] Specific examples

[0582] For example, if you use this system while video chatting with a friend, it works as follows:

[0583] 1. The user enters a generation request

[0584] User: Click the "Generate Surprise Button" during a video chat.

[0585] 2. Receive the generation request and generate the wow factor

[0586] Server: Receives the generation request and generates an interesting GIF image using the generation function.

[0587] 3. Deliver surprise elements to devices

[0588] Server: Sends the generated GIF image to the device.

[0589] Device: Display GIF images in video chat apps.

[0590] 4. Collect user responses

[0591] User: Enters reactions through the reaction interface, such as surprise or laughter.

[0592] Device: Sends reaction data to the server.

[0593] 5. Improve based on collected response data

[0594] Server: Receives reaction data and stores it for analysis.

[0595] Server: Improve the generation function based on the data and use it for the next generation.

[0596] As described above, the system of the present invention not only generates a variety of surprise elements based on generation requests, providing users with new enjoyment and surprises, but also provides a more effective entertainment experience by continuously improving the system based on collected reaction data.

[0597] The processing flow will be explained below.

[0598] Step 1:

[0599] User: Click the "Generate Surprise" button on the device.

[0600] Step 2:

[0601] Terminal: Detects a click event and generates generation request data (e.g., user ID, current context information, parameters for generation, etc.).

[0602] Step 3:

[0603] Terminal: Sends the generation request data to the server.

[0604] Step 4:

[0605] Server: Receives the generation request data sent from the terminal.

[0606] Step 5:

[0607] Server: Analyzes the generation request data and determines what type of surprise element (e.g., audio, image, video, text, etc.) to generate.

[0608] Step 6:

[0609] Server: Calls the generation means and generates surprise elements based on the specified parameters. At this time, an AI engine is used to generate optimal surprise elements based on the user's past reaction data and generation request data.

[0610] Step 7:

[0611] Server: Temporarily stores the generated surprise elements and formats them for delivery to the device.

[0612] Step 8:

[0613] Server: Delivers the prepared surprise elements to the device.

[0614] Step 9:

[0615] Terminal: Receives the surprise element received from the server and displays or plays it in the specified format (e.g., displays an image on the screen, plays a sound).

[0616] Step 10:

[0617] User: Experience the surprise element and enter their thoughts and ratings through the reaction interface.

[0618] Step 11:

[0619] Terminal: Collects user reaction data and sends it to the server.

[0620] Step 12:

[0621] Server: Receives collected user response data and stores it in a database for analysis.

[0622] Step 13:

[0623] Server: Based on the response data, the algorithms and parameters of the generation method are adjusted, and improvements are made to create a better element of surprise for the next generation request.

[0624] Example 1

[0625] 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."

[0626] In conventional systems, the generation of elements to surprise and entertain users is monotonous, and the generation process is rarely improved based on individual user responses. Therefore, it is difficult to maintain user interest.

[0627] 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.

[0628] In this invention, the server includes means for receiving a generation request, means for generating a surprise element using a generative AI model based on the generation request, means for distributing the generated surprise element to a user terminal, means for collecting user responses, and means for analyzing the collected responses and improving the generation means. This makes it possible to provide individual surprise elements to users and improve the content of subsequent generations based on the responses.

[0629] A "generation request" is an action or content of a user requesting the system to generate a surprise element.

[0630] A "generative AI model" is an artificial intelligence engine that uses artificial intelligence technology to generate audio, images, videos, text, etc. based on input prompts.

[0631] A "prompt" is a sentence or text that gives specific instructions to the generative AI model on what to generate.

[0632] A "surprise element" is digital content such as audio, images, video, and text that is created to surprise and entertain users.

[0633] The "distribution means" is a function or process for transmitting the generated surprise element to the user terminal.

[0634] The "collection means" is a function or process for collecting user reaction data.

[0635] "Improvement means" refers to the function or process for analyzing collected response data and improving generative AI models or generative algorithms.

[0636] A "user terminal" is a device through which a user accesses the system and experiences the generated surprise elements.

[0637] This invention relates to a system that accepts generation requests, generates surprise elements, and delivers them to user terminals. It also has a feedback function that collects user responses and improves the generation method based on that data. This system consists of three entities: a server, a user terminal, and the user.

[0638] server

[0639] The server is the central player in receiving requests, generating surprise elements, and delivering them. Specifically, it has the following functions:

[0640] 1. Generation request reception function

[0641] The server receives a generation request from a user terminal. For example, when a user clicks the "surprise generation button" on a smartphone or PC application, the generation request is sent to the server.

[0642] Technologies used: HTTP requests and responses, RESTful APIs.

[0643] 2. Generation function

[0644] The server generates a prompt sentence based on the generation request and inputs it into the generative AI model, such as GPT-4.

[0645] For example, the prompt sentence "Generate a GIF that will make my friends laugh" is input into the generative AI model.

[0646] Technologies used: Generative AI models (e.g., OpenAI's GPT-4), natural language processing (NLP).

[0647] 3. Distribution function

[0648] The server delivers the generated surprise element to the user terminal, for example, by sending the generated GIF image as an HTTP response.

[0649] Technologies used: HTTP protocol, data serialization (e.g. JSON).

[0650] 4. Response collection function

[0651] The server receives the user's reaction data and stores it in a database. The user enters the reaction data in the application and sends it to the server.

[0652] Technologies used: Database management (e.g., SQL, NoSQL), data analysis tools (e.g., Python pandas, scikit-learn).

[0653] 5. Improved features

[0654] The server analyzes the collected response data and improves the prompts and generation algorithms of the generative AI model, making the content generated more effective in the future.

[0655] Techniques used: Machine learning, data mining, feedback loops.

[0656] User terminal

[0657] The user terminal is the device through which the user accesses the system and experiences the wow factor, and has the following features:

[0658] 1. Generation request sending function

[0659] A function that allows the user to click the "surprise generate button" to send a generation request to the server.

[0660] For example, when you tap a button on a smartphone application, a generation request is sent to the server as an HTTP request.

[0661] 2. Display function

[0662] A function to display or play surprise elements delivered from the server.

[0663] For example, a GIF image received in a video chat application is displayed on the screen.

[0664] 3. Reaction input function

[0665] A function that provides an interface for users to input their responses and sends that data to the server.

[0666] For example, a user enters their thoughts in a reaction field and clicks a send button, whereby the reaction data is sent to the server.

[0667] Specific examples

[0668] For example, when a user uses this system during a video chat with a friend, the specific actions are as follows:

[0669] 1. The user enters a generation request

[0670] The user clicks the "Generate Surprise" button in the video chat app.

[0671] 2. Receive and parse the generation request

[0672] The server receives the generation request and generates the prompt "Generate a GIF that will make my friends laugh."

[0673] 3. Generate surprise elements using generative AI models

[0674] The server calls the GPT-4 API, inputs a prompt, and generates a funny GIF image.

[0675] 4. Deliver the generated surprise element to the device

[0676] The server sends the generated GIF image to the terminal as an HTTP response.

[0677] 5. Display or play the surprise element you received

[0678] The user's device displays the GIF image in a video chat app.

[0679] 6. Collect user feedback

[0680] The user enters a response such as "That's funny!" and the device sends it to the server.

[0681] 7. Improve the generation function based on the collected reaction data

[0682] The server analyzes the response data and improves the next prompt and generation algorithm.

[0683] As described above, this system generates a variety of surprise elements based on user requests, not only providing new enjoyment and surprises to users, but also continually improving based on collected reaction data, thereby enabling the provision of a more effective entertainment experience.

[0684] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0685] Step 1:

[0686] The user enters a generation request

[0687] Input: User clicks the "Generate Surprise Button".

[0688] Specific action: The user taps or clicks a button on an application on their smartphone or computer.

[0689] Data processing: The terminal detects this event and sends a generation request (including the user ID and request content) to the server as an HTTP request.

[0690] Output: A generate request is sent to the server.

[0691] Step 2:

[0692] The server receives and analyzes the request

[0693] Input: The generate request submitted in step 1.

[0694] Specific operation: Receives and analyzes the HTTP request received by the server.

[0695] Data processing: Extract and analyze the data in the generation request (user ID, request content). Generate a prompt sentence such as "Generate a GIF that will make my friends laugh."

[0696] Output: The prompt statement is generated.

[0697] Step 3:

[0698] The server generates surprise elements using generative AI models

[0699] Input: The prompt statement generated in step 2.

[0700] Specific operation: The server calls the API of the generative AI model (e.g., GPT-4) and sends the prompt sentence as input.

[0701] Data processing: The generative AI model performs data calculations based on the prompt text to generate a surprise element (e.g., a funny GIF image).

[0702] Output: Generated wow factor (GIF image).

[0703] Step 4:

[0704] The server delivers the generated surprise element to the device.

[0705] Input: The wow factor (GIF image) generated in step 3.

[0706] Specific operation: The server sends the generated data to the terminal as an HTTP response.

[0707] Data processing: The generated surprise data is serialized and converted into a format that can be sent.

[0708] Output: The surprise element is delivered to the device.

[0709] Step 5:

[0710] The device displays or plays a surprise element

[0711] Input: The surprise element (GIF image) delivered in step 4.

[0712] Specific behavior: The device's video chat application renders the received GIF image and displays it on the screen.

[0713] Data processing: Deserialize the received surprise element data and convert it into a displayable format.

[0714] Output: The wow factor is displayed to the user.

[0715] Step 6:

[0716] Collect user responses and send them to the server

[0717] Input: User reaction to seeing the surprise element.

[0718] Specific operation: The user enters their thoughts and evaluations in the reaction interface within the application and presses the send button.

[0719] Data processing: The device collects the user's reaction data and sends it to the server as an HTTP request.

[0720] Output: The user's reaction data is sent to the server.

[0721] Step 7:

[0722] The server receives and analyzes the reaction data.

[0723] Input: User response data submitted in step 6.

[0724] Specific operation: Receives the HTTP request received by the server and extracts the response data.

[0725] Data processing: Reaction data is stored in a database and analyzed using analytical tools.

[0726] Output: The analysis results are obtained.

[0727] Step 8:

[0728] Server generation improvements

[0729] Input: Analysis results obtained in step 7.

[0730] Specific operation: The server designs new prompt sentence patterns based on the analysis results and adjusts the parameters of the generative AI model.

[0731] Data processing: Change the parameters of the generation algorithm and update the prompt text.

[0732] Output: The improved generation functionality will be reflected in subsequent generation results.

[0733] (Application example 1)

[0734] 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."

[0735] Conventional factory work support systems lack effective means for maintaining worker motivation. Continuing monotonous work and accumulating mental fatigue can lead to a decline in work efficiency and quality, which can have a negative impact on overall productivity. The present invention aims to provide an effective means for improving worker motivation and maintaining and improving work efficiency.

[0736] 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.

[0737] In this invention, the server includes means for accepting a generation request, means for generating a surprise element based on the generation request, means for distributing the generated surprise element to a user terminal, means for collecting user responses, means for analyzing the collected responses and improving the generation means, means for supporting work at a workplace by accepting a refresh request, and means for displaying the surprise element to a worker. Thus, when a refresh request is input during work, a surprise element is generated and distributed, thereby improving the worker's motivation.

[0738] "Means for accepting a creation request" is a general term for interfaces and processes for receiving a creation request from a user or worker.

[0739] The "generation means for generating a surprise element based on a generation request" is software or hardware for generating a surprise element from a received generation request.

[0740] The "distribution means for distributing the generated surprise element to the user terminal" is a means for transmitting the generated surprise element to the user terminal via a network.

[0741] The "means for collecting user responses" is a general term for an interface or process for recording or collecting the responses that users have shown to surprise elements.

[0742] The "improvement means for analyzing collected responses and improving the generation means" is a means for analyzing collected user responses as data and improving the process for generating surprise elements based on the results.

[0743] The "work support means for accepting a refresh request at the work site" refers to an interface or process for transmitting a request to the system when a worker desires a refresh.

[0744] The "display means for displaying the surprise element to the worker" refers to a device or interface for providing the generated surprise element to the worker visually, audibly, or the like.

[0745] This invention provides a system that uses a generative AI model to provide surprises when factory workers want to take a break, thereby improving their motivation. This system is mainly composed of three entities: a server, a terminal, and a user.

[0746] server

[0747] The server plays a central role in the system. Specifically, it accepts generation requests, generates and distributes surprise elements based on those requests, and collects and analyzes user responses to improve the generation process. The server uses the following hardware and software:

[0748] Hardware: High-performance servers (e.g. cloud servers or dedicated servers)

[0749] Software: AI engines (e.g., TensorFlow, PyTorch), databases (e.g., MySQL, PostgreSQL), web frameworks (e.g., Flask, Django)

[0750] Terminal

[0751] The terminal is the part that the worker directly interfaces with. It inputs the generation request, inputs the response, and displays the generated surprise element. Specific devices include tablets and PCs with internet connectivity. It has the following functions:

[0752] Generation request sending function: When a worker inputs a refresh request, it is sent to the server.

[0753] Display function: The generated surprise elements are presented to workers visually, audibly, etc.

[0754] Reaction input function: Inputs the reactions of workers and sends the data to the server.

[0755] User

[0756] Users are primarily factory workers. When they want to refresh themselves while working, they access the system through their terminals. When a user inputs a refresh request, the data is sent to the server, and an AI engine is used to generate a surprise element. The generated surprise element is then delivered to the user's terminal, where the user can experience it and input their reaction.

[0757] Specific examples

[0758] For example, when a worker says, "I want to refresh myself," the device sends a generation request to the server. The server uses a generative AI model to generate a surprise element, such as a funny GIF image, an encouraging message, or a short video clip. The generated surprise element is then sent to the worker's device and displayed there. When the worker views the surprise element and enters their thoughts or reactions, the data is sent to the server, where it is collected and analyzed.

[0759] Based on this collected data, the server can improve its generative AI model and generate more effective surprise elements for subsequent refresh requests.

[0760] Prompt Sentence Examples

[0761] An example prompt for a generative AI model might look something like this:

[0762] "Generation request: Please generate a funny video. Example response: A video of a cat flipping."

[0763] "Generation Request: Generate an encouraging message. Example Response: You did a great job today!"

[0764] As described above, this system improves worker motivation and provides a means to increase factory productivity.

[0765] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0766] Step 1:

[0767] Entering and submitting a generation request

[0768] When a user wishes to refresh while working, they input a generation request through the terminal interface. For example, they input "I want to refresh" using voice recognition. When this input is received by the terminal, the generation request data (e.g., a generation request message and user ID) is sent to the server.

[0769] Input: User refresh request (e.g. voice input)

[0770] Output: Creation request data (e.g., creation request message and user ID)

[0771] Step 2:

[0772] Accepting and parsing creation requests

[0773] The server receives and analyzes the generation request data. This analysis includes converting the data into a format that matches the prompt of the generative AI model. Specifically, the server analyzes the received generation request message and determines the type of surprise element (e.g., a funny image, an encouraging message, etc.).

[0774] Input: Creation request data (e.g., creation request message and user ID)

[0775] Output: Analysis results (e.g., type of surprise element)

[0776] Step 3:

[0777] Creating an element of surprise

[0778] The server uses the generative AI model to generate surprise elements based on the analysis results. This is the process of inputting a prompt statement into the generative AI model and generating the corresponding surprise element. For example, video data generated based on the prompt statement "Please generate an interesting video" is output.

[0779] Input: Analysis result (e.g., type of surprise element)

[0780] Output: Generated surprise elements (e.g. video data, image data, messages, etc.)

[0781] Step 4:

[0782] Delivering surprise elements

[0783] The server distributes the generated surprise element to the terminal. The distribution means transmits the generated data to the terminal via the network. The terminal receives the surprise element and displays it in an appropriate format (e.g., display on the screen, play as audio).

[0784] Input: Generated surprise elements (e.g., video data, image data, messages, etc.)

[0785] Output: Device that receives and displays the surprise element

[0786] Step 5:

[0787] Collecting user responses

[0788] The user reacts to the displayed surprise element. The user inputs their reaction using the device's reaction input function (e.g., text input, impression input, evaluation input). The input reaction data is sent from the device to the server.

[0789] Input: User response (e.g., impressions and ratings)

[0790] Output: Response data (e.g., text data, evaluation data)

[0791] Step 6:

[0792] Analysis and storage of reaction data

[0793] The server analyzes the received reaction data and stores it in a database. This analysis includes categorizing reactions as positive or negative and analyzing specific impressions. The analysis results are used to improve the generative AI model in the future.

[0794] Input: Reaction data (e.g., text data, evaluation data)

[0795] Output: Analysis results, saved data

[0796] Step 7:

[0797] Improving generative AI models

[0798] The server uses the analysis results to improve the generative AI model, which includes retraining the model using machine learning algorithms and incorporating new data, allowing it to deliver a more effective wow factor for the next generation request.

[0799] Input: Analysis results, saved data

[0800] Output: An improved generative AI model

[0801] Through each of the above steps, this system can provide factory workers with a refreshing element and improve their motivation to work.

[0802] 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.

[0803] The present invention relates to a system that receives a generation request, generates surprise elements, delivers them to user terminals, collects user reactions, and improves the generation method based on the data. This system further combines an emotion engine to recognize user emotions and generate surprise elements with high accuracy.

[0804] System configuration

[0805] This system consists of three main components: a server, a terminal, and a user. In addition, an emotion engine analyzes the user's emotions and provides feedback to the generator.

[0806] server

[0807] The server is the central component of the system and includes the following functions:

[0808] 1. Generation request reception function: A function to accept generation requests from terminals.

[0809] 2. Generation function: A function that generates surprise elements based on generation requests. It uses an AI engine to generate surprise elements in various formats, including audio, images, videos, and text.

[0810] 3. Distribution function: The function to send the generated surprise element to the terminal.

[0811] 4. Reaction collection function: A function for receiving user reaction data.

[0812] 5. Improvement function: A function to analyze collected reaction data and improve the generation function.

[0813] 6. Emotion analysis function: A function that analyzes collected user voice tone, facial expressions, and text input to recognize the user's emotions.

[0814] Terminal

[0815] The terminal is the device through which the user accesses the system and experiences the wow factor. The terminal's role is to:

[0816] 1. Generation request sending function: An interface for users to input generation requests.

[0817] 2. Display function: A function to display or play the surprise elements delivered from the server.

[0818] 3. Reaction input function: An interface for inputting user reactions.

[0819] System Operation

[0820] The system of the present invention operates as follows.

[0821] 1. The user enters a generation request

[0822] User: Click the "Generate Surprise" button on the device.

[0823] Terminal: Detects a click event, generates generation request data, and sends it to the server.

[0824] 2. Receive the generation request and generate the wow factor

[0825] Server: Receives the generation request and analyzes its contents.

[0826] Server: Using the generation function, generate surprise elements (e.g., interesting images, audio, video, text) based on the AI ​​engine.

[0827] 3. Deliver surprise elements to devices

[0828] Server: Temporarily stores the generated surprise elements, formats them as data, and sends them to the device.

[0829] Terminal: Display or play the received surprise element in an appropriate format.

[0830] 4. Collect user responses

[0831] User: Experience the surprise element and enter their thoughts and ratings through the reaction interface.

[0832] Terminal: Collects user reaction data and sends it to the server.

[0833] 5. Improve based on collected response data

[0834] Server: Receives collected reaction data and stores it for analysis.

[0835] Server: Uses emotion analysis to recognize emotions based on the user's tone of voice, facial expressions, and text input.

[0836] Server: The emotion data recognized by the emotion engine is fed back to the generation means and reflected in future generation. This generates more accurate surprise elements.

[0837] Specific examples

[0838] For example, when using this system during a meeting, it works as follows.

[0839] 1. The user enters a generation request

[0840] User: Click the "Generate Surprise Button" during a meeting.

[0841] 2. Receive the generation request and generate the wow factor

[0842] Server: Receives the generation request and generates an interesting GIF image using the generation function.

[0843] 3. Deliver surprise elements to devices

[0844] Server: Sends the generated GIF image to the device.

[0845] Terminal: Display GIF images on the presentation screen in a meeting.

[0846] 4. Collect user responses

[0847] User: The whole meeting is laughing.

[0848] Terminal: Enter your reaction (e.g., "interesting" or "surprised") through the reaction interface.

[0849] Terminal: Sends collected reaction data to the server.

[0850] 5. Improve based on collected response data

[0851] Server: Receives reaction data and stores it for analysis.

[0852] Server: Uses emotion analysis to analyze the user's tone of voice, facial expressions, and text input to recognize emotions.

[0853] Server: Recognized emotion data is fed back to the generation means, and adjustments are made to maximize the effect of laughter the next time it is generated.

[0854] As described above, the system of the present invention uses an emotion engine to improve the accuracy of the surprise element experienced by the user and to continuously improve it, thereby providing the user with a deeper sense of satisfaction and surprise.

[0855] The processing flow will be explained below.

[0856] Step 1:

[0857] User: Click the "Generate Surprise" button on the device.

[0858] Step 2:

[0859] Terminal: Detects a click event and generates generation request data (e.g., user ID, current context information, parameters for generation, etc.).

[0860] Step 3:

[0861] Terminal: Sends the generation request data to the server.

[0862] Step 4:

[0863] Server: Receives the generation request data sent from the terminal.

[0864] Step 5:

[0865] Server: Analyzes the generation request data and determines what type of surprise element (e.g., audio, image, video, text, etc.) to generate.

[0866] Step 6:

[0867] Server: Calls the generation means and generates surprise elements based on the specified parameters. At this time, an AI engine is used to generate optimal surprise elements based on the user's past reaction data and generation request data.

[0868] Step 7:

[0869] Server: Temporarily stores the generated surprise elements and formats them for delivery to the device.

[0870] Step 8:

[0871] Server: Delivers the prepared surprise elements to the device.

[0872] Step 9:

[0873] Terminal: Receives the surprise element received from the server and displays or plays it in the specified format (e.g., displays an image on the screen, plays a sound).

[0874] Step 10:

[0875] User: Experience the surprise element and enter their thoughts and ratings through the reaction interface.

[0876] Step 11:

[0877] Terminal: Collects user reaction data and sends it to the server.

[0878] Step 12:

[0879] Server: Receives collected user reaction data.

[0880] Step 13:

[0881] Server: Using emotion analysis capabilities, the server analyzes the user's tone of voice, facial expressions, and text input to recognize the user's emotions.

[0882] Step 14:

[0883] Server: Recognized emotion data is fed back to the algorithms and parameters of the generation method, and improvements are made to generate better surprise elements.

[0884] Example 2

[0885] 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."

[0886] Conventional content generation systems lack the ability to accurately recognize user emotions and reactions and improve the generated content based on them. This has led to issues such as low user satisfaction and limited system effectiveness. Furthermore, it is difficult to analyze complex user emotions in real time, so a method to improve the quality of generated content is needed.

[0887] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0888] In this invention, the server includes means for accepting a generation request, means for generating a surprise element based on the generation request, means for distributing the generated surprise element to a user terminal, means for collecting user responses, means for analyzing the collected responses and improving the generation means, means for analyzing emotions that recognize the user's emotions, and means for feeding back the results of the emotion analysis to the generation means. This makes it possible to accurately analyze user emotions and improve the quality of the generated content based on the analysis.

[0889] The "means for accepting a generation request" is a device or program having the function of receiving and analyzing a request for content generation from a user.

[0890] A "generation means for generating a surprise element based on a generation request" is a device or program for generating content (e.g., audio, images, video, text) to surprise a user based on a received generation request.

[0891] The "distribution means for distributing the generated surprise element to the user terminal" is a device or program for transmitting the generated content to the user's device so that the user can experience it.

[0892] The "collection means for collecting user responses" is a device or program for collecting responses (e.g., impressions, evaluations, reactions) made by users to generated content.

[0893] The "improvement means for analyzing collected responses and improving the generation means" is a device or program for analyzing collected user response data and improving the algorithm or model of the generation means based on the analysis results.

[0894] The "emotion analysis means for recognizing user emotions" is a device or program for analyzing and identifying emotions from the user's tone of voice, facial expressions, text input, and the like.

[0895] The "feedback means for feeding back the result of emotion analysis to the generation means" is a device or program for providing the generation means with the user's emotion data recognized by the emotion analysis means and reflecting it in the generated content.

[0896] System Overview

[0897] The present invention is a system that receives generation requests from users, generates surprise elements, delivers them to user terminals, and collects and analyzes their reactions to improve the generation method. This system includes an emotion analysis function, making it possible to generate surprise elements with higher accuracy, thereby increasing the satisfaction of the user experience.

[0898] Hardware and software configuration

[0899] The main components of the system are:

[0900] Server: A central processing unit with the following functions:

[0901] Creation request reception function: Accepts creation requests.

[0902] Generation function: Generates the wow factor based on the generation request.

[0903] Distribution function: The generated surprise element is distributed to the device.

[0904] Reaction collection function: Collects user reaction data.

[0905] Improvement function: Analyze collected reaction data and improve the generation method.

[0906] Sentiment analysis function: Analyzes user emotions.

[0907] Feedback function: The results of sentiment analysis are fed back to the generation means.

[0908] Terminal: A device used by a user, with the following functions:

[0909] Generation request sending function: Sends a generation request.

[0910] Display function: Display or play the generated surprise element.

[0911] Reaction input function: Input reaction data and send it to the server.

[0912] Software used

[0913] Generative AI Models: Use advanced generative AI models such as OpenAI GPT-4 to generate various forms of surprise based on prompts.

[0914] Sentiment analysis engine: Software for analyzing a user's tone of voice, facial expressions, and text input. Some are offered as API services (e.g., EmotionAPI).

[0915] Example of operation process

[0916] Let's walk through the following scenario:

[0917] Use during meetings

[0918] 1. Enter the generation request

[0919] User: Click the "Generate Surprise" button during the meeting and enter a generation request. For example, enter a prompt such as "Generate a prank image of a cat."

[0920] 2. Sending a generation request

[0921] Terminal: Generates the generation request data and sends it to the server.

[0922] 3. Receiving and parsing the generation request

[0923] Server: Receives the generated request data and parses the prompt statement.

[0924] 4. Creating surprise

[0925] Server: Uses a generative AI model such as OpenAI GPT-4 to generate a surprise element (e.g., a funny cat GIF) based on the prompt.

[0926] 5. Deliver surprise elements

[0927] Server: Temporarily stores the generated surprise elements, formats them as data, and sends them to the device.

[0928] Terminal: The received surprise element is displayed on the presentation screen during the meeting.

[0929] 6. Collecting User Responses

[0930] User: Participants react by laughing out loud.

[0931] Terminal: Collects reaction data through reaction interfaces (e.g., reaction buttons and text fields) and sends them to the server.

[0932] 7. Analysis and Improvement of Reaction Data

[0933] Server: Analyzes the reaction data and recognizes the user's emotions using an emotion analysis engine.

[0934] Server: The recognized emotion data is fed back to the generation means and reflected in future generation. This makes it possible to generate more accurate surprise elements in the future.

[0935] Conclusion

[0936] By combining a generative AI model with an emotion analysis engine, this system can accurately analyze users' emotions and reactions and provide high-quality content based on that, significantly improving the satisfaction of the user experience.

[0937] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0938] Specific processing steps of the program

[0939] Step 1: Enter the generation request

[0940] User: Enters a generation request through the terminal interface. The user clicks a specific button (e.g., "Generate a Surprise" button) or enters a prompt statement in text. An example of input is the prompt statement "Generate a prank image of a cat."

[0941] Input: User actions (clicks and text input)

[0942] Output: Generate request data is generated

[0943] Specific operation: During a meeting, the user clicks the "Surprising Generate Button" to request a refresh.

[0944] Step 2: Submit a Generate Request

[0945] Terminal: Generates the generation request data and sends it to the server.

[0946] Input: Generation request data (including prompt statement)

[0947] Output: Generated request data sent to the server as an HTTP request

[0948] Specific operation: The terminal packets the generation request as an HTTP request and sends it to the server's generation request receiving endpoint.

[0949] Step 3: Receiving and parsing the generation request

[0950] Server: Receives the generation request data and analyzes its contents. It references the prompt text and the user's past response data.

[0951] Input: Generation request data

[0952] Output: Data formatted to be input to the AI ​​model

[0953] Specific operation: The server receives the HTTP request, analyzes the generation request, and formats it into data to input into the AI ​​model.

[0954] Step 4: Generate surprise

[0955] Server: Generates surprise elements using a generative AI model (e.g., OpenAI GPT-4) based on the analysis results. For example, generate a funny cat GIF image based on the prompt text.

[0956] Input: Data formatted for the AI ​​model (including prompts)

[0957] Output: Generated surprise element (GIF image, audio, text, etc.)

[0958] Specific operation: The server inputs a prompt sentence into the generative AI model, retrieves the generated content from the model, and temporarily stores it.

[0959] Step 5: Deliver the surprise element

[0960] Server: Formats the generated surprise elements appropriately and sends them to the device.

[0961] Terminal: Display or play the received surprise element.

[0962] Input: Generated wow factor

[0963] Output: Data sent to the device as an HTTP response

[0964] Specific operation: The server sends the generated surprise element to the device as an HTTP response. The device receives the data and displays it on the presentation screen at the conference.

[0965] Step 6: Gathering user responses

[0966] User: Experience the surprise element and enter their thoughts and ratings through the reaction interface.

[0967] Terminal: Collects user reaction data and sends it to the server.

[0968] Input: User response (text impressions, rating button clicks, etc.)

[0969] Output: Reaction data is generated and sent to the server

[0970] Specific operation: The user clicks the reaction button or enters their thoughts in the text field. The device collects the data and sends it to the server.

[0971] Step 7: Analyze and refine reaction data

[0972] Server: Receives the response data and uses an emotion analysis engine to analyze voice tone, facial expressions, and text input.

[0973] Server: Improve the generation method based on the analysis results and reflect them in subsequent generations.

[0974] Input: Reaction data

[0975] Output: Feedback on improving the generator

[0976] Specific operation: The server runs the data analysis engine and performs statistical analysis on the collected reaction data. Based on the analysis results, the parameters of the generative model are adjusted and reflected in the next generation of surprise elements.

[0977] Through these steps, the system generates surprise elements in response to user requests and can continuously improve the generation method based on user responses.

[0978] (Application example 2)

[0979] 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."

[0980] In modern manufacturing, improving employee efficiency and motivation is an important issue. In particular, monotonous work and long working hours can increase employee fatigue and stress, negatively impacting productivity. Conventional methods have made it difficult to properly understand employee emotions and reactions and make continuous improvements that are not disposable.

[0981] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0982] In this invention, the server includes means for receiving a generation request, means for generating a surprise element based on the generation request, means for distributing the generated surprise element to a terminal, means for collecting user responses, means for analyzing the collected responses and improving the generation means, and means for analyzing user emotions. This not only makes it possible to generate and provide surprise elements that reduce employee stress and increase motivation, but also to continuously improve the generation algorithm based on the collected data.

[0983] A "generation request" is a request that a user sends to a server to generate a particular wow factor.

[0984] A "generator" is a system or algorithm for generating a wow factor based on a generation request.

[0985] The "distribution means" refers to a function or method for transmitting the generated surprise element to the user terminal.

[0986] "Collection means" refers to the functions and technologies used to obtain user responses and store them as data.

[0987] An "improvement means" is a system or algorithm that analyzes collected reaction data and improves the performance of the generation means based on the results.

[0988] "Emotion analysis means" refers to technology or a system that analyzes a user's voice tone, facial expression, and text data to recognize emotions.

[0989] A "terminal" is a device that a user uses to access the system and receive generated surprise elements.

[0990] The "surprise element" is content such as audio, images, video, text, and mini-games that are generated to provide surprise and enjoyment to the user.

[0991] "Reaction" refers to the emotions and reactions that users show after experiencing a surprise element.

[0992] "Imaging means" refers to the camera or sensor used to capture the user's facial expressions and movements.

[0993] This invention relates to a system that generates and distributes surprise elements based on user requests, collects and analyzes user responses, and continuously improves the generation method based on the collected responses. This system is primarily composed of three main components: a server, a terminal, and a user. Furthermore, it uses an emotion analysis method to analyze user emotions and generate highly accurate surprise elements.

[0994] System configuration

[0995] server

[0996] Generation request receiving means: receives a generation request from a user. For example, when a user sends a generation request manually or by voice input, the request is received.

[0997] Generation method: Generate surprise elements based on generation requests. Using a generative AI model, surprise elements such as audio, images, videos, text, or mini-games are generated randomly or based on a specific algorithm.

[0998] Delivery means: The generated surprise element is sent to the user's device. The data is delivered in an appropriate format so that the user's device can display or play the surprise element in real time.

[0999] Collection method: Collect user reactions. A webcam and microphone are used to collect the user's facial expressions and voice tone in real time.

[1000] Improvement measures: Analyze the collected reaction data and improve the generation algorithm. For example, based on the collected smiley face data, adjust the next generation so that it will elicit more smiles.

[1001] Sentiment analysis methods: Techniques and software for identifying user emotions from collected data. Examples include facial expression analysis using OpenCV and text sentiment analysis using TextBlob.

[1002] Terminal

[1003] The terminal is the device that the user uses to access the system and receive the generated surprise element. The main functions of the terminal are as follows:

[1004] Generation request sending function: Provides an interface for users to input generation requests. For example, this can be achieved through a smartphone application or voice recognition function.

[1005] Display function: Displays or plays surprise elements distributed from the server. Audio messages are played from the device's speaker, and images and videos are displayed on the screen.

[1006] Reaction input function: An interface for collecting user reactions. The camera and microphone are used to record the user's reactions and send the data to the server.

[1007] Specific examples

[1008] For example, when a worker clicks the "Generate Surprise Button" during a break at the factory, the following occurs:

[1009] User: The worker taps the "surprise generation button" on their smartphone.

[1010] Server: Receives generation requests and generates fun GIFs and mini-games using generative AI models.

[1011] Terminal: The generated surprise element is delivered to the worker's smartphone and displayed on the screen.

[1012] User: The worker looks at it and laughs, and the camera captures the smile.

[1013] Server: Analyzes the collected smile data and improves the generation algorithm.

[1014] Prompt Sentence Examples

[1015] The prompt sentence used for the generative AI model is in the following format:

[1016] "Generate funny GIFs that will make your employees laugh. The content should be humorous and perfect for a break from work."

[1017] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1018] Step 1:

[1019] The user enters a generation request

[1020] The user taps the "surprise generation button" on the device and inputs a generation request.

[1021] Input: User taps

[1022] Output: Generated request data

[1023] Specific operation: The terminal detects a tap event, generates generation request data, and sends it to the server.

[1024] Step 2:

[1025] Receives a generation request and generates the wow factor

[1026] The server receives the generation request, parses it, and generates the wow factor.

[1027] Input: Generation request data

[1028] Output: Surprise element (audio, image, video, text, mini-game)

[1029] Specific operation: Input a prompt into the generative AI model, and generate surprise elements based on the prompt, such as creating funny GIF images or mini-games.

[1030] Step 3:

[1031] Delivering surprise to your device

[1032] The generated surprise element is sent to the user's terminal.

[1033] Input: Generated wow factor

[1034] Output: The wow factor that is played or displayed on the device

[1035] Specific operation: The server converts the generated surprise element into an appropriate format and sends it to the device. The device displays or plays the received data to the user.

[1036] Step 4:

[1037] Collect user responses

[1038] Users experience the surprise element and their reactions are collected.

[1039] Input: User's reaction (facial expression, voice)

[1040] Output: Reaction data

[1041] Specific operation: The device uses a camera and microphone to collect data on the user's facial expressions and voice, and sends it to the server.

[1042] Step 5:

[1043] Improve based on collected reaction data

[1044] The server analyzes the collected reaction data and improves the generation algorithm.

[1045] Input: Reaction data

[1046] Output: Improved generation algorithm

[1047] Specific operation: The server analyzes the reaction data and recognizes the user's emotions using the emotion analysis means. The recognized emotion data is fed back to the generation means and reflected in the next surprise element generation.

[1048] 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.

[1049] 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.

[1050] 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.

[1051] [Third embodiment]

[1052] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1053] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1054] 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).

[1055] 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.

[1056] 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.

[1057] 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).

[1058] 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.

[1059] 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.

[1060] 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.

[1061] 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.

[1062] 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.

[1063] 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."

[1064] The present invention relates to a system that accepts a generation request, generates a surprise element, and delivers it to a user terminal. It also has a feedback function that collects user reactions and improves the generation means based on that data. A detailed description of an embodiment of this system is provided below.

[1065] System configuration

[1066] This system is broadly composed of three components: the server, the terminal, and the user.

[1067] server

[1068] The server is the central component that receives production requests, generates the wow factor, and distributes it. Specifically, it has the following functions:

[1069] 1. Generation request reception function: A function to accept generation requests from terminals.

[1070] 2. Generation function: A function that generates surprise elements based on generation requests. Using an AI engine, surprise elements are generated in various formats, including audio, images, videos, and text.

[1071] 3. Distribution function: The function to send the generated surprise element to the terminal.

[1072] 4. Reaction collection function: A function for receiving user reaction data.

[1073] 5. Improvement function: A function to analyze collected reaction data and improve the generation function.

[1074] Terminal

[1075] The terminal is the device through which the user accesses the system and experiences the wow factor. The terminal has the following functions:

[1076] 1. Generation request sending function: An interface for users to input generation requests. A function to send generation requests to the server.

[1077] 2. Display function: A function to display or play the surprise elements delivered from the server.

[1078] 3. Reaction input function: An interface for inputting user reactions. A function for sending reaction data to the server.

[1079] System Operation

[1080] The system of the present invention operates as follows.

[1081] 1. The user enters a generation request

[1082] User: Click the "Generate Surprise" button on the device.

[1083] Terminal: Detects the click event and sends a generation request to the server.

[1084] 2. Receive the generation request and generate the wow factor

[1085] Server: Receives the generation request and analyzes its contents.

[1086] Server: Uses the generation function to instruct the AI ​​engine to generate surprising elements (e.g., interesting images, audio, video, text).

[1087] 3. Deliver surprise elements to devices

[1088] Server: Sends the generated surprise element to the device.

[1089] Terminal: Display or play the received surprise element in an appropriate format.

[1090] 4. Collect user responses

[1091] User: Experience the surprise element and enter their thoughts and ratings through the reaction interface.

[1092] Terminal: Sends user reaction data to the server.

[1093] 5. Improve based on collected response data

[1094] Server: Receives reaction data and stores it for analysis.

[1095] Server: Use the collected data to improve the generation function and reflect it in the next surprise element generation.

[1096] Specific examples

[1097] For example, if you use this system while video chatting with a friend, it works as follows:

[1098] 1. The user enters a generation request

[1099] User: Click the "Generate Surprise Button" during a video chat.

[1100] 2. Receive the generation request and generate the wow factor

[1101] Server: Receives the generation request and generates an interesting GIF image using the generation function.

[1102] 3. Deliver surprise elements to devices

[1103] Server: Sends the generated GIF image to the device.

[1104] Device: Display GIF images in video chat apps.

[1105] 4. Collect user responses

[1106] User: Enters reactions through the reaction interface, such as surprise or laughter.

[1107] Device: Sends reaction data to the server.

[1108] 5. Improve based on collected response data

[1109] Server: Receives reaction data and stores it for analysis.

[1110] Server: Improve the generation function based on the data and use it for the next generation.

[1111] As described above, the system of the present invention not only generates a variety of surprise elements based on generation requests, providing users with new enjoyment and surprises, but also provides a more effective entertainment experience by continuously improving the system based on collected reaction data.

[1112] The processing flow will be explained below.

[1113] Step 1:

[1114] User: Click the "Generate Surprise" button on the device.

[1115] Step 2:

[1116] Terminal: Detects a click event and generates generation request data (e.g., user ID, current context information, parameters for generation, etc.).

[1117] Step 3:

[1118] Terminal: Sends the generation request data to the server.

[1119] Step 4:

[1120] Server: Receives the generation request data sent from the terminal.

[1121] Step 5:

[1122] Server: Analyzes the generation request data and determines what type of surprise element (e.g., audio, image, video, text, etc.) to generate.

[1123] Step 6:

[1124] Server: Calls the generation means and generates surprise elements based on the specified parameters. At this time, an AI engine is used to generate optimal surprise elements based on the user's past reaction data and generation request data.

[1125] Step 7:

[1126] Server: Temporarily stores the generated surprise elements and formats them for delivery to the device.

[1127] Step 8:

[1128] Server: Delivers the prepared surprise elements to the device.

[1129] Step 9:

[1130] Terminal: Receives the surprise element received from the server and displays or plays it in the specified format (e.g., displays an image on the screen, plays a sound).

[1131] Step 10:

[1132] User: Experience the surprise element and enter their thoughts and ratings through the reaction interface.

[1133] Step 11:

[1134] Terminal: Collects user reaction data and sends it to the server.

[1135] Step 12:

[1136] Server: Receives collected user response data and stores it in a database for analysis.

[1137] Step 13:

[1138] Server: Based on the response data, the algorithms and parameters of the generation method are adjusted, and improvements are made to create a better element of surprise for the next generation request.

[1139] Example 1

[1140] 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."

[1141] In conventional systems, the generation of elements to surprise and entertain users is monotonous, and the generation process is rarely improved based on individual user responses. Therefore, it is difficult to maintain user interest.

[1142] 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.

[1143] In this invention, the server includes means for receiving a generation request, means for generating a surprise element using a generative AI model based on the generation request, means for distributing the generated surprise element to a user terminal, means for collecting user responses, and means for analyzing the collected responses and improving the generation means. This makes it possible to provide individual surprise elements to users and improve the content of subsequent generations based on the responses.

[1144] A "generation request" is an action or content of a user requesting the system to generate a surprise element.

[1145] A "generative AI model" is an artificial intelligence engine that uses artificial intelligence technology to generate audio, images, videos, text, etc. based on input prompts.

[1146] A "prompt" is a sentence or text that gives specific instructions to the generative AI model on what to generate.

[1147] A "surprise element" is digital content such as audio, images, video, and text that is created to surprise and entertain users.

[1148] The "distribution means" is a function or process for transmitting the generated surprise element to the user terminal.

[1149] The "collection means" is a function or process for collecting user reaction data.

[1150] "Improvement means" refers to the function or process for analyzing collected response data and improving generative AI models or generative algorithms.

[1151] A "user terminal" is a device through which a user accesses the system and experiences the generated surprise elements.

[1152] This invention relates to a system that accepts generation requests, generates surprise elements, and delivers them to user terminals. It also has a feedback function that collects user responses and improves the generation method based on that data. This system consists of three entities: a server, a user terminal, and the user.

[1153] server

[1154] The server is the central player in receiving requests, generating surprise elements, and delivering them. Specifically, it has the following functions:

[1155] 1. Generation request reception function

[1156] The server receives a generation request from a user terminal. For example, when a user clicks the "surprise generation button" on a smartphone or PC application, the generation request is sent to the server.

[1157] Technologies used: HTTP requests and responses, RESTful APIs.

[1158] 2. Generation function

[1159] The server generates a prompt sentence based on the generation request and inputs it into the generative AI model, such as GPT-4.

[1160] For example, the prompt sentence "Generate a GIF that will make my friends laugh" is input into the generative AI model.

[1161] Technologies used: Generative AI models (e.g., OpenAI's GPT-4), natural language processing (NLP).

[1162] 3. Distribution function

[1163] The server delivers the generated surprise element to the user terminal, for example, by sending the generated GIF image as an HTTP response.

[1164] Technologies used: HTTP protocol, data serialization (e.g. JSON).

[1165] 4. Response collection function

[1166] The server receives the user's reaction data and stores it in a database. The user enters the reaction data in the application and sends it to the server.

[1167] Technologies used: Database management (e.g., SQL, NoSQL), data analysis tools (e.g., Python pandas, scikit-learn).

[1168] 5. Improved features

[1169] The server analyzes the collected response data and improves the prompts and generation algorithms of the generative AI model, making the content generated more effective in the future.

[1170] Techniques used: Machine learning, data mining, feedback loops.

[1171] User terminal

[1172] The user terminal is the device through which the user accesses the system and experiences the wow factor, and has the following features:

[1173] 1. Generation request sending function

[1174] A function that allows the user to click the "surprise generate button" to send a generation request to the server.

[1175] For example, when you tap a button on a smartphone application, a generation request is sent to the server as an HTTP request.

[1176] 2. Display function

[1177] A function to display or play surprise elements delivered from the server.

[1178] For example, a GIF image received in a video chat application is displayed on the screen.

[1179] 3. Reaction input function

[1180] A function that provides an interface for users to input their responses and sends that data to the server.

[1181] For example, a user enters their thoughts in a reaction field and clicks a send button, whereby the reaction data is sent to the server.

[1182] Specific examples

[1183] For example, when a user uses this system during a video chat with a friend, the specific actions are as follows:

[1184] 1. The user enters a generation request

[1185] The user clicks the "Generate Surprise" button in the video chat app.

[1186] 2. Receive and parse the generation request

[1187] The server receives the generation request and generates the prompt "Generate a GIF that will make my friends laugh."

[1188] 3. Generate surprise elements using generative AI models

[1189] The server calls the GPT-4 API, inputs a prompt, and generates a funny GIF image.

[1190] 4. Deliver the generated surprise element to the device

[1191] The server sends the generated GIF image to the terminal as an HTTP response.

[1192] 5. Display or play the surprise element you received

[1193] The user's device displays the GIF image in a video chat app.

[1194] 6. Collect user feedback

[1195] The user enters a response such as "That's funny!" and the device sends it to the server.

[1196] 7. Improve the generation function based on the collected reaction data

[1197] The server analyzes the response data and improves the next prompt and generation algorithm.

[1198] As described above, this system generates a variety of surprise elements based on user requests, not only providing new enjoyment and surprises to users, but also continually improving based on collected reaction data, thereby enabling the provision of a more effective entertainment experience.

[1199] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1200] Step 1:

[1201] The user enters a generation request

[1202] Input: User clicks the "Generate Surprise Button".

[1203] Specific action: The user taps or clicks a button on an application on their smartphone or computer.

[1204] Data processing: The terminal detects this event and sends a generation request (including the user ID and request content) to the server as an HTTP request.

[1205] Output: A generate request is sent to the server.

[1206] Step 2:

[1207] The server receives and analyzes the request

[1208] Input: The generate request submitted in step 1.

[1209] Specific operation: Receives and analyzes the HTTP request received by the server.

[1210] Data processing: Extract and analyze the data in the generation request (user ID, request content). Generate a prompt sentence such as "Generate a GIF that will make my friends laugh."

[1211] Output: The prompt statement is generated.

[1212] Step 3:

[1213] The server generates surprise elements using generative AI models

[1214] Input: The prompt statement generated in step 2.

[1215] Specific operation: The server calls the API of the generative AI model (e.g., GPT-4) and sends the prompt sentence as input.

[1216] Data processing: The generative AI model performs data calculations based on the prompt text to generate a surprise element (e.g., a funny GIF image).

[1217] Output: Generated wow factor (GIF image).

[1218] Step 4:

[1219] The server delivers the generated surprise element to the device.

[1220] Input: The wow factor (GIF image) generated in step 3.

[1221] Specific operation: The server sends the generated data to the terminal as an HTTP response.

[1222] Data processing: The generated surprise data is serialized and converted into a format that can be sent.

[1223] Output: The surprise element is delivered to the device.

[1224] Step 5:

[1225] The device displays or plays a surprise element

[1226] Input: The surprise element (GIF image) delivered in step 4.

[1227] Specific behavior: The device's video chat application renders the received GIF image and displays it on the screen.

[1228] Data processing: Deserialize the received surprise element data and convert it into a displayable format.

[1229] Output: The wow factor is displayed to the user.

[1230] Step 6:

[1231] Collect user responses and send them to the server

[1232] Input: User reaction to seeing the surprise element.

[1233] Specific operation: The user enters their thoughts and evaluations in the reaction interface within the application and presses the send button.

[1234] Data processing: The device collects the user's reaction data and sends it to the server as an HTTP request.

[1235] Output: The user's reaction data is sent to the server.

[1236] Step 7:

[1237] The server receives and analyzes the reaction data.

[1238] Input: User response data submitted in step 6.

[1239] Specific operation: Receives the HTTP request received by the server and extracts the response data.

[1240] Data processing: Reaction data is stored in a database and analyzed using analytical tools.

[1241] Output: The analysis results are obtained.

[1242] Step 8:

[1243] Server generation improvements

[1244] Input: Analysis results obtained in step 7.

[1245] Specific operation: The server designs new prompt sentence patterns based on the analysis results and adjusts the parameters of the generative AI model.

[1246] Data processing: Change the parameters of the generation algorithm and update the prompt text.

[1247] Output: The improved generation functionality will be reflected in subsequent generation results.

[1248] (Application example 1)

[1249] 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."

[1250] Conventional factory work support systems lack effective means for maintaining worker motivation. Continuing monotonous work and accumulating mental fatigue can lead to a decline in work efficiency and quality, which can have a negative impact on overall productivity. The present invention aims to provide an effective means for improving worker motivation and maintaining and improving work efficiency.

[1251] 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.

[1252] In this invention, the server includes means for accepting a generation request, means for generating a surprise element based on the generation request, means for distributing the generated surprise element to a user terminal, means for collecting user responses, means for analyzing the collected responses and improving the generation means, means for supporting work at a workplace by accepting a refresh request, and means for displaying the surprise element to a worker. Thus, when a refresh request is input during work, a surprise element is generated and distributed, thereby improving the worker's motivation.

[1253] "Means for accepting a creation request" is a general term for interfaces and processes for receiving a creation request from a user or worker.

[1254] The "generation means for generating a surprise element based on a generation request" is software or hardware for generating a surprise element from a received generation request.

[1255] The "distribution means for distributing the generated surprise element to the user terminal" is a means for transmitting the generated surprise element to the user terminal via a network.

[1256] The "means for collecting user responses" is a general term for an interface or process for recording or collecting the responses that users have shown to surprise elements.

[1257] The "improvement means for analyzing collected responses and improving the generation means" is a means for analyzing collected user responses as data and improving the process for generating surprise elements based on the results.

[1258] The "work support means for accepting a refresh request at the work site" refers to an interface or process for transmitting a request to the system when a worker desires a refresh.

[1259] The "display means for displaying the surprise element to the worker" refers to a device or interface for providing the generated surprise element to the worker visually, audibly, or the like.

[1260] This invention provides a system that uses a generative AI model to provide surprises when factory workers want to take a break, thereby improving their motivation. This system is mainly composed of three entities: a server, a terminal, and a user.

[1261] server

[1262] The server plays a central role in the system. Specifically, it accepts generation requests, generates and distributes surprise elements based on those requests, and collects and analyzes user responses to improve the generation process. The server uses the following hardware and software:

[1263] Hardware: High-performance servers (e.g. cloud servers or dedicated servers)

[1264] Software: AI engines (e.g., TensorFlow, PyTorch), databases (e.g., MySQL, PostgreSQL), web frameworks (e.g., Flask, Django)

[1265] Terminal

[1266] The terminal is the part that the worker directly interfaces with. It inputs the generation request, inputs the response, and displays the generated surprise element. Specific devices include tablets and PCs with internet connectivity. It has the following functions:

[1267] Generation request sending function: When a worker inputs a refresh request, it is sent to the server.

[1268] Display function: The generated surprise elements are presented to workers visually, audibly, etc.

[1269] Reaction input function: Inputs the reactions of workers and sends the data to the server.

[1270] User

[1271] Users are primarily factory workers. When they want to refresh themselves while working, they access the system through their terminals. When a user inputs a refresh request, the data is sent to the server, and an AI engine is used to generate a surprise element. The generated surprise element is then delivered to the user's terminal, where the user can experience it and input their reaction.

[1272] Specific examples

[1273] For example, when a worker says, "I want to refresh myself," the device sends a generation request to the server. The server uses a generative AI model to generate a surprise element, such as a funny GIF image, an encouraging message, or a short video clip. The generated surprise element is then sent to the worker's device and displayed there. When the worker views the surprise element and enters their thoughts or reactions, the data is sent to the server, where it is collected and analyzed.

[1274] Based on this collected data, the server can improve its generative AI model and generate more effective surprise elements for subsequent refresh requests.

[1275] Prompt Sentence Examples

[1276] An example prompt for a generative AI model might look something like this:

[1277] "Generation request: Please generate a funny video. Example response: A video of a cat flipping."

[1278] "Generation Request: Generate an encouraging message. Example Response: You did a great job today!"

[1279] As described above, this system improves worker motivation and provides a means to increase factory productivity.

[1280] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1281] Step 1:

[1282] Entering and submitting a generation request

[1283] When a user wishes to refresh while working, they input a generation request through the terminal interface. For example, they input "I want to refresh" using voice recognition. When this input is received by the terminal, the generation request data (e.g., a generation request message and user ID) is sent to the server.

[1284] Input: User refresh request (e.g. voice input)

[1285] Output: Creation request data (e.g., creation request message and user ID)

[1286] Step 2:

[1287] Accepting and parsing creation requests

[1288] The server receives and analyzes the generation request data. This analysis includes converting the data into a format that matches the prompt of the generative AI model. Specifically, the server analyzes the received generation request message and determines the type of surprise element (e.g., a funny image, an encouraging message, etc.).

[1289] Input: Creation request data (e.g., creation request message and user ID)

[1290] Output: Analysis results (e.g., type of surprise element)

[1291] Step 3:

[1292] Creating an element of surprise

[1293] The server uses the generative AI model to generate surprise elements based on the analysis results. This is the process of inputting a prompt statement into the generative AI model and generating the corresponding surprise element. For example, video data generated based on the prompt statement "Please generate an interesting video" is output.

[1294] Input: Analysis result (e.g., type of surprise element)

[1295] Output: Generated surprise elements (e.g. video data, image data, messages, etc.)

[1296] Step 4:

[1297] Delivering surprise elements

[1298] The server distributes the generated surprise element to the terminal. The distribution means transmits the generated data to the terminal via the network. The terminal receives the surprise element and displays it in an appropriate format (e.g., display on the screen, play as audio).

[1299] Input: Generated surprise elements (e.g., video data, image data, messages, etc.)

[1300] Output: Device that receives and displays the surprise element

[1301] Step 5:

[1302] Collecting user responses

[1303] The user reacts to the displayed surprise element. The user inputs their reaction using the device's reaction input function (e.g., text input, impression input, evaluation input). The input reaction data is sent from the device to the server.

[1304] Input: User response (e.g., impressions and ratings)

[1305] Output: Response data (e.g., text data, evaluation data)

[1306] Step 6:

[1307] Analysis and storage of reaction data

[1308] The server analyzes the received reaction data and stores it in a database. This analysis includes categorizing reactions as positive or negative and analyzing specific impressions. The analysis results are used to improve the generative AI model in the future.

[1309] Input: Reaction data (e.g., text data, evaluation data)

[1310] Output: Analysis results, saved data

[1311] Step 7:

[1312] Improving generative AI models

[1313] The server uses the analysis results to improve the generative AI model, which includes retraining the model using machine learning algorithms and incorporating new data, allowing it to deliver a more effective wow factor for the next generation request.

[1314] Input: Analysis results, saved data

[1315] Output: An improved generative AI model

[1316] Through each of the above steps, this system can provide factory workers with a refreshing element and improve their motivation to work.

[1317] 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.

[1318] The present invention relates to a system that receives a generation request, generates surprise elements, delivers them to user terminals, collects user reactions, and improves the generation method based on the data. This system further combines an emotion engine to recognize user emotions and generate surprise elements with high accuracy.

[1319] System configuration

[1320] This system consists of three main components: a server, a terminal, and a user. In addition, an emotion engine analyzes the user's emotions and provides feedback to the generator.

[1321] server

[1322] The server is the central component of the system and includes the following functions:

[1323] 1. Generation request reception function: A function to accept generation requests from terminals.

[1324] 2. Generation function: A function that generates surprise elements based on generation requests. It uses an AI engine to generate surprise elements in various formats, including audio, images, videos, and text.

[1325] 3. Distribution function: The function to send the generated surprise element to the terminal.

[1326] 4. Reaction collection function: A function for receiving user reaction data.

[1327] 5. Improvement function: A function to analyze collected reaction data and improve the generation function.

[1328] 6. Emotion analysis function: A function that analyzes collected user voice tone, facial expressions, and text input to recognize the user's emotions.

[1329] Terminal

[1330] The terminal is the device through which the user accesses the system and experiences the wow factor. The terminal's role is to:

[1331] 1. Generation request sending function: An interface for users to input generation requests.

[1332] 2. Display function: A function to display or play the surprise elements delivered from the server.

[1333] 3. Reaction input function: An interface for inputting user reactions.

[1334] System Operation

[1335] The system of the present invention operates as follows.

[1336] 1. The user enters a generation request

[1337] User: Click the "Generate Surprise" button on the device.

[1338] Terminal: Detects a click event, generates generation request data, and sends it to the server.

[1339] 2. Receive the generation request and generate the wow factor

[1340] Server: Receives the generation request and analyzes its contents.

[1341] Server: Using the generation function, generate surprise elements (e.g., interesting images, audio, video, text) based on the AI ​​engine.

[1342] 3. Deliver surprise elements to devices

[1343] Server: Temporarily stores the generated surprise elements, formats them as data, and sends them to the device.

[1344] Terminal: Display or play the received surprise element in an appropriate format.

[1345] 4. Collect user responses

[1346] User: Experience the surprise element and enter their thoughts and ratings through the reaction interface.

[1347] Terminal: Collects user reaction data and sends it to the server.

[1348] 5. Improve based on collected response data

[1349] Server: Receives collected reaction data and stores it for analysis.

[1350] Server: Uses emotion analysis to recognize emotions based on the user's tone of voice, facial expressions, and text input.

[1351] Server: The emotion data recognized by the emotion engine is fed back to the generation means and reflected in future generation. This generates more accurate surprise elements.

[1352] Specific examples

[1353] For example, when using this system during a meeting, it works as follows.

[1354] 1. The user enters a generation request

[1355] User: Click the "Generate Surprise Button" during a meeting.

[1356] 2. Receive the generation request and generate the wow factor

[1357] Server: Receives the generation request and generates an interesting GIF image using the generation function.

[1358] 3. Deliver surprise elements to devices

[1359] Server: Sends the generated GIF image to the device.

[1360] Terminal: Display GIF images on the presentation screen in a meeting.

[1361] 4. Collect user responses

[1362] User: The whole meeting is laughing.

[1363] Terminal: Enter your reaction (e.g., "interesting" or "surprised") through the reaction interface.

[1364] Terminal: Sends collected reaction data to the server.

[1365] 5. Improve based on collected response data

[1366] Server: Receives reaction data and stores it for analysis.

[1367] Server: Uses emotion analysis to analyze the user's tone of voice, facial expressions, and text input to recognize emotions.

[1368] Server: Recognized emotion data is fed back to the generation means, and adjustments are made to maximize the effect of laughter the next time it is generated.

[1369] As described above, the system of the present invention uses an emotion engine to improve the accuracy of the surprise element experienced by the user and to continuously improve it, thereby providing the user with a deeper sense of satisfaction and surprise.

[1370] The processing flow will be explained below.

[1371] Step 1:

[1372] User: Click the "Generate Surprise" button on the device.

[1373] Step 2:

[1374] Terminal: Detects a click event and generates generation request data (e.g., user ID, current context information, parameters for generation, etc.).

[1375] Step 3:

[1376] Terminal: Sends the generation request data to the server.

[1377] Step 4:

[1378] Server: Receives the generation request data sent from the terminal.

[1379] Step 5:

[1380] Server: Analyzes the generation request data and determines what type of surprise element (e.g., audio, image, video, text, etc.) to generate.

[1381] Step 6:

[1382] Server: Calls the generation means and generates surprise elements based on the specified parameters. At this time, an AI engine is used to generate optimal surprise elements based on the user's past reaction data and generation request data.

[1383] Step 7:

[1384] Server: Temporarily stores the generated surprise elements and formats them for delivery to the device.

[1385] Step 8:

[1386] Server: Delivers the prepared surprise elements to the device.

[1387] Step 9:

[1388] Terminal: Receives the surprise element received from the server and displays or plays it in the specified format (e.g., displays an image on the screen, plays a sound).

[1389] Step 10:

[1390] User: Experience the surprise element and enter their thoughts and ratings through the reaction interface.

[1391] Step 11:

[1392] Terminal: Collects user reaction data and sends it to the server.

[1393] Step 12:

[1394] Server: Receives collected user reaction data.

[1395] Step 13:

[1396] Server: Using emotion analysis capabilities, the server analyzes the user's tone of voice, facial expressions, and text input to recognize the user's emotions.

[1397] Step 14:

[1398] Server: Recognized emotion data is fed back to the algorithms and parameters of the generation method, and improvements are made to generate better surprise elements.

[1399] Example 2

[1400] 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."

[1401] Conventional content generation systems lack the ability to accurately recognize user emotions and reactions and improve the generated content based on them. This has led to issues such as low user satisfaction and limited system effectiveness. Furthermore, it is difficult to analyze complex user emotions in real time, so a method to improve the quality of generated content is needed.

[1402] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1403] In this invention, the server includes means for accepting a generation request, means for generating a surprise element based on the generation request, means for distributing the generated surprise element to a user terminal, means for collecting user responses, means for analyzing the collected responses and improving the generation means, means for analyzing emotions that recognize the user's emotions, and means for feeding back the results of the emotion analysis to the generation means. This makes it possible to accurately analyze user emotions and improve the quality of the generated content based on the analysis.

[1404] The "means for accepting a generation request" is a device or program having the function of receiving and analyzing a request for content generation from a user.

[1405] A "generation means for generating a surprise element based on a generation request" is a device or program for generating content (e.g., audio, images, video, text) to surprise a user based on a received generation request.

[1406] The "distribution means for distributing the generated surprise element to the user terminal" is a device or program for transmitting the generated content to the user's device so that the user can experience it.

[1407] The "collection means for collecting user responses" is a device or program for collecting responses (e.g., impressions, evaluations, reactions) made by users to generated content.

[1408] The "improvement means for analyzing collected responses and improving the generation means" is a device or program for analyzing collected user response data and improving the algorithm or model of the generation means based on the analysis results.

[1409] The "emotion analysis means for recognizing user emotions" is a device or program for analyzing and identifying emotions from the user's tone of voice, facial expressions, text input, and the like.

[1410] The "feedback means for feeding back the result of emotion analysis to the generation means" is a device or program for providing the generation means with the user's emotion data recognized by the emotion analysis means and reflecting it in the generated content.

[1411] System Overview

[1412] The present invention is a system that receives generation requests from users, generates surprise elements, delivers them to user terminals, and collects and analyzes their reactions to improve the generation method. This system includes an emotion analysis function, making it possible to generate surprise elements with higher accuracy, thereby increasing the satisfaction of the user experience.

[1413] Hardware and software configuration

[1414] The main components of the system are:

[1415] Server: A central processing unit with the following functions:

[1416] Creation request reception function: Accepts creation requests.

[1417] Generation function: Generates the wow factor based on the generation request.

[1418] Distribution function: The generated surprise element is distributed to the device.

[1419] Reaction collection function: Collects user reaction data.

[1420] Improvement function: Analyze collected reaction data and improve the generation method.

[1421] Sentiment analysis function: Analyzes user emotions.

[1422] Feedback function: The results of sentiment analysis are fed back to the generation means.

[1423] Terminal: A device used by a user, with the following functions:

[1424] Generation request sending function: Sends a generation request.

[1425] Display function: Display or play the generated surprise element.

[1426] Reaction input function: Input reaction data and send it to the server.

[1427] Software used

[1428] Generative AI Models: Use advanced generative AI models such as OpenAI GPT-4 to generate various forms of surprise based on prompts.

[1429] Sentiment analysis engine: Software for analyzing a user's tone of voice, facial expressions, and text input. Some are offered as API services (e.g., EmotionAPI).

[1430] Example of operation process

[1431] Let's walk through the following scenario:

[1432] Use during meetings

[1433] 1. Enter the generation request

[1434] User: Click the "Generate Surprise" button during the meeting and enter a generation request. For example, enter a prompt such as "Generate a prank image of a cat."

[1435] 2. Sending a generation request

[1436] Terminal: Generates the generation request data and sends it to the server.

[1437] 3. Receiving and parsing the generation request

[1438] Server: Receives the generated request data and parses the prompt statement.

[1439] 4. Creating surprise

[1440] Server: Uses a generative AI model such as OpenAI GPT-4 to generate a surprise element (e.g., a funny cat GIF) based on the prompt.

[1441] 5. Deliver surprise elements

[1442] Server: Temporarily stores the generated surprise elements, formats them as data, and sends them to the device.

[1443] Terminal: The received surprise element is displayed on the presentation screen during the meeting.

[1444] 6. Collecting User Responses

[1445] User: Participants react by laughing out loud.

[1446] Terminal: Collects reaction data through reaction interfaces (e.g., reaction buttons and text fields) and sends them to the server.

[1447] 7. Analysis and Improvement of Reaction Data

[1448] Server: Analyzes the reaction data and recognizes the user's emotions using an emotion analysis engine.

[1449] Server: The recognized emotion data is fed back to the generation means and reflected in future generation. This makes it possible to generate more accurate surprise elements in the future.

[1450] Conclusion

[1451] By combining a generative AI model with an emotion analysis engine, this system can accurately analyze users' emotions and reactions and provide high-quality content based on that, significantly improving the satisfaction of the user experience.

[1452] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1453] Specific processing steps of the program

[1454] Step 1: Enter the generation request

[1455] User: Enters a generation request through the terminal interface. The user clicks a specific button (e.g., "Generate a Surprise" button) or enters a prompt statement in text. An example of input is the prompt statement "Generate a prank image of a cat."

[1456] Input: User actions (clicks and text input)

[1457] Output: Generate request data is generated

[1458] Specific operation: During a meeting, the user clicks the "Surprising Generate Button" to request a refresh.

[1459] Step 2: Submit a Generate Request

[1460] Terminal: Generates the generation request data and sends it to the server.

[1461] Input: Generation request data (including prompt statement)

[1462] Output: Generated request data sent to the server as an HTTP request

[1463] Specific operation: The terminal packets the generation request as an HTTP request and sends it to the server's generation request receiving endpoint.

[1464] Step 3: Receiving and parsing the generation request

[1465] Server: Receives the generation request data and analyzes its contents. It references the prompt text and the user's past response data.

[1466] Input: Generation request data

[1467] Output: Data formatted to be input to the AI ​​model

[1468] Specific operation: The server receives the HTTP request, analyzes the generation request, and formats it into data to input into the AI ​​model.

[1469] Step 4: Generate surprise

[1470] Server: Generates surprise elements using a generative AI model (e.g., OpenAI GPT-4) based on the analysis results. For example, generate a funny cat GIF image based on the prompt text.

[1471] Input: Data formatted for the AI ​​model (including prompts)

[1472] Output: Generated surprise element (GIF image, audio, text, etc.)

[1473] Specific operation: The server inputs a prompt sentence into the generative AI model, retrieves the generated content from the model, and temporarily stores it.

[1474] Step 5: Deliver the surprise element

[1475] Server: Formats the generated surprise elements appropriately and sends them to the device.

[1476] Terminal: Display or play the received surprise element.

[1477] Input: Generated wow factor

[1478] Output: Data sent to the device as an HTTP response

[1479] Specific operation: The server sends the generated surprise element to the device as an HTTP response. The device receives the data and displays it on the presentation screen at the conference.

[1480] Step 6: Gathering user responses

[1481] User: Experience the surprise element and enter their thoughts and ratings through the reaction interface.

[1482] Terminal: Collects user reaction data and sends it to the server.

[1483] Input: User response (text impressions, rating button clicks, etc.)

[1484] Output: Reaction data is generated and sent to the server

[1485] Specific operation: The user clicks the reaction button or enters their thoughts in the text field. The device collects the data and sends it to the server.

[1486] Step 7: Analyze and refine reaction data

[1487] Server: Receives the response data and uses an emotion analysis engine to analyze voice tone, facial expressions, and text input.

[1488] Server: Improve the generation method based on the analysis results and reflect them in subsequent generations.

[1489] Input: Reaction data

[1490] Output: Feedback on improving the generator

[1491] Specific operation: The server runs the data analysis engine and performs statistical analysis on the collected reaction data. Based on the analysis results, the parameters of the generative model are adjusted and reflected in the next generation of surprise elements.

[1492] Through these steps, the system generates surprise elements in response to user requests and can continuously improve the generation method based on user responses.

[1493] (Application example 2)

[1494] 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."

[1495] In modern manufacturing, improving employee efficiency and motivation is an important issue. In particular, monotonous work and long working hours can increase employee fatigue and stress, negatively impacting productivity. Conventional methods have made it difficult to properly understand employee emotions and reactions and make continuous improvements that are not disposable.

[1496] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1497] In this invention, the server includes means for receiving a generation request, means for generating a surprise element based on the generation request, means for distributing the generated surprise element to a terminal, means for collecting user responses, means for analyzing the collected responses and improving the generation means, and means for analyzing user emotions. This not only makes it possible to generate and provide surprise elements that reduce employee stress and increase motivation, but also to continuously improve the generation algorithm based on the collected data.

[1498] A "generation request" is a request that a user sends to a server to generate a particular wow factor.

[1499] A "generator" is a system or algorithm for generating a wow factor based on a generation request.

[1500] The "distribution means" refers to a function or method for transmitting the generated surprise element to the user terminal.

[1501] "Collection means" refers to the functions and technologies used to obtain user responses and store them as data.

[1502] An "improvement means" is a system or algorithm that analyzes collected reaction data and improves the performance of the generation means based on the results.

[1503] "Emotion analysis means" refers to technology or a system that analyzes a user's voice tone, facial expression, and text data to recognize emotions.

[1504] A "terminal" is a device that a user uses to access the system and receive generated surprise elements.

[1505] The "surprise element" is content such as audio, images, video, text, and mini-games that are generated to provide surprise and enjoyment to the user.

[1506] "Reaction" refers to the emotions and reactions that users show after experiencing a surprise element.

[1507] "Imaging means" refers to the camera or sensor used to capture the user's facial expressions and movements.

[1508] This invention relates to a system that generates and distributes surprise elements based on user requests, collects and analyzes user responses, and continuously improves the generation method based on the collected responses. This system is primarily composed of three main components: a server, a terminal, and a user. Furthermore, it uses an emotion analysis method to analyze user emotions and generate highly accurate surprise elements.

[1509] System configuration

[1510] server

[1511] Generation request receiving means: receives a generation request from a user. For example, when a user sends a generation request manually or by voice input, the request is received.

[1512] Generation method: Generate surprise elements based on generation requests. Using a generative AI model, surprise elements such as audio, images, videos, text, or mini-games are generated randomly or based on a specific algorithm.

[1513] Delivery means: The generated surprise element is sent to the user's device. The data is delivered in an appropriate format so that the user's device can display or play the surprise element in real time.

[1514] Collection method: Collect user reactions. A webcam and microphone are used to collect the user's facial expressions and voice tone in real time.

[1515] Improvement measures: Analyze the collected reaction data and improve the generation algorithm. For example, based on the collected smiley face data, adjust the next generation so that it will elicit more smiles.

[1516] Sentiment analysis methods: Techniques and software for identifying user emotions from collected data. Examples include facial expression analysis using OpenCV and text sentiment analysis using TextBlob.

[1517] Terminal

[1518] The terminal is the device that the user uses to access the system and receive the generated surprise element. The main functions of the terminal are as follows:

[1519] Generation request sending function: Provides an interface for users to input generation requests. For example, this can be achieved through a smartphone application or voice recognition function.

[1520] Display function: Displays or plays surprise elements distributed from the server. Audio messages are played from the device's speaker, and images and videos are displayed on the screen.

[1521] Reaction input function: An interface for collecting user reactions. The camera and microphone are used to record the user's reactions and send the data to the server.

[1522] Specific examples

[1523] For example, when a worker clicks the "Generate Surprise Button" during a break at the factory, the following occurs:

[1524] User: The worker taps the "surprise generation button" on their smartphone.

[1525] Server: Receives generation requests and generates fun GIFs and mini-games using generative AI models.

[1526] Terminal: The generated surprise element is delivered to the worker's smartphone and displayed on the screen.

[1527] User: The worker looks at it and laughs, and the camera captures the smile.

[1528] Server: Analyzes the collected smile data and improves the generation algorithm.

[1529] Prompt Sentence Examples

[1530] The prompt sentence used for the generative AI model is in the following format:

[1531] "Generate funny GIFs that will make your employees laugh. The content should be humorous and perfect for a break from work."

[1532] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1533] Step 1:

[1534] The user enters a generation request

[1535] The user taps the "surprise generation button" on the device and inputs a generation request.

[1536] Input: User taps

[1537] Output: Generated request data

[1538] Specific operation: The terminal detects a tap event, generates generation request data, and sends it to the server.

[1539] Step 2:

[1540] Receives a generation request and generates the wow factor

[1541] The server receives the generation request, parses it, and generates the wow factor.

[1542] Input: Generation request data

[1543] Output: Surprise element (audio, image, video, text, mini-game)

[1544] Specific operation: Input a prompt into the generative AI model, and generate surprise elements based on the prompt, such as creating funny GIF images or mini-games.

[1545] Step 3:

[1546] Delivering surprise to your device

[1547] The generated surprise element is sent to the user's terminal.

[1548] Input: Generated wow factor

[1549] Output: The wow factor that is played or displayed on the device

[1550] Specific operation: The server converts the generated surprise element into an appropriate format and sends it to the device. The device displays or plays the received data to the user.

[1551] Step 4:

[1552] Collect user responses

[1553] Users experience the surprise element and their reactions are collected.

[1554] Input: User's reaction (facial expression, voice)

[1555] Output: Reaction data

[1556] Specific operation: The device uses a camera and microphone to collect data on the user's facial expressions and voice, and sends it to the server.

[1557] Step 5:

[1558] Improve based on collected reaction data

[1559] The server analyzes the collected reaction data and improves the generation algorithm.

[1560] Input: Reaction data

[1561] Output: Improved generation algorithm

[1562] Specific operation: The server analyzes the reaction data and recognizes the user's emotions using the emotion analysis means. The recognized emotion data is fed back to the generation means and reflected in the next surprise element generation.

[1563] 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.

[1564] 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.

[1565] 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.

[1566] [Fourth embodiment]

[1567] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1568] 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.

[1569] 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).

[1570] 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.

[1571] 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.

[1572] 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).

[1573] 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.

[1574] 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.

[1575] 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.

[1576] 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.

[1577] 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.

[1578] 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.

[1579] 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."

[1580] The present invention relates to a system that accepts a generation request, generates a surprise element, and delivers it to a user terminal. It also has a feedback function that collects user reactions and improves the generation means based on that data. A detailed description of an embodiment of this system is provided below.

[1581] System configuration

[1582] This system is broadly composed of three components: the server, the terminal, and the user.

[1583] server

[1584] The server is the central component that receives production requests, generates the wow factor, and distributes it. Specifically, it has the following functions:

[1585] 1. Generation request reception function: A function to accept generation requests from terminals.

[1586] 2. Generation function: A function that generates surprise elements based on generation requests. Using an AI engine, surprise elements are generated in various formats, including audio, images, videos, and text.

[1587] 3. Distribution function: The function to send the generated surprise element to the terminal.

[1588] 4. Reaction collection function: A function for receiving user reaction data.

[1589] 5. Improvement function: A function to analyze collected reaction data and improve the generation function.

[1590] Terminal

[1591] The terminal is the device through which the user accesses the system and experiences the wow factor. The terminal has the following functions:

[1592] 1. Generation request sending function: An interface for users to input generation requests. A function to send generation requests to the server.

[1593] 2. Display function: A function to display or play the surprise elements delivered from the server.

[1594] 3. Reaction input function: An interface for inputting user reactions. A function for sending reaction data to the server.

[1595] System Operation

[1596] The system of the present invention operates as follows.

[1597] 1. The user enters a generation request

[1598] User: Click the "Generate Surprise" button on the device.

[1599] Terminal: Detects the click event and sends a generation request to the server.

[1600] 2. Receive the generation request and generate the wow factor

[1601] Server: Receives the generation request and analyzes its contents.

[1602] Server: Uses the generation function to instruct the AI ​​engine to generate surprising elements (e.g., interesting images, audio, video, text).

[1603] 3. Deliver surprise elements to devices

[1604] Server: Sends the generated surprise element to the device.

[1605] Terminal: Display or play the received surprise element in an appropriate format.

[1606] 4. Collect user responses

[1607] User: Experience the surprise element and enter their thoughts and ratings through the reaction interface.

[1608] Terminal: Sends user reaction data to the server.

[1609] 5. Improve based on collected response data

[1610] Server: Receives reaction data and stores it for analysis.

[1611] Server: Use the collected data to improve the generation function and reflect it in the next surprise element generation.

[1612] Specific examples

[1613] For example, if you use this system while video chatting with a friend, it works as follows:

[1614] 1. The user enters a generation request

[1615] User: Click the "Generate Surprise Button" during a video chat.

[1616] 2. Receive the generation request and generate the wow factor

[1617] Server: Receives the generation request and generates an interesting GIF image using the generation function.

[1618] 3. Deliver surprise elements to devices

[1619] Server: Sends the generated GIF image to the device.

[1620] Device: Display GIF images in video chat apps.

[1621] 4. Collect user responses

[1622] User: Enters reactions through the reaction interface, such as surprise or laughter.

[1623] Device: Sends reaction data to the server.

[1624] 5. Improve based on collected response data

[1625] Server: Receives reaction data and stores it for analysis.

[1626] Server: Improve the generation function based on the data and use it for the next generation.

[1627] As described above, the system of the present invention not only generates a variety of surprise elements based on generation requests, providing users with new enjoyment and surprises, but also provides a more effective entertainment experience by continuously improving the system based on collected reaction data.

[1628] The processing flow will be explained below.

[1629] Step 1:

[1630] User: Click the "Generate Surprise" button on the device.

[1631] Step 2:

[1632] Terminal: Detects a click event and generates generation request data (e.g., user ID, current context information, parameters for generation, etc.).

[1633] Step 3:

[1634] Terminal: Sends the generation request data to the server.

[1635] Step 4:

[1636] Server: Receives the generation request data sent from the terminal.

[1637] Step 5:

[1638] Server: Analyzes the generation request data and determines what type of surprise element (e.g., audio, image, video, text, etc.) to generate.

[1639] Step 6:

[1640] Server: Calls the generation means and generates surprise elements based on the specified parameters. At this time, an AI engine is used to generate optimal surprise elements based on the user's past reaction data and generation request data.

[1641] Step 7:

[1642] Server: Temporarily stores the generated surprise elements and formats them for delivery to the device.

[1643] Step 8:

[1644] Server: Delivers the prepared surprise elements to the device.

[1645] Step 9:

[1646] Terminal: Receives the surprise element received from the server and displays or plays it in the specified format (e.g., displays an image on the screen, plays a sound).

[1647] Step 10:

[1648] User: Experience the surprise element and enter their thoughts and ratings through the reaction interface.

[1649] Step 11:

[1650] Terminal: Collects user reaction data and sends it to the server.

[1651] Step 12:

[1652] Server: Receives collected user response data and stores it in a database for analysis.

[1653] Step 13:

[1654] Server: Based on the response data, the algorithms and parameters of the generation method are adjusted, and improvements are made to create a better element of surprise for the next generation request.

[1655] Example 1

[1656] 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."

[1657] In conventional systems, the generation of elements to surprise and entertain users is monotonous, and the generation process is rarely improved based on individual user responses. Therefore, it is difficult to maintain user interest.

[1658] 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.

[1659] In this invention, the server includes means for receiving a generation request, means for generating a surprise element using a generative AI model based on the generation request, means for distributing the generated surprise element to a user terminal, means for collecting user responses, and means for analyzing the collected responses and improving the generation means. This makes it possible to provide individual surprise elements to users and improve the content of subsequent generations based on the responses.

[1660] A "generation request" is an action or content of a user requesting the system to generate a surprise element.

[1661] A "generative AI model" is an artificial intelligence engine that uses artificial intelligence technology to generate audio, images, videos, text, etc. based on input prompts.

[1662] A "prompt" is a sentence or text that gives specific instructions to the generative AI model on what to generate.

[1663] A "surprise element" is digital content such as audio, images, video, and text that is created to surprise and entertain users.

[1664] The "distribution means" is a function or process for transmitting the generated surprise element to the user terminal.

[1665] The "collection means" is a function or process for collecting user reaction data.

[1666] "Improvement means" refers to the function or process for analyzing collected response data and improving generative AI models or generative algorithms.

[1667] A "user terminal" is a device through which a user accesses the system and experiences the generated surprise elements.

[1668] This invention relates to a system that accepts generation requests, generates surprise elements, and delivers them to user terminals. It also has a feedback function that collects user responses and improves the generation method based on that data. This system consists of three entities: a server, a user terminal, and the user.

[1669] server

[1670] The server is the central player in receiving requests, generating surprise elements, and delivering them. Specifically, it has the following functions:

[1671] 1. Generation request reception function

[1672] The server receives a generation request from a user terminal. For example, when a user clicks the "surprise generation button" on a smartphone or PC application, the generation request is sent to the server.

[1673] Technologies used: HTTP requests and responses, RESTful APIs.

[1674] 2. Generation function

[1675] The server generates a prompt sentence based on the generation request and inputs it into the generative AI model, such as GPT-4.

[1676] For example, the prompt sentence "Generate a GIF that will make my friends laugh" is input into the generative AI model.

[1677] Technologies used: Generative AI models (e.g., OpenAI's GPT-4), natural language processing (NLP).

[1678] 3. Distribution function

[1679] The server delivers the generated surprise element to the user terminal, for example, by sending the generated GIF image as an HTTP response.

[1680] Technologies used: HTTP protocol, data serialization (e.g. JSON).

[1681] 4. Response collection function

[1682] The server receives the user's reaction data and stores it in a database. The user enters the reaction data in the application and sends it to the server.

[1683] Technologies used: Database management (e.g., SQL, NoSQL), data analysis tools (e.g., Python pandas, scikit-learn).

[1684] 5. Improved features

[1685] The server analyzes the collected response data and improves the prompts and generation algorithms of the generative AI model, making the content generated more effective in the future.

[1686] Techniques used: Machine learning, data mining, feedback loops.

[1687] User terminal

[1688] The user terminal is the device through which the user accesses the system and experiences the wow factor, and has the following features:

[1689] 1. Generation request sending function

[1690] A function that allows the user to click the "surprise generate button" to send a generation request to the server.

[1691] For example, when you tap a button on a smartphone application, a generation request is sent to the server as an HTTP request.

[1692] 2. Display function

[1693] A function to display or play surprise elements delivered from the server.

[1694] For example, a GIF image received in a video chat application is displayed on the screen.

[1695] 3. Reaction input function

[1696] A function that provides an interface for users to input their responses and sends that data to the server.

[1697] For example, a user enters their thoughts in a reaction field and clicks a send button, whereby the reaction data is sent to the server.

[1698] Specific examples

[1699] For example, when a user uses this system during a video chat with a friend, the specific actions are as follows:

[1700] 1. The user enters a generation request

[1701] The user clicks the "Generate Surprise" button in the video chat app.

[1702] 2. Receive and parse the generation request

[1703] The server receives the generation request and generates the prompt "Generate a GIF that will make my friends laugh."

[1704] 3. Generate surprise elements using generative AI models

[1705] The server calls the GPT-4 API, inputs a prompt, and generates a funny GIF image.

[1706] 4. Deliver the generated surprise element to the device

[1707] The server sends the generated GIF image to the terminal as an HTTP response.

[1708] 5. Display or play the surprise element you received

[1709] The user's device displays the GIF image in a video chat app.

[1710] 6. Collect user feedback

[1711] The user enters a response such as "That's funny!" and the device sends it to the server.

[1712] 7. Improve the generation function based on the collected reaction data

[1713] The server analyzes the response data and improves the next prompt and generation algorithm.

[1714] As described above, this system generates a variety of surprise elements based on user requests, not only providing new enjoyment and surprises to users, but also continually improving based on collected reaction data, thereby enabling the provision of a more effective entertainment experience.

[1715] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1716] Step 1:

[1717] The user enters a generation request

[1718] Input: User clicks the "Generate Surprise Button".

[1719] Specific action: The user taps or clicks a button on an application on their smartphone or computer.

[1720] Data processing: The terminal detects this event and sends a generation request (including the user ID and request content) to the server as an HTTP request.

[1721] Output: A generate request is sent to the server.

[1722] Step 2:

[1723] The server receives and analyzes the request

[1724] Input: The generate request submitted in step 1.

[1725] Specific operation: Receives and analyzes the HTTP request received by the server.

[1726] Data processing: Extract and analyze the data in the generation request (user ID, request content). Generate a prompt sentence such as "Generate a GIF that will make my friends laugh."

[1727] Output: The prompt statement is generated.

[1728] Step 3:

[1729] The server generates surprise elements using generative AI models

[1730] Input: The prompt statement generated in step 2.

[1731] Specific operation: The server calls the API of the generative AI model (e.g., GPT-4) and sends the prompt sentence as input.

[1732] Data processing: The generative AI model performs data calculations based on the prompt text to generate a surprise element (e.g., a funny GIF image).

[1733] Output: Generated wow factor (GIF image).

[1734] Step 4:

[1735] The server delivers the generated surprise element to the device.

[1736] Input: The wow factor (GIF image) generated in step 3.

[1737] Specific operation: The server sends the generated data to the terminal as an HTTP response.

[1738] Data processing: The generated surprise data is serialized and converted into a format that can be sent.

[1739] Output: The surprise element is delivered to the device.

[1740] Step 5:

[1741] The device displays or plays a surprise element

[1742] Input: The surprise element (GIF image) delivered in step 4.

[1743] Specific behavior: The device's video chat application renders the received GIF image and displays it on the screen.

[1744] Data processing: Deserialize the received surprise element data and convert it into a displayable format.

[1745] Output: The wow factor is displayed to the user.

[1746] Step 6:

[1747] Collect user responses and send them to the server

[1748] Input: User reaction to seeing the surprise element.

[1749] Specific operation: The user enters their thoughts and evaluations in the reaction interface within the application and presses the send button.

[1750] Data processing: The device collects the user's reaction data and sends it to the server as an HTTP request.

[1751] Output: The user's reaction data is sent to the server.

[1752] Step 7:

[1753] The server receives and analyzes the reaction data.

[1754] Input: User response data submitted in step 6.

[1755] Specific operation: Receives the HTTP request received by the server and extracts the response data.

[1756] Data processing: Reaction data is stored in a database and analyzed using analytical tools.

[1757] Output: The analysis results are obtained.

[1758] Step 8:

[1759] Server generation improvements

[1760] Input: Analysis results obtained in step 7.

[1761] Specific operation: The server designs new prompt sentence patterns based on the analysis results and adjusts the parameters of the generative AI model.

[1762] Data processing: Change the parameters of the generation algorithm and update the prompt text.

[1763] Output: The improved generation functionality will be reflected in subsequent generation results.

[1764] (Application example 1)

[1765] 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."

[1766] Conventional factory work support systems lack effective means for maintaining worker motivation. Continuing monotonous work and accumulating mental fatigue can lead to a decline in work efficiency and quality, which can have a negative impact on overall productivity. The present invention aims to provide an effective means for improving worker motivation and maintaining and improving work efficiency.

[1767] 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.

[1768] In this invention, the server includes means for accepting a generation request, means for generating a surprise element based on the generation request, means for distributing the generated surprise element to a user terminal, means for collecting user responses, means for analyzing the collected responses and improving the generation means, means for supporting work at a workplace by accepting a refresh request, and means for displaying the surprise element to a worker. Thus, when a refresh request is input during work, a surprise element is generated and distributed, thereby improving the worker's motivation.

[1769] "Means for accepting a creation request" is a general term for interfaces and processes for receiving a creation request from a user or worker.

[1770] The "generation means for generating a surprise element based on a generation request" is software or hardware for generating a surprise element from a received generation request.

[1771] The "distribution means for distributing the generated surprise element to the user terminal" is a means for transmitting the generated surprise element to the user terminal via a network.

[1772] The "means for collecting user responses" is a general term for an interface or process for recording or collecting the responses that users have shown to surprise elements.

[1773] The "improvement means for analyzing collected responses and improving the generation means" is a means for analyzing collected user responses as data and improving the process for generating surprise elements based on the results.

[1774] The "work support means for accepting a refresh request at the work site" refers to an interface or process for transmitting a request to the system when a worker desires a refresh.

[1775] The "display means for displaying the surprise element to the worker" refers to a device or interface for providing the generated surprise element to the worker visually, audibly, or the like.

[1776] This invention provides a system that uses a generative AI model to provide surprises when factory workers want to take a break, thereby improving their motivation. This system is mainly composed of three entities: a server, a terminal, and a user.

[1777] server

[1778] The server plays a central role in the system. Specifically, it accepts generation requests, generates and distributes surprise elements based on those requests, and collects and analyzes user responses to improve the generation process. The server uses the following hardware and software:

[1779] Hardware: High-performance servers (e.g. cloud servers or dedicated servers)

[1780] Software: AI engines (e.g., TensorFlow, PyTorch), databases (e.g., MySQL, PostgreSQL), web frameworks (e.g., Flask, Django)

[1781] Terminal

[1782] The terminal is the part that the worker directly interfaces with. It inputs the generation request, inputs the response, and displays the generated surprise element. Specific devices include tablets and PCs with internet connectivity. It has the following functions:

[1783] Generation request sending function: When a worker inputs a refresh request, it is sent to the server.

[1784] Display function: The generated surprise elements are presented to workers visually, audibly, etc.

[1785] Reaction input function: Inputs the reactions of workers and sends the data to the server.

[1786] User

[1787] Users are primarily factory workers. When they want to refresh themselves while working, they access the system through their terminals. When a user inputs a refresh request, the data is sent to the server, and an AI engine is used to generate a surprise element. The generated surprise element is then delivered to the user's terminal, where the user can experience it and input their reaction.

[1788] Specific examples

[1789] For example, when a worker says, "I want to refresh myself," the device sends a generation request to the server. The server uses a generative AI model to generate a surprise element, such as a funny GIF image, an encouraging message, or a short video clip. The generated surprise element is then sent to the worker's device and displayed there. When the worker views the surprise element and enters their thoughts or reactions, the data is sent to the server, where it is collected and analyzed.

[1790] Based on this collected data, the server can improve its generative AI model and generate more effective surprise elements for subsequent refresh requests.

[1791] Prompt Sentence Examples

[1792] An example prompt for a generative AI model might look something like this:

[1793] "Generation request: Please generate a funny video. Example response: A video of a cat flipping."

[1794] "Generation Request: Generate an encouraging message. Example Response: You did a great job today!"

[1795] As described above, this system improves worker motivation and provides a means to increase factory productivity.

[1796] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1797] Step 1:

[1798] Entering and submitting a generation request

[1799] When a user wishes to refresh while working, they input a generation request through the terminal interface. For example, they input "I want to refresh" using voice recognition. When this input is received by the terminal, the generation request data (e.g., a generation request message and user ID) is sent to the server.

[1800] Input: User refresh request (e.g. voice input)

[1801] Output: Creation request data (e.g., creation request message and user ID)

[1802] Step 2:

[1803] Accepting and parsing creation requests

[1804] The server receives and analyzes the generation request data. This analysis includes converting the data into a format that matches the prompt of the generative AI model. Specifically, the server analyzes the received generation request message and determines the type of surprise element (e.g., a funny image, an encouraging message, etc.).

[1805] Input: Creation request data (e.g., creation request message and user ID)

[1806] Output: Analysis results (e.g., type of surprise element)

[1807] Step 3:

[1808] Creating an element of surprise

[1809] The server uses the generative AI model to generate surprise elements based on the analysis results. This is the process of inputting a prompt statement into the generative AI model and generating the corresponding surprise element. For example, video data generated based on the prompt statement "Please generate an interesting video" is output.

[1810] Input: Analysis result (e.g., type of surprise element)

[1811] Output: Generated surprise elements (e.g. video data, image data, messages, etc.)

[1812] Step 4:

[1813] Delivering surprise elements

[1814] The server distributes the generated surprise element to the terminal. The distribution means transmits the generated data to the terminal via the network. The terminal receives the surprise element and displays it in an appropriate format (e.g., display on the screen, play as audio).

[1815] Input: Generated surprise elements (e.g., video data, image data, messages, etc.)

[1816] Output: Device that receives and displays the surprise element

[1817] Step 5:

[1818] Collecting user responses

[1819] The user reacts to the displayed surprise element. The user inputs their reaction using the device's reaction input function (e.g., text input, impression input, evaluation input). The input reaction data is sent from the device to the server.

[1820] Input: User response (e.g., impressions and ratings)

[1821] Output: Response data (e.g., text data, evaluation data)

[1822] Step 6:

[1823] Analysis and storage of reaction data

[1824] The server analyzes the received reaction data and stores it in a database. This analysis includes categorizing reactions as positive or negative and analyzing specific impressions. The analysis results are used to improve the generative AI model in the future.

[1825] Input: Reaction data (e.g., text data, evaluation data)

[1826] Output: Analysis results, saved data

[1827] Step 7:

[1828] Improving generative AI models

[1829] The server uses the analysis results to improve the generative AI model, which includes retraining the model using machine learning algorithms and incorporating new data, allowing it to deliver a more effective wow factor for the next generation request.

[1830] Input: Analysis results, saved data

[1831] Output: An improved generative AI model

[1832] Through each of the above steps, this system can provide factory workers with a refreshing element and improve their motivation to work.

[1833] 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.

[1834] The present invention relates to a system that receives a generation request, generates surprise elements, delivers them to user terminals, collects user reactions, and improves the generation method based on the data. This system further combines an emotion engine to recognize user emotions and generate surprise elements with high accuracy.

[1835] System configuration

[1836] This system consists of three main components: a server, a terminal, and a user. In addition, an emotion engine analyzes the user's emotions and provides feedback to the generator.

[1837] server

[1838] The server is the central component of the system and includes the following functions:

[1839] 1. Generation request reception function: A function to accept generation requests from terminals.

[1840] 2. Generation function: A function that generates surprise elements based on generation requests. It uses an AI engine to generate surprise elements in various formats, including audio, images, videos, and text.

[1841] 3. Distribution function: The function to send the generated surprise element to the terminal.

[1842] 4. Reaction collection function: A function for receiving user reaction data.

[1843] 5. Improvement function: A function to analyze collected reaction data and improve the generation function.

[1844] 6. Emotion analysis function: A function that analyzes collected user voice tone, facial expressions, and text input to recognize the user's emotions.

[1845] Terminal

[1846] The terminal is the device through which the user accesses the system and experiences the wow factor. The terminal's role is to:

[1847] 1. Generation request sending function: An interface for users to input generation requests.

[1848] 2. Display function: A function to display or play the surprise elements delivered from the server.

[1849] 3. Reaction input function: An interface for inputting user reactions.

[1850] System Operation

[1851] The system of the present invention operates as follows.

[1852] 1. The user enters a generation request

[1853] User: Click the "Generate Surprise" button on the device.

[1854] Terminal: Detects a click event, generates generation request data, and sends it to the server.

[1855] 2. Receive the generation request and generate the wow factor

[1856] Server: Receives the generation request and analyzes its contents.

[1857] Server: Using the generation function, generate surprise elements (e.g., interesting images, audio, video, text) based on the AI ​​engine.

[1858] 3. Deliver surprise elements to devices

[1859] Server: Temporarily stores the generated surprise elements, formats them as data, and sends them to the device.

[1860] Terminal: Display or play the received surprise element in an appropriate format.

[1861] 4. Collect user responses

[1862] User: Experience the surprise element and enter their thoughts and ratings through the reaction interface.

[1863] Terminal: Collects user reaction data and sends it to the server.

[1864] 5. Improve based on collected response data

[1865] Server: Receives collected reaction data and stores it for analysis.

[1866] Server: Uses emotion analysis to recognize emotions based on the user's tone of voice, facial expressions, and text input.

[1867] Server: The emotion data recognized by the emotion engine is fed back to the generation means and reflected in future generation. This generates more accurate surprise elements.

[1868] Specific examples

[1869] For example, when using this system during a meeting, it works as follows.

[1870] 1. The user enters a generation request

[1871] User: Click the "Generate Surprise Button" during a meeting.

[1872] 2. Receive the generation request and generate the wow factor

[1873] Server: Receives the generation request and generates an interesting GIF image using the generation function.

[1874] 3. Deliver surprise elements to devices

[1875] Server: Sends the generated GIF image to the device.

[1876] Terminal: Display GIF images on the presentation screen in a meeting.

[1877] 4. Collect user responses

[1878] User: The whole meeting is laughing.

[1879] Terminal: Enter your reaction (e.g., "interesting" or "surprised") through the reaction interface.

[1880] Terminal: Sends collected reaction data to the server.

[1881] 5. Improve based on collected response data

[1882] Server: Receives reaction data and stores it for analysis.

[1883] Server: Uses emotion analysis to analyze the user's tone of voice, facial expressions, and text input to recognize emotions.

[1884] Server: Recognized emotion data is fed back to the generation means, and adjustments are made to maximize the effect of laughter the next time it is generated.

[1885] As described above, the system of the present invention uses an emotion engine to improve the accuracy of the surprise element experienced by the user and to continuously improve it, thereby providing the user with a deeper sense of satisfaction and surprise.

[1886] The processing flow will be explained below.

[1887] Step 1:

[1888] User: Click the "Generate Surprise" button on the device.

[1889] Step 2:

[1890] Terminal: Detects a click event and generates generation request data (e.g., user ID, current context information, parameters for generation, etc.).

[1891] Step 3:

[1892] Terminal: Sends the generation request data to the server.

[1893] Step 4:

[1894] Server: Receives the generation request data sent from the terminal.

[1895] Step 5:

[1896] Server: Analyzes the generation request data and determines what type of surprise element (e.g., audio, image, video, text, etc.) to generate.

[1897] Step 6:

[1898] Server: Calls the generation means and generates surprise elements based on the specified parameters. At this time, an AI engine is used to generate optimal surprise elements based on the user's past reaction data and generation request data.

[1899] Step 7:

[1900] Server: Temporarily stores the generated surprise elements and formats them for delivery to the device.

[1901] Step 8:

[1902] Server: Delivers the prepared surprise elements to the device.

[1903] Step 9:

[1904] Terminal: Receives the surprise element received from the server and displays or plays it in the specified format (e.g., displays an image on the screen, plays a sound).

[1905] Step 10:

[1906] User: Experience the surprise element and enter their thoughts and ratings through the reaction interface.

[1907] Step 11:

[1908] Terminal: Collects user reaction data and sends it to the server.

[1909] Step 12:

[1910] Server: Receives collected user reaction data.

[1911] Step 13:

[1912] Server: Using emotion analysis capabilities, the server analyzes the user's tone of voice, facial expressions, and text input to recognize the user's emotions.

[1913] Step 14:

[1914] Server: Recognized emotion data is fed back to the algorithms and parameters of the generation method, and improvements are made to generate better surprise elements.

[1915] Example 2

[1916] 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."

[1917] Conventional content generation systems lack the ability to accurately recognize user emotions and reactions and improve the generated content based on them. This has led to issues such as low user satisfaction and limited system effectiveness. Furthermore, it is difficult to analyze complex user emotions in real time, so a method to improve the quality of generated content is needed.

[1918] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1919] In this invention, the server includes means for accepting a generation request, means for generating a surprise element based on the generation request, means for distributing the generated surprise element to a user terminal, means for collecting user responses, means for analyzing the collected responses and improving the generation means, means for analyzing emotions that recognize the user's emotions, and means for feeding back the results of the emotion analysis to the generation means. This makes it possible to accurately analyze user emotions and improve the quality of the generated content based on the analysis.

[1920] The "means for accepting a generation request" is a device or program having the function of receiving and analyzing a request for content generation from a user.

[1921] A "generation means for generating a surprise element based on a generation request" is a device or program for generating content (e.g., audio, images, video, text) to surprise a user based on a received generation request.

[1922] The "distribution means for distributing the generated surprise element to the user terminal" is a device or program for transmitting the generated content to the user's device so that the user can experience it.

[1923] The "collection means for collecting user responses" is a device or program for collecting responses (e.g., impressions, evaluations, reactions) made by users to generated content.

[1924] The "improvement means for analyzing collected responses and improving the generation means" is a device or program for analyzing collected user response data and improving the algorithm or model of the generation means based on the analysis results.

[1925] The "emotion analysis means for recognizing user emotions" is a device or program for analyzing and identifying emotions from the user's tone of voice, facial expressions, text input, and the like.

[1926] The "feedback means for feeding back the result of emotion analysis to the generation means" is a device or program for providing the generation means with the user's emotion data recognized by the emotion analysis means and reflecting it in the generated content.

[1927] System Overview

[1928] The present invention is a system that receives generation requests from users, generates surprise elements, delivers them to user terminals, and collects and analyzes their reactions to improve the generation method. This system includes an emotion analysis function, making it possible to generate surprise elements with higher accuracy, thereby increasing the satisfaction of the user experience.

[1929] Hardware and software configuration

[1930] The main components of the system are:

[1931] Server: A central processing unit with the following functions:

[1932] Creation request reception function: Accepts creation requests.

[1933] Generation function: Generates the wow factor based on the generation request.

[1934] Distribution function: The generated surprise element is distributed to the device.

[1935] Reaction collection function: Collects user reaction data.

[1936] Improvement function: Analyze collected reaction data and improve the generation method.

[1937] Sentiment analysis function: Analyzes user emotions.

[1938] Feedback function: The results of sentiment analysis are fed back to the generation means.

[1939] Terminal: A device used by a user, with the following functions:

[1940] Generation request sending function: Sends a generation request.

[1941] Display function: Display or play the generated surprise element.

[1942] Reaction input function: Input reaction data and send it to the server.

[1943] Software used

[1944] Generative AI Models: Use advanced generative AI models such as OpenAI GPT-4 to generate various forms of surprise based on prompts.

[1945] Sentiment analysis engine: Software for analyzing a user's tone of voice, facial expressions, and text input. Some are offered as API services (e.g., EmotionAPI).

[1946] Example of operation process

[1947] Let's walk through the following scenario:

[1948] Use during meetings

[1949] 1. Enter the generation request

[1950] User: Click the "Generate Surprise" button during the meeting and enter a generation request. For example, enter a prompt such as "Generate a prank image of a cat."

[1951] 2. Sending a generation request

[1952] Terminal: Generates the generation request data and sends it to the server.

[1953] 3. Receiving and parsing the generation request

[1954] Server: Receives the generated request data and parses the prompt statement.

[1955] 4. Creating surprise

[1956] Server: Uses a generative AI model such as OpenAI GPT-4 to generate a surprise element (e.g., a funny cat GIF) based on the prompt.

[1957] 5. Deliver surprise elements

[1958] Server: Temporarily stores the generated surprise elements, formats them as data, and sends them to the device.

[1959] Terminal: The received surprise element is displayed on the presentation screen during the meeting.

[1960] 6. Collecting User Responses

[1961] User: Participants react by laughing out loud.

[1962] Terminal: Collects reaction data through reaction interfaces (e.g., reaction buttons and text fields) and sends them to the server.

[1963] 7. Analysis and Improvement of Reaction Data

[1964] Server: Analyzes the reaction data and recognizes the user's emotions using an emotion analysis engine.

[1965] Server: The recognized emotion data is fed back to the generation means and reflected in future generation. This makes it possible to generate more accurate surprise elements in the future.

[1966] Conclusion

[1967] By combining a generative AI model with an emotion analysis engine, this system can accurately analyze users' emotions and reactions and provide high-quality content based on that, significantly improving the satisfaction of the user experience.

[1968] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1969] Specific processing steps of the program

[1970] Step 1: Enter the generation request

[1971] User: Enters a generation request through the terminal interface. The user clicks a specific button (e.g., "Generate a Surprise" button) or enters a prompt statement in text. An example of input is the prompt statement "Generate a prank image of a cat."

[1972] Input: User actions (clicks and text input)

[1973] Output: Generate request data is generated

[1974] Specific operation: During a meeting, the user clicks the "Surprising Generate Button" to request a refresh.

[1975] Step 2: Submit a Generate Request

[1976] Terminal: Generates the generation request data and sends it to the server.

[1977] Input: Generation request data (including prompt statement)

[1978] Output: Generated request data sent to the server as an HTTP request

[1979] Specific operation: The terminal packets the generation request as an HTTP request and sends it to the server's generation request receiving endpoint.

[1980] Step 3: Receiving and parsing the generation request

[1981] Server: Receives the generation request data and analyzes its contents. It references the prompt text and the user's past response data.

[1982] Input: Generation request data

[1983] Output: Data formatted to be input to the AI ​​model

[1984] Specific operation: The server receives the HTTP request, analyzes the generation request, and formats it into data to input into the AI ​​model.

[1985] Step 4: Generate surprise

[1986] Server: Generates surprise elements using a generative AI model (e.g., OpenAI GPT-4) based on the analysis results. For example, generate a funny cat GIF image based on the prompt text.

[1987] Input: Data formatted for the AI ​​model (including prompts)

[1988] Output: Generated surprise element (GIF image, audio, text, etc.)

[1989] Specific operation: The server inputs a prompt sentence into the generative AI model, retrieves the generated content from the model, and temporarily stores it.

[1990] Step 5: Deliver the surprise element

[1991] Server: Formats the generated surprise elements appropriately and sends them to the device.

[1992] Terminal: Display or play the received surprise element.

[1993] Input: Generated wow factor

[1994] Output: Data sent to the device as an HTTP response

[1995] Specific operation: The server sends the generated surprise element to the device as an HTTP response. The device receives the data and displays it on the presentation screen at the conference.

[1996] Step 6: Gathering user responses

[1997] User: Experience the surprise element and enter their thoughts and ratings through the reaction interface.

[1998] Terminal: Collects user reaction data and sends it to the server.

[1999] Input: User response (text impressions, rating button clicks, etc.)

[2000] Output: Reaction data is generated and sent to the server

[2001] Specific operation: The user clicks the reaction button or enters their thoughts in the text field. The device collects the data and sends it to the server.

[2002] Step 7: Analyze and refine reaction data

[2003] Server: Receives the response data and uses an emotion analysis engine to analyze voice tone, facial expressions, and text input.

[2004] Server: Improve the generation method based on the analysis results and reflect them in subsequent generations.

[2005] Input: Reaction data

[2006] Output: Feedback on improving the generator

[2007] Specific operation: The server runs the data analysis engine and performs statistical analysis on the collected reaction data. Based on the analysis results, the parameters of the generative model are adjusted and reflected in the next generation of surprise elements.

[2008] Through these steps, the system generates surprise elements in response to user requests and can continuously improve the generation method based on user responses.

[2009] (Application example 2)

[2010] 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."

[2011] In modern manufacturing, improving employee efficiency and motivation is an important issue. In particular, monotonous work and long working hours can increase employee fatigue and stress, negatively impacting productivity. Conventional methods have made it difficult to properly understand employee emotions and reactions and make continuous improvements that are not disposable.

[2012] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[2013] In this invention, the server includes means for receiving a generation request, means for generating a surprise element based on the generation request, means for distributing the generated surprise element to a terminal, means for collecting user responses, means for analyzing the collected responses and improving the generation means, and means for analyzing user emotions. This not only makes it possible to generate and provide surprise elements that reduce employee stress and increase motivation, but also to continuously improve the generation algorithm based on the collected data.

[2014] A "generation request" is a request that a user sends to a server to generate a particular wow factor.

[2015] A "generator" is a system or algorithm for generating a wow factor based on a generation request.

[2016] The "distribution means" refers to a function or method for transmitting the generated surprise element to the user terminal.

[2017] "Collection means" refers to the functions and technologies used to obtain user responses and store them as data.

[2018] An "improvement means" is a system or algorithm that analyzes collected reaction data and improves the performance of the generation means based on the results.

[2019] "Emotion analysis means" refers to technology or a system that analyzes a user's voice tone, facial expression, and text data to recognize emotions.

[2020] A "terminal" is a device that a user uses to access the system and receive generated surprise elements.

[2021] The "surprise element" is content such as audio, images, video, text, and mini-games that are generated to provide surprise and enjoyment to the user.

[2022] "Reaction" refers to the emotions and reactions that users show after experiencing a surprise element.

[2023] "Imaging means" refers to the camera or sensor used to capture the user's facial expressions and movements.

[2024] This invention relates to a system that generates and distributes surprise elements based on user requests, collects and analyzes user responses, and continuously improves the generation method based on the collected responses. This system is primarily composed of three main components: a server, a terminal, and a user. Furthermore, it uses an emotion analysis method to analyze user emotions and generate highly accurate surprise elements.

[2025] System configuration

[2026] server

[2027] Generation request receiving means: receives a generation request from a user. For example, when a user sends a generation request manually or by voice input, the request is received.

[2028] Generation method: Generate surprise elements based on generation requests. Using a generative AI model, surprise elements such as audio, images, videos, text, or mini-games are generated randomly or based on a specific algorithm.

[2029] Delivery means: The generated surprise element is sent to the user's device. The data is delivered in an appropriate format so that the user's device can display or play the surprise element in real time.

[2030] Collection method: Collect user reactions. A webcam and microphone are used to collect the user's facial expressions and voice tone in real time.

[2031] Improvement measures: Analyze the collected reaction data and improve the generation algorithm. For example, based on the collected smiley face data, adjust the next generation so that it will elicit more smiles.

[2032] Sentiment analysis methods: Techniques and software for identifying user emotions from collected data. Examples include facial expression analysis using OpenCV and text sentiment analysis using TextBlob.

[2033] Terminal

[2034] The terminal is the device that the user uses to access the system and receive the generated surprise element. The main functions of the terminal are as follows:

[2035] Generation request sending function: Provides an interface for users to input generation requests. For example, this can be achieved through a smartphone application or voice recognition function.

[2036] Display function: Displays or plays surprise elements distributed from the server. Audio messages are played from the device's speaker, and images and videos are displayed on the screen.

[2037] Reaction input function: An interface for collecting user reactions. The camera and microphone are used to record the user's reactions and send the data to the server.

[2038] Specific examples

[2039] For example, when a worker clicks the "Generate Surprise Button" during a break at the factory, the following occurs:

[2040] User: The worker taps the "surprise generation button" on their smartphone.

[2041] Server: Receives generation requests and generates fun GIFs and mini-games using generative AI models.

[2042] Terminal: The generated surprise element is delivered to the worker's smartphone and displayed on the screen.

[2043] User: The worker looks at it and laughs, and the camera captures the smile.

[2044] Server: Analyzes the collected smile data and improves the generation algorithm.

[2045] Prompt Sentence Examples

[2046] The prompt sentence used for the generative AI model is in the following format:

[2047] "Generate funny GIFs that will make your employees laugh. The content should be humorous and perfect for a break from work."

[2048] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2049] Step 1:

[2050] The user enters a generation request

[2051] The user taps the "surprise generation button" on the device and inputs a generation request.

[2052] Input: User taps

[2053] Output: Generated request data

[2054] Specific operation: The terminal detects a tap event, generates generation request data, and sends it to the server.

[2055] Step 2:

[2056] Receives a generation request and generates the wow factor

[2057] The server receives the generation request, parses it, and generates the wow factor.

[2058] Input: Generation request data

[2059] Output: Surprise element (audio, image, video, text, mini-game)

[2060] Specific operation: Input a prompt into the generative AI model, and generate surprise elements based on the prompt, such as creating funny GIF images or mini-games.

[2061] Step 3:

[2062] Delivering surprise to your device

[2063] The generated surprise element is sent to the user's terminal.

[2064] Input: Generated wow factor

[2065] Output: The wow factor that is played or displayed on the device

[2066] Specific operation: The server converts the generated surprise element into an appropriate format and sends it to the device. The device displays or plays the received data to the user.

[2067] Step 4:

[2068] Collect user responses

[2069] Users experience the surprise element and their reactions are collected.

[2070] Input: User's reaction (facial expression, voice)

[2071] Output: Reaction data

[2072] Specific operation: The device uses a camera and microphone to collect data on the user's facial expressions and voice, and sends it to the server.

[2073] Step 5:

[2074] Improve based on collected reaction data

[2075] The server analyzes the collected reaction data and improves the generation algorithm.

[2076] Input: Reaction data

[2077] Output: Improved generation algorithm

[2078] Specific operation: The server analyzes the reaction data and recognizes the user's emotions using the emotion analysis means. The recognized emotion data is fed back to the generation means and reflected in the next surprise element generation.

[2079] 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.

[2080] 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.

[2081] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[2082] 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.

[2083] 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.

[2084] 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.

[2085] 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).

[2086] 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.

[2087] 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."

[2088] 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.

[2089] 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).

[2090] 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.

[2091] 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.

[2092] 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.

[2093] 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.

[2094] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[2095] 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.

[2096] 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.

[2097] 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.

[2098] 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.

[2099] 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.

[2100] The following is further disclosed regarding the above embodiment.

[2101] (Claim 1)

[2102] means for accepting a generation request;

[2103] a generating means for generating a surprise element based on a generation request;

[2104] a distribution means for distributing the generated surprise element to a user terminal;

[2105] a collection means for collecting user responses;

[2106] an improvement means for analyzing the collected responses and improving the generation means;

[2107] A system including:

[2108] (Claim 2)

[2109] 2. The system of claim 1, wherein the generating means generates at least one of audio, image, video, or text.

[2110] (Claim 3)

[2111] 2. The system according to claim 1, wherein the reaction collection means collects user reactions in real time.

[2112] "Example 1"

[2113] (Claim 1)

[2114] means for accepting a generation request;

[2115] A generating means for generating a surprise element using a generative AI model based on a generation request;

[2116] a distribution means for distributing the generated surprise element to a user terminal;

[2117] a collection means for collecting user responses;

[2118] an improvement means for analyzing the collected responses and improving the generation means;

[2119] A system including:

[2120] (Claim 2)

[2121] 2. The system of claim 1, wherein the generating means inputs a prompt sentence into a generative AI model to generate at least one of audio, image, video, or text.

[2122] (Claim 3)

[2123] 2. The system according to claim 1, wherein the reaction collection means collects user reactions in real time.

[2124] "Application Example 1"

[2125] (Claim 1)

[2126] means for accepting a generation request;

[2127] a generating means for generating a surprise element based on a generation request;

[2128] a distribution means for distributing the generated surprise element to a user terminal;

[2129] a collection means for collecting user responses;

[2130] an improvement means for analyzing the collected responses and improving the generation means;

[2131] a work support means for receiving a refresh request at a work site;

[2132] a display means for displaying the surprise element to the worker;

[2133] A system including:

[2134] (Claim 2)

[2135] 2. The system of claim 1, wherein the generating means generates at least one of audio, image, video, or text.

[2136] (Claim 3)

[2137] 2. The system according to claim 1, wherein the reaction collection means collects user reactions in real time and includes an interface through which the user inputs reactions in a work environment.

[2138] "Example 2: Combining Emotion Engines"

[2139] (Claim 1)

[2140] means for accepting a generation request;

[2141] a generating means for generating a surprise element based on a generation request;

[2142] a distribution means for distributing the generated surprise element to a user terminal;

[2143] a collection means for collecting user responses;

[2144] an improvement means for analyzing the collected responses and improving the generation means;

[2145] emotion analysis means for recognizing the emotion of a user;

[2146] a feedback means for feeding back the result of the emotion analysis to the generation means;

[2147] A system including:

[2148] (Claim 2)

[2149] 2. The system of claim 1, wherein the generating means generates at least one of audio, image, video, or text.

[2150] (Claim 3)

[2151] 2. The system according to claim 1, wherein the collecting means collects user reactions in real time.

[2152] "Application example 2 when combining emotion engines"

[2153] (Claim 1)

[2154] means for accepting a generation request;

[2155] a generating means for generating a surprise element based on a generation request;

[2156] a distribution means for distributing the generated surprise element to a terminal;

[2157] a collection means for collecting user responses;

[2158] an improvement means for analyzing the collected responses and improving the generation means;

[2159] emotion analysis means for analyzing the emotions of a user;

[2160] A system including:

[2161] (Claim 2)

[2162] 2. The system according to claim 1, wherein the generating means generates at least one of audio, image, video, text, or a mini-game.

[2163] (Claim 3)

[2164] 2. The system according to claim 1, wherein the reaction collection means collects the user's facial expressions using a camera. [Explanation of symbols]

[2165] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for accepting a generation request; a generating means for generating a surprise element based on a generation request; a distribution means for distributing the generated surprise element to a user terminal; a collection means for collecting user responses; an improvement means for analyzing the collected responses and improving the generation means; A system including:

2. The system of claim 1 , wherein the generating means generates at least one of audio, image, video, or text.

3. 2. The system according to claim 1, wherein the reaction collection means collects user reactions in real time.

Images