system

Abstract

Provide a system. The method includes: receiving instructions from a prompt engineer on the platform; means for transmitting the received instructions to an associated user terminal in real time; means for displaying instructions at a user terminal; A system including means for receiving feedback from a user terminal.

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] In the entertainment industry, performers need to be given prompt, accurate instructions according to the situation when performing in real time. Traditional methods often result in delayed or unclear instructions, resulting in a decline in the quality of performance. Furthermore, performers must rely on their own judgment to respond to situations, which can increase stress and negatively impact the overall performance and production efficiency. Furthermore, performers' feedback is sometimes not properly reflected, making overall improvement difficult. [Means for solving the problem]

[0005] This invention provides a system that includes means for receiving instructions from a prompt engineer on a platform and transmitting the received instructions to relevant user terminals in real time, means for displaying the instructions on the user terminal, and means for receiving feedback from the user terminal. This system quickly and accurately conveys the prompt engineer's instructions to users (performers), providing real-time performance support. Furthermore, by providing means for allocating the instructions to specific users, the system provides instructions tailored to individual performers, improving the quality of performance. Furthermore, by providing means for adjusting the next instruction based on feedback, the system enables flexible instruction provision that reflects the performers' opinions, improving overall performance and production efficiency.

[0006] "Platform" refers to the dedicated system for receiving and sending instructions from Prompt Engineers.

[0007] A "prompt engineer" is a specialist who provides real-time instructions to support smooth performance.

[0008] "Instructions" refer to specific actions or messages provided by the Prompt Engineer.

[0009] "Means for Receiving" refers to the functionality or methods for receiving instructions and feedback on the Platform.

[0010] "Means for sending" refers to a function or method for sending received instructions to a user terminal.

[0011] "User terminal" refers to devices such as smartphones, tablets, and personal computers used by performers.

[0012] The "display means" refers to a function or method for displaying instructions on the screen of a user terminal.

[0013] "Feedback" refers to a user sending back to the platform a response or result to an instruction.

[0014] The "distribution means" refers to a function or method for appropriately distributing received instructions to specific users.

[0015] "Means to adjust" refers to a function or method for modifying or optimizing the next instruction based on feedback. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] This invention is a system that supports performers in the entertainment industry by allowing them to receive instructions in real time and perform smoothly. It is realized through the cooperation of a platform, a server, user terminals, and prompt engineers.

[0038] Overall system overview

[0039] The system mainly consists of the following components:

[0040] Prompt An interface for engineers to enter instructions.

[0041] The server receives and stores the instructions and sends them to the appropriate user.

[0042] The user terminal displays the instructions and sends the feedback to the server.

[0043] Prompt engineer inputs instructions

[0044] Prompt engineers access the system through a web or mobile interface and enter specific instructions, such as "get ready to move to the next corner," which are then sent to the server.

[0045] Processing on the server

[0046] The server first receives instructions sent by the prompt engineer. It then stores the received instructions in a database along with associated metadata. After storing the instructions, the server analyzes the instructions and identifies the relevant user (performer). Once the target user is identified, the server sends the instructions to the user's device in real time.

[0047] Processing on the user terminal

[0048] The user device receives instructions sent from the server in real time and displays them on the screen. After the user confirms the instructions, they actually take action based on the instructions (for example, preparing to move to the next corner). After responding to the instructions, the user clicks the "Done" button on the device and sends feedback to the server.

[0049] Processing Feedback

[0050] The server analyzes the feedback received from the user terminal and stores it in the database, and the feedback information is notified to the prompt engineer for reference in adjusting the next instruction.

[0051] Specific examples

[0052] Examples from TV shows

[0053] The prompt engineer inputs the instruction "Please prepare to move to the next segment" and sends it to the server. The server receives this instruction and sends it to the device of the target user (performer). The performer's device displays the instruction, and the performer acts according to the instruction. When the performer clicks the "Done" button, the feedback is sent back to the server and the prompt engineer is notified. This process ensures that the entire performance is smooth and effective.

[0054] This system allows prompt engineers to quickly and accurately communicate instructions to users, improving the quality of their performance. Furthermore, it can provide flexible and effective support by adjusting subsequent instructions based on feedback.

[0055] The processing flow will be explained below.

[0056] Step 1:

[0057] A prompt engineer accesses the system through an interface and inputs instructions (e.g., "Prepare for the next corner").

[0058] Step 2:

[0059] The server receives instructions sent by prompt engineers and stores them in a database along with associated metadata (instruction ID, user ID, timestamp, etc.).

[0060] Step 3:

[0061] The server analyzes the stored instructions and identifies the content of the instructions and the target users, for example, identifying the performers based on the specified program and user ID.

[0062] Step 4:

[0063] The server sends instructions in real time to the target user's (performer's) device. The instructions are sent in an appropriate data format (e.g., JSON format).

[0064] Step 5:

[0065] The user's device receives the instructions sent from the server and displays them on the user interface, such as a message like "Prepare to move to the next corner."

[0066] Step 6:

[0067] The user checks the instructions displayed on the device and takes the necessary action (preparing to move to the next corner) according to those instructions.

[0068] Step 7:

[0069] After the user responds to the instructions, they click the "Done" button on the device screen, which sends feedback from the user to the server.

[0070] Step 8:

[0071] The feedback includes metadata such as instruction ID, user ID, and timestamp, which the server receives, analyzes, and stores in a database.

[0072] Step 9:

[0073] The server notifies the prompt engineer of the received feedback, who then adjusts the next instructions based on the feedback.

[0074] Step 10:

[0075] This series of processes ensures that prompt engineer instructions are conveyed to users quickly and accurately, maintaining excellent performance.

[0076] Example 1

[0077] 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."

[0078] Conventional systems for providing instructions to performers in the entertainment industry have suffered from delays in transmitting instructions and the cumbersome process of confirming instructions and providing feedback to performers. Furthermore, there have been cases where instructions were not properly assigned to specific users, resulting in a decline in the quality of the performance. The present invention aims to solve these problems and provide a system that allows performers to receive instructions in real time and perform smoothly.

[0079] 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.

[0080] In this invention, the server includes means for receiving instructions from a prompt engineer, means for saving the received instructions in a database, means for analyzing the saved instructions and identifying the relevant user, means for sending instructions to the identified user terminal in real time, means for displaying the instructions on the user terminal, means for sending feedback by clicking a "Done" button on the user terminal after responding to the instructions, means for receiving feedback from the user terminal and saving the feedback in a database, and means for notifying the prompt engineer of the feedback information, thereby enabling prompt and accurate transmission of instructions and flexible adjustment of instructions based on the feedback.

[0081] A "prompt engineer" is a person in the entertainment industry whose role is to input instructions to performers in real time and transmit them through the system.

[0082] "Instructions" are messages regarding actions and preparations that the prompt engineer sends to the performers.

[0083] A "database" is a system that organizes and stores data such as instructions and feedback, and makes it quickly accessible when needed.

[0084] "Analysis" is the process by which the server understands the content of the instructions received and distributes them to the appropriate user.

[0085] "User" refers to a performer who receives instructions from the system and acts accordingly.

[0086] A "user terminal" is a device, such as a smartphone, tablet, or PC, that a user uses to receive and display instructions.

[0087] "Real-time transmission means" refers to the technology and protocols for transmitting instructions to a user terminal almost instantaneously.

[0088] "Feedback" is information that notifies the server that the user has completed an action in response to an instruction.

[0089] "Notification" is a means by which the server notifies the prompt engineer of feedback information, etc.

[0090] This invention is a system for supporting performers in the entertainment industry to receive real-time instructions and perform smoothly. The system components include a server, a user terminal, and a prompt engineer.

[0091] Program processing overview

[0092] The system mainly consists of the following components:

[0093] Prompt An interface (web or mobile) for engineers to enter instructions.

[0094] The server receives, stores, parses, and transmits the instructions to the appropriate user terminal.

[0095] The user terminal receives and displays instructions in real time and sends feedback to the server after completing the action.

[0096] Server Roles and Operations

[0097] The server is built in Python, using frameworks like Flask or Django. The server has the following features:

[0098] 1. Receives an HTTP POST request from a prompt engineer and parses the instructions.

[0099] 2. Store the received instructions along with associated metadata in a PostgreSQL database.

[0100] 3. Analyze the saved instructions and identify the target user.

[0101] 4. Send instructions to the identified user device in real time via Firebase or Socket.io.

[0102] 5. Receive user feedback and store it back in the database.

[0103] 6. Use email and notification APIs to notify prompt engineers of feedback information.

[0104] Roles and operations of user terminals

[0105] User devices include a variety of devices such as smartphones, tablets, and PCs. These devices run applications built with frameworks such as React Native and Flutter (registered trademark). Specific operations are as follows:

[0106] 1. Receive instructions sent from the server via a real-time communication protocol.

[0107] 2. Display the received instructions on the screen.

[0108] 3. After completing the instructions, click the "Done" button.

[0109] 4. Send the feedback to the server with an HTTP POST request.

[0110] User Roles

[0111] The user (performer) checks the instructions displayed on the device and takes action based on them. A specific example is the instruction "Please prepare to move to the next corner." After completing the action according to the instructions, the user clicks the "Done" button on the device and sends feedback to the server.

[0112] Specific examples of operation

[0113] The prompt engineer inputs the instruction "Please prepare to move to the next corner" through the web interface. The server receives this instruction and stores it in a database. It then analyzes the instruction and sends it to the user device of the relevant performer. The performer's device displays the instruction, and the performer acts according to it. When the performer clicks the "Done" button, feedback is sent to the server, which then notifies the prompt engineer of the feedback.

[0114] Examples of prompt statements

[0115] An example of a prompt sentence for a generative AI model is, "In this system, when the prompt engineer inputs the instruction 'Get ready to move to the next corner,' the server receives the instruction and sends it to the display terminal. The user (performer) checks the instruction, acts as instructed, and when completes, clicks the 'Done' button on the terminal to send feedback to the server."

[0116] With the above configuration and processing, this invention allows performers to receive instructions in real time and perform efficiently and smoothly.

[0117] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0118] Step 1:

[0119] A prompt engineer enters instructions. Using a web or mobile interface, the prompt engineer enters instructions such as "Get ready to move to the next corner." This entered instruction is sent to the server as an HTTP POST request. The input data is the textual instructions, and the output is the data sent to the server.

[0120] Step 2:

[0121] The server receives instructions from the prompt engineer. Using the Flask or Django framework, the server receives an HTTP POST request and parses the instructions. The input data is the HTTP request, and the output is the parsed text data. The server then stores the received instructions and associated metadata (such as a timestamp and the prompt engineer's ID) in a PostgreSQL database.

[0122] Step 3:

[0123] The server parses the stored instructions to identify the relevant users. It retrieves the stored database record and parses the instructions to identify the target users. This parsing uses specific rules and pattern matching. The input data is the database record, and the output is the target user's ID.

[0124] Step 4:

[0125] The server sends instructions to the identified user device in real time. Firebase or Socket.io is used to send instructions to the specified user device. Instructions are sent in JSON format and use real-time communication protocols. The input data is the user ID and the instruction content, and the output is the sent data.

[0126] Step 5:

[0127] The user device receives instructions sent from the server and displays them on the screen. The user device runs an application built with React Native or Flutter and receives instructions in real time via Firebase or Socket.io. When an instruction is received, the screen displays "Please prepare to move to the next corner." The input data is JSON data from the server, and the output is what is displayed on the device screen.

[0128] Step 6:

[0129] The user takes an action based on the instructions. For example, preparing to move to the next corner. When the action is complete, the user clicks the "Done" button on the device. The input data is the user's completion of the action, and the output is the click event of the "Done" button.

[0130] Step 7:

[0131] The user device sends the click of the "Done" button to the server as feedback. The feedback is sent as an HTTP POST request, and includes the user ID and the action completion status. The input data is the click event, and the output is an HTTP request.

[0132] Step 8:

[0133] The server receives feedback from the user device and stores it in a database. It parses the received feedback and stores it along with metadata (timestamp, user ID, etc.). The input data is an HTTP request, and the output is a database record.

[0134] Step 9:

[0135] The server notifies the prompt engineer of the saved feedback information. The prompt engineer is notified of the feedback using email API or notification API. The input data is a database record, and the output is a notification message.

[0136] (Application example 1)

[0137] 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."

[0138] Conventional factory work management systems lack the means to instantly notify robots and workers of work instructions, monitor progress in real time, and provide efficient feedback. As a result, work efficiency declines and productivity does not improve. In addition, it is difficult to accurately grasp the progress of work processes and issue the next instructions in a timely manner, making it difficult to manage the entire production line.

[0139] 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.

[0140] In this invention, the server includes a means for receiving instructions from a prompt engineer on the platform, a means for transmitting the received instructions to a related user terminal in real time, a means for displaying the instructions on the user terminal, a means for receiving feedback from the user terminal, a means for transmitting instructions to automated machinery and managing the work process, and a means for monitoring the progress of the work process based on the instructions. This allows work instructions in the factory to be quickly and accurately transmitted to robots and workers, progress to be monitored in real time, and the next instructions to be issued efficiently.

[0141] "Platform" refers to the platform through which prompt engineers input instructions and the server receives and processes the instructions.

[0142] A "prompt engineer" is a professional whose role is to input instructions into the system in real time.

[0143] "Instructions" are specific instructions for work or actions that are input by a prompt engineer and transmitted to a user terminal or automated machine device.

[0144] A "user terminal" is a device that displays received instructions and sends feedback, such as a tablet or smartphone.

[0145] "Feedback" refers to data sent back from the user terminal or robot to the server, such as reactions to executed instructions, completion reports, and progress status.

[0146] "Automated machinery" refers to robots and other automated equipment used to perform tasks automatically within a factory.

[0147] A "work process" is a series of steps for manufacturing or assembling an item according to a set procedure.

[0148] "Progress monitoring" refers to monitoring and understanding the progress of a work process in real time.

[0149] This invention applies a system that supports entertainment performers in receiving real-time instructions and performing smoothly to factory production line management. The main components of the system are realized through the cooperation of a platform, a server, user terminals (robots or worker devices), and a prompt engineer.

[0150] Overall system overview

[0151] The server receives instructions from the prompt engineer on the platform and transmits them to the relevant user device in real time. The user device displays the instructions and directs the automated machinery (robot) to perform the tasks based on the instructions. The server also monitors the progress of the work process, receives feedback from the user device, and adjusts the instructions.

[0152] Prompt engineer inputs instructions

[0153] A prompt engineer accesses the system through a web or mobile interface and enters specific work instructions, such as "Start assembly process on production line 1," which are then sent to the server.

[0154] Processing on the server

[0155] The server receives instructions sent by prompt engineers and stores them in a database along with associated metadata. After storing them, the server analyzes the instructions and identifies the specific user (robot or worker). Once the target user is identified, the server sends the instructions to the user's device in real time. The software to be used is planned to be Flask (a Python web framework).

[0156] Processing on the user terminal

[0157] The user device receives instructions sent from the server in real time and displays them on the screen. For example, a robot may receive the instruction "Please start the assembly process on production line 1." The robot will then begin work based on the instruction. Once the work is complete, the user clicks the "Done" button on the user device to send feedback to the server.

[0158] Processing Feedback

[0159] The server analyzes the feedback received from the user device and stores it in a database. Based on this feedback, the server adjusts the next instruction appropriately. For example, when it receives feedback such as "Assembly of production line 1 is completed," it notifies the prompt engineer and prepares to issue the next instruction.

[0160] Specific examples

[0161] For example, a prompt engineer inputs the instruction "Please start the assembly process on production line 1" into the system. This instruction is received by the server and sent to the robot on production line 1. The robot receives this instruction and starts the assembly process. When the work is completed, the robot reports "Assembly completed" to the system. The server receives this feedback and notifies the prompt engineer.

[0162] Prompt Sentence Examples

[0163] Prompt Engineer Instructions: Start assembly process on Production Line 1

[0164] Robot feedback: Assembly complete

[0165] This system allows work instructions within the factory to be transmitted quickly and accurately to robots and workers, monitors progress in real time, and efficiently issues subsequent instructions.

[0166] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0167] Step 1: Prompt engineer inputs instructions

[0168] A prompt engineer accesses the system through a web or mobile interface and enters specific work instructions, such as "Start assembly process on production line 1," which are then sent to the server in JSON format.

[0169] Input: prompt engineer instructions

[0170] Data processing: Convert instructions into JSON format

[0171] Output: Instruction data in JSON format

[0172] Step 2: Server receives and analyzes instructions

[0173] The server receives instructions in JSON format sent by the prompt engineer, stores them in a database, analyzes the instructions, and assigns them to specific users (robots or workers).

[0174] Input: Instruction data in JSON format

[0175] Data processing: Analysis of instruction data and saving to database

[0176] Output: Information on instruction distribution to specific users

[0177] Step 3: Server sends instructions

[0178] Based on the analysis results, the server sends instructions to the relevant user devices in real time, such as "Please start the assembly process for the robot on manufacturing line 1."

[0179] Input: Instruction distribution information for specific users

[0180] Data processing: Identifying user devices and sending real-time data

[0181] Output: Sends instruction data to the user terminal

[0182] Step 4: User terminal receives and displays instructions

[0183] The user terminal (e.g., a robot) receives instructions sent from the server in real time and displays them on its screen. The robot begins work according to the instructions. An instruction such as "Please start the assembly process on production line 1" is displayed.

[0184] Input: Instruction data from the server

[0185] Data processing: Decoding instruction data, displaying on screen

[0186] Output: On-screen instructions

[0187] Step 5: User performs task and provides feedback

[0188] The robot actually starts and completes the task based on the received instructions. When the task is completed, the user device clicks the "Done" button and sends feedback to the server. The feedback information "Assembly completed" is sent.

[0189] Input: Work progress, completion report

[0190] Data processing: Generate feedback information and send it to the server

[0191] Output: Feedback data to the server

[0192] Step 6: Server receives and analyzes feedback

[0193] The server analyzes the feedback received from the user terminal and stores it in the database. Based on the feedback information, it adjusts the next instruction and notifies the prompt engineer.

[0194] Input: Feedback data from user terminal

[0195] Data processing: Analysis of feedback data and storage in database

[0196] Output: Prompt engineer notification information

[0197] Step 7: Adjust and issue next instructions

[0198] The prompt engineer adjusts the next instructions based on the feedback notification from the server and inputs the new instructions into the system, thereby ensuring that the production line continues to operate efficiently.

[0199] Input: Feedback notification from the server

[0200] Data processing: creating new instructions

[0201] Output: System input for next instruction

[0202] 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.

[0203] This invention combines a prompt engineer's real-time instruction system, which displays, receives, and feeds back instructions via the user's terminal, with an emotion engine that recognizes the user's emotions, thereby improving the quality of instruction provision and realizing more effective performance support based on the user's emotional state.

[0204] Overall system overview

[0205] The system mainly consists of the following components:

[0206] Prompt An interface for engineers to enter instructions.

[0207] The server receives and stores the instructions and sends them to the appropriate users in real time.

[0208] The user terminal displays the instructions and sends the feedback to the server.

[0209] It is equipped with an emotion engine that recognizes the user's emotions and performs data analysis.

[0210] Prompt engineer inputs instructions

[0211] Prompt engineers access the system through a web or mobile interface and enter specific instructions, such as "get ready to move to the next corner," which are then sent to the server.

[0212] Processing on the server

[0213] The server first receives instructions sent by the prompt engineer. It then stores the received instructions in a database along with related metadata (instruction ID, user ID, timestamp, etc.). After storing the instructions, the server analyzes the instructions and identifies the corresponding user (performer). Once the target user is identified, the server sends the instructions to the user's device in real time.

[0214] Processing on the user terminal

[0215] The user device receives instructions sent from the server in real time and displays them on the screen. After the user confirms the instructions, they actually take action based on the instructions (for example, preparing to move to the next corner). After responding to the instructions, the user clicks the "Done" button on the device and sends feedback to the server.

[0216] Emotion engine processing

[0217] The emotion engine installed in the user's device uses sensors such as a camera and microphone to analyze the user's facial expressions, tone of voice, movements, etc. to grasp the user's emotional state. The emotion engine includes this emotional data in feedback and sends it to the server.

[0218] Processing feedback and adjusting next steps

[0219] The server analyzes the feedback and emotion data received from the user terminal and stores them in a database. This feedback information and emotion data are then notified to the prompt engineer, who uses it as a reference to adjust the next instruction based on the user's emotional state.

[0220] Specific examples

[0221] Examples from TV shows

[0222] The prompt engineer inputs the instruction "Please prepare to move to the next segment" and sends it to the server. The server receives this instruction and sends it to the device of the target user (performer). The instruction is displayed on the device of the performer, who then acts according to the instruction. When the performer clicks the "Done" button, feedback is sent to the server along with the emotional data collected by the emotion engine. The server analyzes this feedback and emotional data and notifies the prompt engineer. The prompt engineer can adjust the next instruction based on the feedback and emotional data to further improve the performer's performance.

[0223] This allows prompt engineers to quickly and accurately communicate their instructions to users, enabling flexible responses based on the user's emotional state. This improves the quality of the system's overall performance, reducing stress on performers and providing effective performance support.

[0224] The processing flow will be explained below.

[0225] Step 1:

[0226] A prompt engineer accesses the system through an interface and inputs instructions (e.g., "Prepare for the next corner").

[0227] Step 2:

[0228] The server receives instructions sent by prompt engineers and stores them in a database along with associated metadata (instruction ID, user ID, timestamp, etc.).

[0229] Step 3:

[0230] The server analyzes the stored instructions and identifies the content of the instructions and the target users, for example, identifying the performers based on the specified program and user ID.

[0231] Step 4:

[0232] The server sends instructions in real time to the target user's (performer's) device. The instructions are sent in an appropriate data format (e.g., JSON format).

[0233] Step 5:

[0234] The user's device receives the instructions sent from the server and displays them on the user interface, such as a message like "Prepare to move to the next corner."

[0235] Step 6:

[0236] The emotion engine uses the device's camera and microphone to analyze the user's facial expressions, tone of voice, movements, etc. in real time to determine the user's emotional state.

[0237] Step 7:

[0238] The user checks the instructions displayed on the device and takes the necessary action (preparing to move to the next corner) according to those instructions.

[0239] Step 8:

[0240] After responding to the instructions, the user clicks the "Done" button on the device screen, which sends feedback from the user to the server. At the same time, the feedback also includes emotional data analyzed by the emotion engine.

[0241] Step 9:

[0242] The server receives feedback and emotion data sent from the user device, analyzes the received data, and stores it in a database.

[0243] Step 10:

[0244] Based on the analysis results, the server notifies the prompt engineer of the feedback and emotional data, who then uses the feedback and emotional data to optimize the next instructions.

[0245] Step 11:

[0246] This series of processes allows prompt engineers to quickly and accurately convey instructions to users, and also enables flexible instructions to be provided according to the user's emotional state, improving the overall quality of the performance and providing effective performance support while reducing stress for performers.

[0247] Example 2

[0248] 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."

[0249] Conventional instruction systems require prompt and accurate delivery of instructions, but lack the ability to flexibly respond to the user's emotional state, which can result in reduced user performance and satisfaction. Furthermore, it is difficult to effectively utilize feedback and emotional data to adjust the next instruction. This has led to the issue of being unable to improve the overall performance of the system.

[0250] 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.

[0251] In this invention, the server includes means for receiving instructions from a prompt engineer, means for saving the received instructions in a database, means for analyzing the saved instruction data to identify the relevant user, means for sending instructions to the identified user terminal in real time, means for displaying the instructions on the user terminal, means for receiving feedback on the instructions on the user terminal, means for collecting emotion data using an emotion engine that analyzes the user's emotional state, and means for saving the feedback including the emotion data in the database. This enables prompt and accurate transmission of instructions and realizes flexible responses according to the user's emotional state. Furthermore, adjusting the content of the next instruction based on the feedback and emotion data improves the quality of overall system performance, enabling effective support while reducing user stress.

[0252] A "prompt engineer" refers to a person or role whose role is to input specific instructions into a system.

[0253] "Server" refers to a central control unit that receives, stores, analyzes, transmits, etc. instructions.

[0254] "Database" means a data storage area within a system for storing instruction data and associated metadata.

[0255] "User terminal" refers to the device used to display instructions and send feedback, such as a smartphone, tablet, or computer.

[0256] "Feedback" refers to response data sent to a server after a user completes an action in response to an instruction.

[0257] An "emotion engine" refers to a combination of software and hardware for analyzing a user's emotional state and collecting it as emotional data.

[0258] "Metadata" refers to additional information related to an instruction, such as an instruction ID, a user ID, a timestamp, etc.

[0259] "Instructions" refer to guidelines or tasks that prompt engineers provide to users through the system.

[0260] "User" refers to a person who uses the system to receive and accomplish instructions.

[0261] "Analysis" refers to the process of analyzing received data to extract specific information.

[0262] "Emotional Data" refers to data that indicates the emotional state of a user collected and analyzed by the Emotion Engine.

[0263] Overall system overview

[0264] This invention relates to a system in which a prompt engineer inputs instructions, provides the instructions to a user terminal in real time via a server, and adjusts the next instructions based on the user's emotional state. This system aims to achieve quick and accurate transmission of instructions and flexible response according to the user's emotional state, thereby improving overall performance.

[0265] Hardware and software used

[0266] 1. Web or mobile interface: Used by prompt engineers to enter instructions.

[0267] 2. Server: Receives, stores, analyzes and transmits instructions.

[0268] 3. Database: Stores instruction data and associated metadata.

[0269] 4. User device (smartphone, tablet, computer): Used to display instructions and send feedback.

[0270] 5. Emotion engine (camera, microphone): Analyzes the user's emotional state and collects it as emotional data.

[0271] Prompt engineer inputs instructions

[0272] Prompt engineers access the system through a web or mobile interface and enter specific instructions, such as "get ready to move to the next corner," which are then sent to the server.

[0273] Processing on the server

[0274] The server first receives instructions sent by the prompt engineer. Then, it stores the received instructions in a database along with related metadata (instruction ID, user ID, timestamp, etc.). After storing the instructions, the server analyzes the instructions and identifies the relevant user. Once the target user is identified, the server sends the instructions to the user device in real time.

[0275] Processing on the user terminal

[0276] The device receives instructions sent from the server in real time and displays them on the screen. After the user confirms the instructions, they actually take action based on them. After responding to the instructions, the user clicks the "Done" button on the device and sends feedback to the server. The emotion engine installed on the device also uses sensors such as a camera and microphone to analyze the user's facial expressions, tone of voice, and movements to understand the user's emotional state. The emotion engine then includes this emotional data in feedback and sends it to the server.

[0277] Processing feedback and adjusting next steps

[0278] The server analyzes the feedback and emotion data received from the user terminal and stores them in a database. This feedback information and emotion data are then notified to the prompt engineer, who uses it as a reference to adjust the next instruction based on the user's emotional state.

[0279] Specific examples

[0280] Examples from TV shows:

[0281] The prompt engineer inputs the instruction "Please prepare to move to the next segment" and sends it to the server. The server receives this instruction and sends it to the target performer's device. The performer's device displays the instruction, and the performer acts according to the instruction. When the performer clicks the "Done" button, feedback is sent to the server along with emotional data collected by the device's emotion engine. The server analyzes this feedback and emotional data and notifies the prompt engineer. The prompt engineer adjusts the next instruction based on this data.

[0282] Prompt Sentence Examples

[0283] 1. "Get ready to move to the next corner."

[0284] 2. "Please introduce the next performer."

[0285] 3. "Please be ready for rehearsal to begin."

[0286] In this way, the system enables prompt and accurate transmission of instructions and flexible responses according to the user's emotional state, improving overall system performance and providing effective support while reducing user stress.

[0287] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0288] Step 1: Prompt Engineer Enters Instructions

[0289] A user accesses a web or mobile interface and enters specific instructions (e.g., "Get ready to move around the next corner").

[0290] Input: The prompt engineer types in instructions.

[0291] Output: The entered instructions are sent to the server.

[0292] Step 2: Server receives instructions

[0293] The server receives the instructions sent by the prompt engineer.

[0294] Input: Instruction data from prompt engineer.

[0295] Output: The instruction data received.

[0296] Step 3: Server saves data

[0297] The server stores the received instruction in a database along with associated metadata (instruction ID, user ID, timestamp, etc.).

[0298] Input: Received instruction data and associated metadata.

[0299] Output: Instruction data and metadata stored in a database.

[0300] Step 4: Server analyzes instruction data

[0301] The server analyzes the stored instruction data and identifies the relevant user.

[0302] Input: Instruction data stored in the database.

[0303] Output: Identified target users.

[0304] Step 5: Server sends instructions

[0305] The server transmits instructions to the identified user's terminal in real time.

[0306] Input: Identified user and instruction data.

[0307] Output: Instruction data sent to the user terminal.

[0308] Step 6: Terminal receives and displays instructions

[0309] The terminal receives instructions sent from the server in real time and displays them on the screen.

[0310] Input: Instruction data sent from the server.

[0311] Output: The instructions displayed on the screen.

[0312] Step 7: User executes instructions

[0313] The user confirms and executes the instruction (e.g., prepares to move to the next corner).

[0314] Input: The instructions displayed on the screen.

[0315] Output: The task that was executed.

[0316] Step 8: Send feedback via device

[0317] The user clicks the "Done" button after completing the task.

[0318] The device sends "Complete" feedback and the emotion data collected by the emotion engine to the server.

[0319] Input: "Done" state and emotion data.

[0320] Output: Feedback and emotion data sent to the server.

[0321] Step 9: Collect and analyze emotion data using the emotion engine

[0322] The device uses a camera and microphone to analyze the user's facial expressions, tone of voice, movements, etc. to understand their emotional state.

[0323] Input: User facial expressions, tone of voice, movements, etc.

[0324] Output: Parsed emotion data.

[0325] Step 10: Server receives feedback and emotion data

[0326] The server receives the feedback and emotion data received from the user terminal.

[0327] Input: Feedback and emotion data sent from the user device.

[0328] Output: Received feedback and sentiment data.

[0329] Step 11: Server analyzes feedback and emotion data

[0330] The server analyzes the received feedback and emotion data and stores it in a database.

[0331] Input: Received feedback and sentiment data.

[0332] Output: Analysis results stored in a database.

[0333] Step 12: Adjust the following instructions

[0334] The server notifies the prompt engineer of the analysis results, and the prompt engineer adjusts the next instructions based on this.

[0335] Input: Feedback and sentiment data analysis results.

[0336] Output: Adjusted next instruction.

[0337] As described above, specific actions are performed at each step, enabling prompt and accurate transmission of instructions and flexible responses according to the user's emotions.

[0338] (Application example 2)

[0339] 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."

[0340] In conventional food delivery services, delivery personnel are required to respond appropriately and promptly to customers, but information about the delivery personnel's emotional state and stress level is not taken into consideration, which raises concerns about a decline in customer satisfaction and delivery efficiency. Furthermore, insufficient work efficiency and stress management for delivery personnel tend to increase employee turnover. It is necessary to solve this problem and improve customer satisfaction and work efficiency.

[0341] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving instructions from a prompt engineer, means for transmitting the received instructions to a related user terminal in real time, means for displaying the instructions on the user terminal, means for receiving feedback from the user terminal, means for analyzing the emotional state of the user using an emotion recognition engine, and means for transmitting the analyzed emotional data. This makes it possible to monitor the emotional state of delivery personnel in real time and provide appropriate instructions, thereby improving the quality of customer service and managing the stress of delivery personnel.

[0342] A "prompt engineer" is a specialized engineer whose role is to provide appropriate instructions to users and manage tasks while receiving feedback in real time.

[0343] A "user terminal" is a device for receiving and displaying instructions, and refers to an electronic device such as a smartphone or tablet.

[0344] "Real-time transmission means" refers to communication technologies and mechanisms that allow instructions to be transmitted immediately to a user terminal.

[0345] "Means for receiving feedback" refers to a mechanism for collecting responses and impressions from users and feeding them back to the system.

[0346] An "emotion recognition engine" refers to a software or hardware component that analyzes a user's facial expressions, tone of voice, etc. to identify their emotional state.

[0347] "Emotional state" refers to a psychological state related to emotions, such as stress or fatigue felt by a user.

[0348] "Analyzed Emotion Data" refers to information about a user's emotions acquired and analyzed by the emotion recognition engine.

[0349] MODE FOR CARRYING OUT THE INVENTION

[0350] This invention is a system in which a prompt engineer provides instructions and adjusts work instructions based on the user's emotional state. A specific embodiment for realizing this system is described below. This system is mainly composed of the following hardware and software:

[0351] Hardware

[0352] User devices: smartphones, tablets

[0353] Sensors: Camera, microphone

[0354] software

[0355] Mobile Application Framework: React Native

[0356] Emotion recognition engine: Affectiva, Microsoft® Azure® Emotion API

[0357] Server: Node.js, AWS (registered trademark)

[0358] Program Overview

[0359] 1. Data collection and sentiment analysis

[0360] The user device uses the smartphone's camera and microphone to collect the delivery person's facial expressions and voice in real time, and this collected data is sent to an emotion recognition engine (e.g., Affectiva, Microsoft Azure Emotion API) to analyze the delivery person's emotional state (e.g., stress, fatigue, joy).

[0361] 2. Providing Instructions

[0362] Prompt engineers input work instructions through a web interface or mobile app and send them to the server, such as "Please proceed to the next delivery destination" or "Please take note of the customer's special requests." The server receives these instructions and transmits them to the target user device in real time.

[0363] 3. Instructions and feedback

[0364] The user terminal displays the instructions received from the server on the screen and notifies the delivery person. The delivery person confirms the instructions and carries out the task. After completing the task, the delivery person presses the "Complete" button and sends the feedback to the server.

[0365] 4. Utilizing Emotional Data

[0366] The server receives the feedback sent from the user's device along with the emotional data collected and analyzed by the emotion recognition engine, allowing the prompt engineer to adjust the next instructions and support in real time according to the delivery person's emotional state.

[0367] Specific use cases

[0368] Food Delivery System

[0369] In food delivery work, delivery personnel receive instructions in real time via a smartphone app and carry out their work based on those instructions. For example, a prompt engineer inputs an instruction such as "Please head to the next delivery destination," which is sent to the delivery personnel's smartphone via the server. When the delivery personnel presses the "Done" button, feedback is sent to the server along with emotional data analyzed by the emotion engine. This data is analyzed by the prompt engineer, and if the delivery personnel is feeling stressed, instructions such as "Take a short break before your next delivery" are provided.

[0370] Prompt Sentence Examples

[0371] "Please proceed to the next delivery destination."

[0372] Pay attention to the customer's special requests

[0373] "Let's take a break for the next delivery."

[0374] In this way, collaboration between the emotion recognition engine and prompt engineers can improve delivery efficiency and customer satisfaction.

[0375] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0376] Step 1:

[0377] The user device uses the smartphone's camera and microphone to collect the delivery person's facial expressions and voice in real time. The input is the delivery person's facial image data and voice data, and the output is the collection of these data. Specifically, the system activates the user device's sensor and periodically captures images and voice.

[0378] Step 2:

[0379] The user device sends the collected facial image data and voice data to the emotion recognition engine. The input is the collected facial image data and voice data, and the output is the data sent to the emotion recognition engine. Specifically, the data is sent using the emotion recognition API and the analysis results are awaited.

[0380] Step 3:

[0381] The emotion recognition engine analyzes the received facial image data and voice data to identify the user's emotional state (e.g., stress, fatigue, joy). The input is facial image data and voice data, and the output is emotional state data. Specifically, it applies a recognition algorithm to analyze the data and generate a result.

[0382] Step 4:

[0383] The emotion recognition engine returns the analysis results to the user device. The input is emotional state data, and the output is data to be sent to the user device. Specifically, the analysis results are returned to the user device via an API.

[0384] Step 5:

[0385] Prompt engineers input instructions through a web interface or mobile app and send them to the server. The input is the prompt text (e.g., "Please proceed to the next delivery destination"), and the output is the data to be sent to the server. Specifically, instructions are input using a GUI and sent via the server's API.

[0386] Step 6:

[0387] The server receives instructions sent by the prompt engineer and transmits them to the relevant user terminal in real time. The input is the prompt text, and the output is the data to be sent to the user terminal. The specific operation is to receive the prompt text, identify the target user terminal, and transmit the data.

[0388] Step 7:

[0389] The user terminal displays the instructions received from the server and notifies the user. The input is the prompt sent from the server, and the output is the notification to the user. Specifically, the received prompt is displayed on the screen to notify the user.

[0390] Step 8:

[0391] The delivery person performs the task based on the instructions, and when complete, presses the "Done" button to send feedback. The input is the user action (clicking the "Done" button), and the output is sending feedback data to the server. Specifically, the system detects that the button has been clicked, generates feedback data, and sends it to the server.

[0392] Step 9:

[0393] The server receives the feedback sent from the user device as well as the emotion data collected by the emotion recognition engine. The input is the feedback data and emotion data, and the output is the storage and analysis of the data. Specifically, the received data is stored in a database and the necessary analysis is performed.

[0394] 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.

[0395] 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.

[0396] 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.

[0397] [Second embodiment]

[0398] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0399] 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.

[0400] 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).

[0401] 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.

[0402] 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.

[0403] 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).

[0404] 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. 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.

[0405] 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.

[0406] 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.

[0407] 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.

[0408] In the smart glasses 214, 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.

[0409] 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."

[0410] This invention is a system that supports performers in the entertainment industry by allowing them to receive instructions in real time and perform smoothly. It is realized through the cooperation of a platform, a server, user terminals, and prompt engineers.

[0411] Overall system overview

[0412] The system mainly consists of the following components:

[0413] Prompt An interface for engineers to enter instructions.

[0414] The server receives and stores the instructions and sends them to the appropriate user.

[0415] The user terminal displays the instructions and sends the feedback to the server.

[0416] Prompt engineer inputs instructions

[0417] Prompt engineers access the system through a web or mobile interface and enter specific instructions, such as "get ready to move to the next corner," which are then sent to the server.

[0418] Processing on the server

[0419] The server first receives instructions sent by the prompt engineer. It then stores the received instructions in a database along with associated metadata. After storing the instructions, the server analyzes the instructions and identifies the relevant user (performer). Once the target user is identified, the server sends the instructions to the user's device in real time.

[0420] Processing on the user terminal

[0421] The user device receives instructions sent from the server in real time and displays them on the screen. After the user confirms the instructions, they actually take action based on the instructions (for example, preparing to move to the next corner). After responding to the instructions, the user clicks the "Done" button on the device and sends feedback to the server.

[0422] Processing Feedback

[0423] The server analyzes the feedback received from the user terminal and stores it in the database, and the feedback information is notified to the prompt engineer for reference in adjusting the next instruction.

[0424] Specific examples

[0425] Examples from TV shows

[0426] The prompt engineer inputs the instruction "Please prepare to move to the next segment" and sends it to the server. The server receives this instruction and sends it to the device of the target user (performer). The performer's device displays the instruction, and the performer acts according to the instruction. When the performer clicks the "Done" button, the feedback is sent back to the server and the prompt engineer is notified. This process ensures that the entire performance is smooth and effective.

[0427] This system allows prompt engineers to quickly and accurately communicate instructions to users, improving the quality of their performance. Furthermore, it can provide flexible and effective support by adjusting subsequent instructions based on feedback.

[0428] The processing flow will be explained below.

[0429] Step 1:

[0430] A prompt engineer accesses the system through an interface and inputs instructions (e.g., "Prepare for the next corner").

[0431] Step 2:

[0432] The server receives instructions sent by prompt engineers and stores them in a database along with associated metadata (instruction ID, user ID, timestamp, etc.).

[0433] Step 3:

[0434] The server analyzes the stored instructions and identifies the content of the instructions and the target users, for example, identifying the performers based on the specified program and user ID.

[0435] Step 4:

[0436] The server sends instructions in real time to the target user's (performer's) device. The instructions are sent in an appropriate data format (e.g., JSON format).

[0437] Step 5:

[0438] The user's device receives the instructions sent from the server and displays them on the user interface, such as a message like "Prepare to move to the next corner."

[0439] Step 6:

[0440] The user checks the instructions displayed on the device and takes the necessary action (preparing to move to the next corner) according to those instructions.

[0441] Step 7:

[0442] After the user responds to the instructions, they click the "Done" button on the device screen, which sends feedback from the user to the server.

[0443] Step 8:

[0444] The feedback includes metadata such as instruction ID, user ID, and timestamp, which the server receives, analyzes, and stores in a database.

[0445] Step 9:

[0446] The server notifies the prompt engineer of the received feedback, who then adjusts the next instructions based on the feedback.

[0447] Step 10:

[0448] This series of processes ensures that prompt engineer instructions are conveyed to users quickly and accurately, maintaining excellent performance.

[0449] Example 1

[0450] 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."

[0451] Conventional systems for providing instructions to performers in the entertainment industry have suffered from delays in transmitting instructions and the cumbersome process of confirming instructions and providing feedback to performers. Furthermore, there have been cases where instructions were not properly assigned to specific users, resulting in a decline in the quality of the performance. The present invention aims to solve these problems and provide a system that allows performers to receive instructions in real time and perform smoothly.

[0452] 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.

[0453] In this invention, the server includes means for receiving instructions from a prompt engineer, means for saving the received instructions in a database, means for analyzing the saved instructions and identifying the relevant user, means for sending instructions to the identified user terminal in real time, means for displaying the instructions on the user terminal, means for sending feedback by clicking a "Done" button on the user terminal after responding to the instructions, means for receiving feedback from the user terminal and saving the feedback in a database, and means for notifying the prompt engineer of the feedback information, thereby enabling prompt and accurate transmission of instructions and flexible adjustment of instructions based on the feedback.

[0454] A "prompt engineer" is a person in the entertainment industry whose role is to input instructions to performers in real time and transmit them through the system.

[0455] "Instructions" are messages regarding actions and preparations that the prompt engineer sends to the performers.

[0456] A "database" is a system that organizes and stores data such as instructions and feedback, and makes it quickly accessible when needed.

[0457] "Analysis" is the process by which the server understands the content of the instructions received and distributes them to the appropriate user.

[0458] "User" refers to a performer who receives instructions from the system and acts accordingly.

[0459] A "user terminal" is a device, such as a smartphone, tablet, or PC, that a user uses to receive and display instructions.

[0460] "Real-time transmission means" refers to the technology and protocols for transmitting instructions to a user terminal almost instantaneously.

[0461] "Feedback" is information that notifies the server that the user has completed an action in response to an instruction.

[0462] "Notification" is a means by which the server notifies the prompt engineer of feedback information, etc.

[0463] This invention is a system for supporting performers in the entertainment industry to receive real-time instructions and perform smoothly. The system components include a server, a user terminal, and a prompt engineer.

[0464] Program processing overview

[0465] The system mainly consists of the following components:

[0466] Prompt An interface (web or mobile) for engineers to enter instructions.

[0467] The server receives, stores, parses, and transmits the instructions to the appropriate user terminal.

[0468] The user terminal receives and displays instructions in real time and sends feedback to the server after completing the action.

[0469] Server Roles and Operations

[0470] The server is built in Python, using frameworks like Flask or Django. The server has the following features:

[0471] 1. Receives an HTTP POST request from a prompt engineer and parses the instructions.

[0472] 2. Store the received instructions along with associated metadata in a PostgreSQL database.

[0473] 3. Analyze the saved instructions and identify the target user.

[0474] 4. Send instructions to the identified user device in real time via Firebase or Socket.io.

[0475] 5. Receive user feedback and store it back in the database.

[0476] 6. Use email and notification APIs to notify prompt engineers of feedback information.

[0477] Roles and operations of user terminals

[0478] User devices include a variety of devices, such as smartphones, tablets, and PCs. These devices run applications built with frameworks such as React Native and Flutter. Specific operations are as follows:

[0479] 1. Receive instructions sent from the server via a real-time communication protocol.

[0480] 2. Display the received instructions on the screen.

[0481] 3. After completing the instructions, click the "Done" button.

[0482] 4. Send the feedback to the server with an HTTP POST request.

[0483] User Roles

[0484] The user (performer) checks the instructions displayed on the device and takes action based on them. A specific example is the instruction "Please prepare to move to the next corner." After completing the action according to the instructions, the user clicks the "Done" button on the device and sends feedback to the server.

[0485] Specific examples of operation

[0486] The prompt engineer inputs the instruction "Please prepare to move to the next corner" through the web interface. The server receives this instruction and stores it in a database. It then analyzes the instruction and sends it to the user device of the relevant performer. The performer's device displays the instruction, and the performer acts according to it. When the performer clicks the "Done" button, feedback is sent to the server, which then notifies the prompt engineer of the feedback.

[0487] Examples of prompt statements

[0488] An example of a prompt sentence for a generative AI model is, "In this system, when the prompt engineer inputs the instruction 'Get ready to move to the next corner,' the server receives the instruction and sends it to the display terminal. The user (performer) checks the instruction, acts as instructed, and when completes, clicks the 'Done' button on the terminal to send feedback to the server."

[0489] With the above configuration and processing, this invention allows performers to receive instructions in real time and perform efficiently and smoothly.

[0490] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0491] Step 1:

[0492] A prompt engineer enters instructions. Using a web or mobile interface, the prompt engineer enters instructions such as "Get ready to move to the next corner." This entered instruction is sent to the server as an HTTP POST request. The input data is the textual instructions, and the output is the data sent to the server.

[0493] Step 2:

[0494] The server receives instructions from the prompt engineer. Using the Flask or Django framework, the server receives an HTTP POST request and parses the instructions. The input data is the HTTP request, and the output is the parsed text data. The server then stores the received instructions and associated metadata (such as a timestamp and the prompt engineer's ID) in a PostgreSQL database.

[0495] Step 3:

[0496] The server parses the stored instructions to identify the relevant users. It retrieves the stored database record and parses the instructions to identify the target users. This parsing uses specific rules and pattern matching. The input data is the database record, and the output is the target user's ID.

[0497] Step 4:

[0498] The server sends instructions to the identified user device in real time. Firebase or Socket.io is used to send instructions to the specified user device. Instructions are sent in JSON format and use real-time communication protocols. The input data is the user ID and the instruction content, and the output is the sent data.

[0499] Step 5:

[0500] The user device receives instructions sent from the server and displays them on the screen. The user device runs an application built with React Native or Flutter and receives instructions in real time via Firebase or Socket.io. When an instruction is received, the screen displays "Please prepare to move to the next corner." The input data is JSON data from the server, and the output is what is displayed on the device screen.

[0501] Step 6:

[0502] The user takes an action based on the instructions. For example, preparing to move to the next corner. When the action is complete, the user clicks the "Done" button on the device. The input data is the user's completion of the action, and the output is the click event of the "Done" button.

[0503] Step 7:

[0504] The user device sends the click of the "Done" button to the server as feedback. The feedback is sent as an HTTP POST request, and includes the user ID and the action completion status. The input data is the click event, and the output is an HTTP request.

[0505] Step 8:

[0506] The server receives feedback from the user device and stores it in a database. It parses the received feedback and stores it along with metadata (timestamp, user ID, etc.). The input data is an HTTP request, and the output is a database record.

[0507] Step 9:

[0508] The server notifies the prompt engineer of the saved feedback information. The prompt engineer is notified of the feedback using email API or notification API. The input data is a database record, and the output is a notification message.

[0509] (Application example 1)

[0510] 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."

[0511] Conventional factory work management systems lack the means to instantly notify robots and workers of work instructions, monitor progress in real time, and provide efficient feedback. As a result, work efficiency declines and productivity does not improve. In addition, it is difficult to accurately grasp the progress of work processes and issue the next instructions in a timely manner, making it difficult to manage the entire production line.

[0512] 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.

[0513] In this invention, the server includes a means for receiving instructions from a prompt engineer on the platform, a means for transmitting the received instructions to a related user terminal in real time, a means for displaying the instructions on the user terminal, a means for receiving feedback from the user terminal, a means for transmitting instructions to automated machinery and managing the work process, and a means for monitoring the progress of the work process based on the instructions. This allows work instructions in the factory to be quickly and accurately transmitted to robots and workers, progress to be monitored in real time, and the next instructions to be issued efficiently.

[0514] "Platform" refers to the platform through which prompt engineers input instructions and the server receives and processes the instructions.

[0515] A "prompt engineer" is a professional whose role is to input instructions into the system in real time.

[0516] "Instructions" are specific instructions for work or actions that are input by a prompt engineer and transmitted to a user terminal or automated machine device.

[0517] A "user terminal" is a device that displays received instructions and sends feedback, such as a tablet or smartphone.

[0518] "Feedback" refers to data sent back from the user terminal or robot to the server, such as reactions to executed instructions, completion reports, and progress status.

[0519] "Automated machinery" refers to robots and other automated equipment used to perform tasks automatically within a factory.

[0520] A "work process" is a series of steps for manufacturing or assembling an item according to a set procedure.

[0521] "Progress monitoring" refers to monitoring and understanding the progress of a work process in real time.

[0522] This invention applies a system that supports entertainment performers in receiving real-time instructions and performing smoothly to factory production line management. The main components of the system are realized through the cooperation of a platform, a server, user terminals (robots or worker devices), and a prompt engineer.

[0523] Overall system overview

[0524] The server receives instructions from the prompt engineer on the platform and transmits them to the relevant user device in real time. The user device displays the instructions and directs the automated machinery (robot) to perform the tasks based on the instructions. The server also monitors the progress of the work process, receives feedback from the user device, and adjusts the instructions.

[0525] Prompt engineer inputs instructions

[0526] A prompt engineer accesses the system through a web or mobile interface and enters specific work instructions, such as "Start assembly process on production line 1," which are then sent to the server.

[0527] Processing on the server

[0528] The server receives instructions sent by prompt engineers and stores them in a database along with associated metadata. After storing them, the server analyzes the instructions and identifies the specific user (robot or worker). Once the target user is identified, the server sends the instructions to the user's device in real time. The software to be used is planned to be Flask (a Python web framework).

[0529] Processing on the user terminal

[0530] The user device receives instructions sent from the server in real time and displays them on the screen. For example, a robot may receive the instruction "Please start the assembly process on production line 1." The robot will then begin work based on the instruction. Once the work is complete, the user clicks the "Done" button on the user device to send feedback to the server.

[0531] Processing Feedback

[0532] The server analyzes the feedback received from the user device and stores it in a database. Based on this feedback, the server adjusts the next instruction appropriately. For example, when it receives feedback such as "Assembly of production line 1 is completed," it notifies the prompt engineer and prepares to issue the next instruction.

[0533] Specific examples

[0534] For example, a prompt engineer inputs the instruction "Please start the assembly process on production line 1" into the system. This instruction is received by the server and sent to the robot on production line 1. The robot receives this instruction and starts the assembly process. When the work is completed, the robot reports "Assembly completed" to the system. The server receives this feedback and notifies the prompt engineer.

[0535] Prompt Sentence Examples

[0536] Prompt Engineer Instructions: Start assembly process on Production Line 1

[0537] Robot feedback: Assembly complete

[0538] This system allows work instructions within the factory to be transmitted quickly and accurately to robots and workers, monitors progress in real time, and efficiently issues subsequent instructions.

[0539] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0540] Step 1: Prompt engineer inputs instructions

[0541] A prompt engineer accesses the system through a web or mobile interface and enters specific work instructions, such as "Start assembly process on production line 1," which are then sent to the server in JSON format.

[0542] Input: prompt engineer instructions

[0543] Data processing: Convert instructions into JSON format

[0544] Output: Instruction data in JSON format

[0545] Step 2: Server receives and analyzes instructions

[0546] The server receives instructions in JSON format sent by the prompt engineer, stores them in a database, analyzes the instructions, and assigns them to specific users (robots or workers).

[0547] Input: Instruction data in JSON format

[0548] Data processing: Analysis of instruction data and saving to database

[0549] Output: Information on instruction distribution to specific users

[0550] Step 3: Server sends instructions

[0551] Based on the analysis results, the server sends instructions to the relevant user devices in real time, such as "Please start the assembly process for the robot on manufacturing line 1."

[0552] Input: Instruction distribution information for specific users

[0553] Data processing: Identifying user devices and sending real-time data

[0554] Output: Sends instruction data to the user terminal

[0555] Step 4: User terminal receives and displays instructions

[0556] The user terminal (e.g., a robot) receives instructions sent from the server in real time and displays them on its screen. The robot begins work according to the instructions. An instruction such as "Please start the assembly process on production line 1" is displayed.

[0557] Input: Instruction data from the server

[0558] Data processing: Decoding instruction data, displaying on screen

[0559] Output: On-screen instructions

[0560] Step 5: User performs task and provides feedback

[0561] The robot actually starts and completes the task based on the received instructions. When the task is completed, the user device clicks the "Done" button and sends feedback to the server. The feedback information "Assembly completed" is sent.

[0562] Input: Work progress, completion report

[0563] Data processing: Generate feedback information and send it to the server

[0564] Output: Feedback data to the server

[0565] Step 6: Server receives and analyzes feedback

[0566] The server analyzes the feedback received from the user terminal and stores it in the database. Based on the feedback information, it adjusts the next instruction and notifies the prompt engineer.

[0567] Input: Feedback data from user terminal

[0568] Data processing: Analysis of feedback data and storage in database

[0569] Output: Prompt engineer notification information

[0570] Step 7: Adjust and issue next instructions

[0571] The prompt engineer adjusts the next instructions based on the feedback notification from the server and inputs the new instructions into the system, thereby ensuring that the production line continues to operate efficiently.

[0572] Input: Feedback notification from the server

[0573] Data processing: creating new instructions

[0574] Output: System input for next instruction

[0575] 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.

[0576] This invention combines a prompt engineer's real-time instruction system, which displays, receives, and feeds back instructions via the user's terminal, with an emotion engine that recognizes the user's emotions, thereby improving the quality of instruction provision and realizing more effective performance support based on the user's emotional state.

[0577] Overall system overview

[0578] The system mainly consists of the following components:

[0579] Prompt An interface for engineers to enter instructions.

[0580] The server receives and stores the instructions and sends them to the appropriate users in real time.

[0581] The user terminal displays the instructions and sends the feedback to the server.

[0582] It is equipped with an emotion engine that recognizes the user's emotions and performs data analysis.

[0583] Prompt engineer inputs instructions

[0584] Prompt engineers access the system through a web or mobile interface and enter specific instructions, such as "get ready to move to the next corner," which are then sent to the server.

[0585] Processing on the server

[0586] The server first receives instructions sent by the prompt engineer. It then stores the received instructions in a database along with related metadata (instruction ID, user ID, timestamp, etc.). After storing the instructions, the server analyzes the instructions and identifies the corresponding user (performer). Once the target user is identified, the server sends the instructions to the user's device in real time.

[0587] Processing on the user terminal

[0588] The user device receives instructions sent from the server in real time and displays them on the screen. After the user confirms the instructions, they actually take action based on the instructions (for example, preparing to move to the next corner). After responding to the instructions, the user clicks the "Done" button on the device and sends feedback to the server.

[0589] Emotion engine processing

[0590] The emotion engine installed in the user's device uses sensors such as a camera and microphone to analyze the user's facial expressions, tone of voice, movements, etc. to grasp the user's emotional state. The emotion engine includes this emotional data in feedback and sends it to the server.

[0591] Processing feedback and adjusting next steps

[0592] The server analyzes the feedback and emotion data received from the user terminal and stores them in a database. This feedback information and emotion data are then notified to the prompt engineer, who uses it as a reference to adjust the next instruction based on the user's emotional state.

[0593] Specific examples

[0594] Examples from TV shows

[0595] The prompt engineer inputs the instruction "Please prepare to move to the next segment" and sends it to the server. The server receives this instruction and sends it to the device of the target user (performer). The instruction is displayed on the device of the performer, who then acts according to the instruction. When the performer clicks the "Done" button, feedback is sent to the server along with the emotional data collected by the emotion engine. The server analyzes this feedback and emotional data and notifies the prompt engineer. The prompt engineer can adjust the next instruction based on the feedback and emotional data to further improve the performer's performance.

[0596] This allows prompt engineers to quickly and accurately communicate their instructions to users, enabling flexible responses based on the user's emotional state. This improves the quality of the system's overall performance, reducing stress on performers and providing effective performance support.

[0597] The processing flow will be explained below.

[0598] Step 1:

[0599] A prompt engineer accesses the system through an interface and inputs instructions (e.g., "Prepare for the next corner").

[0600] Step 2:

[0601] The server receives instructions sent by prompt engineers and stores them in a database along with associated metadata (instruction ID, user ID, timestamp, etc.).

[0602] Step 3:

[0603] The server analyzes the stored instructions and identifies the content of the instructions and the target users, for example, identifying the performers based on the specified program and user ID.

[0604] Step 4:

[0605] The server sends instructions in real time to the target user's (performer's) device. The instructions are sent in an appropriate data format (e.g., JSON format).

[0606] Step 5:

[0607] The user's device receives the instructions sent from the server and displays them on the user interface, such as a message like "Prepare to move to the next corner."

[0608] Step 6:

[0609] The emotion engine uses the device's camera and microphone to analyze the user's facial expressions, tone of voice, movements, etc. in real time to determine the user's emotional state.

[0610] Step 7:

[0611] The user checks the instructions displayed on the device and takes the necessary action (preparing to move to the next corner) according to those instructions.

[0612] Step 8:

[0613] After responding to the instructions, the user clicks the "Done" button on the device screen, which sends feedback from the user to the server. At the same time, the feedback also includes emotional data analyzed by the emotion engine.

[0614] Step 9:

[0615] The server receives feedback and emotion data sent from the user device, analyzes the received data, and stores it in a database.

[0616] Step 10:

[0617] Based on the analysis results, the server notifies the prompt engineer of the feedback and emotional data, who then uses the feedback and emotional data to optimize the next instructions.

[0618] Step 11:

[0619] This series of processes allows prompt engineers to quickly and accurately convey instructions to users, and also enables flexible instructions to be provided according to the user's emotional state, improving the overall quality of the performance and providing effective performance support while reducing stress for performers.

[0620] Example 2

[0621] 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."

[0622] Conventional instruction systems require prompt and accurate delivery of instructions, but lack the ability to flexibly respond to the user's emotional state, which can result in reduced user performance and satisfaction. Furthermore, it is difficult to effectively utilize feedback and emotional data to adjust the next instruction. This has led to the issue of being unable to improve the overall performance of the system.

[0623] 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.

[0624] In this invention, the server includes means for receiving instructions from a prompt engineer, means for saving the received instructions in a database, means for analyzing the saved instruction data to identify the relevant user, means for sending instructions to the identified user terminal in real time, means for displaying the instructions on the user terminal, means for receiving feedback on the instructions on the user terminal, means for collecting emotion data using an emotion engine that analyzes the user's emotional state, and means for saving the feedback including the emotion data in the database. This enables prompt and accurate transmission of instructions and realizes flexible responses according to the user's emotional state. Furthermore, adjusting the content of the next instruction based on the feedback and emotion data improves the quality of overall system performance, enabling effective support while reducing user stress.

[0625] A "prompt engineer" refers to a person or role whose role is to input specific instructions into a system.

[0626] "Server" refers to a central control unit that receives, stores, analyzes, transmits, etc. instructions.

[0627] "Database" means a data storage area within a system for storing instruction data and associated metadata.

[0628] "User terminal" refers to the device used to display instructions and send feedback, such as a smartphone, tablet, or computer.

[0629] "Feedback" refers to response data sent to a server after a user completes an action in response to an instruction.

[0630] An "emotion engine" refers to a combination of software and hardware for analyzing a user's emotional state and collecting it as emotional data.

[0631] "Metadata" refers to additional information related to an instruction, such as an instruction ID, a user ID, a timestamp, etc.

[0632] "Instructions" refer to guidelines or tasks that prompt engineers provide to users through the system.

[0633] "User" refers to a person who uses the system to receive and accomplish instructions.

[0634] "Analysis" refers to the process of analyzing received data to extract specific information.

[0635] "Emotional Data" refers to data that indicates the emotional state of a user collected and analyzed by the Emotion Engine.

[0636] Overall system overview

[0637] This invention relates to a system in which a prompt engineer inputs instructions, provides the instructions to a user terminal in real time via a server, and adjusts the next instructions based on the user's emotional state. This system aims to achieve quick and accurate transmission of instructions and flexible response according to the user's emotional state, thereby improving overall performance.

[0638] Hardware and software used

[0639] 1. Web or mobile interface: Used by prompt engineers to enter instructions.

[0640] 2. Server: Receives, stores, analyzes and transmits instructions.

[0641] 3. Database: Stores instruction data and associated metadata.

[0642] 4. User device (smartphone, tablet, computer): Used to display instructions and send feedback.

[0643] 5. Emotion engine (camera, microphone): Analyzes the user's emotional state and collects it as emotional data.

[0644] Prompt engineer inputs instructions

[0645] Prompt engineers access the system through a web or mobile interface and enter specific instructions, such as "get ready to move to the next corner," which are then sent to the server.

[0646] Processing on the server

[0647] The server first receives instructions sent by the prompt engineer. Then, it stores the received instructions in a database along with related metadata (instruction ID, user ID, timestamp, etc.). After storing the instructions, the server analyzes the instructions and identifies the relevant user. Once the target user is identified, the server sends the instructions to the user device in real time.

[0648] Processing on the user terminal

[0649] The device receives instructions sent from the server in real time and displays them on the screen. After the user confirms the instructions, they actually take action based on them. After responding to the instructions, the user clicks the "Done" button on the device and sends feedback to the server. The emotion engine installed on the device also uses sensors such as a camera and microphone to analyze the user's facial expressions, tone of voice, and movements to understand the user's emotional state. The emotion engine then includes this emotional data in feedback and sends it to the server.

[0650] Processing feedback and adjusting next steps

[0651] The server analyzes the feedback and emotion data received from the user terminal and stores them in a database. This feedback information and emotion data are then notified to the prompt engineer, who uses it as a reference to adjust the next instruction based on the user's emotional state.

[0652] Specific examples

[0653] Examples from TV shows:

[0654] The prompt engineer inputs the instruction "Please prepare to move to the next segment" and sends it to the server. The server receives this instruction and sends it to the target performer's device. The performer's device displays the instruction, and the performer acts according to the instruction. When the performer clicks the "Done" button, feedback is sent to the server along with emotional data collected by the device's emotion engine. The server analyzes this feedback and emotional data and notifies the prompt engineer. The prompt engineer adjusts the next instruction based on this data.

[0655] Prompt Sentence Examples

[0656] 1. "Get ready to move to the next corner."

[0657] 2. "Please introduce the next performer."

[0658] 3. "Please be ready for rehearsal to begin."

[0659] In this way, the system enables prompt and accurate transmission of instructions and flexible responses according to the user's emotional state, improving overall system performance and providing effective support while reducing user stress.

[0660] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0661] Step 1: Prompt Engineer Enters Instructions

[0662] A user accesses a web or mobile interface and enters specific instructions (e.g., "Get ready to move around the next corner").

[0663] Input: The prompt engineer types in instructions.

[0664] Output: The entered instructions are sent to the server.

[0665] Step 2: Server receives instructions

[0666] The server receives the instructions sent by the prompt engineer.

[0667] Input: Instruction data from prompt engineer.

[0668] Output: The instruction data received.

[0669] Step 3: Server saves data

[0670] The server stores the received instruction in a database along with associated metadata (instruction ID, user ID, timestamp, etc.).

[0671] Input: Received instruction data and associated metadata.

[0672] Output: Instruction data and metadata stored in a database.

[0673] Step 4: Server analyzes instruction data

[0674] The server analyzes the stored instruction data and identifies the relevant user.

[0675] Input: Instruction data stored in the database.

[0676] Output: Identified target users.

[0677] Step 5: Server sends instructions

[0678] The server transmits instructions to the identified user's terminal in real time.

[0679] Input: Identified user and instruction data.

[0680] Output: Instruction data sent to the user terminal.

[0681] Step 6: Terminal receives and displays instructions

[0682] The terminal receives instructions sent from the server in real time and displays them on the screen.

[0683] Input: Instruction data sent from the server.

[0684] Output: The instructions displayed on the screen.

[0685] Step 7: User executes instructions

[0686] The user confirms and executes the instruction (e.g., prepares to move to the next corner).

[0687] Input: The instructions displayed on the screen.

[0688] Output: The task that was executed.

[0689] Step 8: Send feedback via device

[0690] The user clicks the "Done" button after completing the task.

[0691] The device sends "Complete" feedback and the emotion data collected by the emotion engine to the server.

[0692] Input: "Done" state and emotion data.

[0693] Output: Feedback and emotion data sent to the server.

[0694] Step 9: Collect and analyze emotion data using the emotion engine

[0695] The device uses a camera and microphone to analyze the user's facial expressions, tone of voice, movements, etc. to understand their emotional state.

[0696] Input: User facial expressions, tone of voice, movements, etc.

[0697] Output: Parsed emotion data.

[0698] Step 10: Server receives feedback and emotion data

[0699] The server receives the feedback and emotion data received from the user terminal.

[0700] Input: Feedback and emotion data sent from the user device.

[0701] Output: Received feedback and sentiment data.

[0702] Step 11: Server analyzes feedback and emotion data

[0703] The server analyzes the received feedback and emotion data and stores it in a database.

[0704] Input: Received feedback and sentiment data.

[0705] Output: Analysis results stored in a database.

[0706] Step 12: Adjust the following instructions

[0707] The server notifies the prompt engineer of the analysis results, and the prompt engineer adjusts the next instructions based on this.

[0708] Input: Feedback and sentiment data analysis results.

[0709] Output: Adjusted next instruction.

[0710] As described above, specific actions are performed at each step, enabling prompt and accurate transmission of instructions and flexible responses according to the user's emotions.

[0711] (Application example 2)

[0712] 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."

[0713] In conventional food delivery services, delivery personnel are required to respond appropriately and promptly to customers, but information about the delivery personnel's emotional state and stress level is not taken into consideration, which raises concerns about a decline in customer satisfaction and delivery efficiency. Furthermore, insufficient work efficiency and stress management for delivery personnel tend to increase employee turnover. It is necessary to solve this problem and improve customer satisfaction and work efficiency.

[0714] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving instructions from a prompt engineer, means for transmitting the received instructions to a related user terminal in real time, means for displaying the instructions on the user terminal, means for receiving feedback from the user terminal, means for analyzing the emotional state of the user using an emotion recognition engine, and means for transmitting the analyzed emotional data. This makes it possible to monitor the emotional state of delivery personnel in real time and provide appropriate instructions, thereby improving the quality of customer service and managing the stress of delivery personnel.

[0715] A "prompt engineer" is a specialized engineer whose role is to provide appropriate instructions to users and manage tasks while receiving feedback in real time.

[0716] A "user terminal" is a device for receiving and displaying instructions, and refers to an electronic device such as a smartphone or tablet.

[0717] "Real-time transmission means" refers to communication technologies and mechanisms that allow instructions to be transmitted immediately to a user terminal.

[0718] "Means for receiving feedback" refers to a mechanism for collecting responses and impressions from users and feeding them back to the system.

[0719] An "emotion recognition engine" refers to a software or hardware component that analyzes a user's facial expressions, tone of voice, etc. to identify their emotional state.

[0720] "Emotional state" refers to a psychological state related to emotions, such as stress or fatigue felt by a user.

[0721] "Analyzed Emotion Data" refers to information about a user's emotions acquired and analyzed by the emotion recognition engine.

[0722] MODE FOR CARRYING OUT THE INVENTION

[0723] This invention is a system in which a prompt engineer provides instructions and adjusts work instructions based on the user's emotional state. A specific embodiment for realizing this system is described below. This system is mainly composed of the following hardware and software:

[0724] Hardware

[0725] User devices: smartphones, tablets

[0726] Sensors: Camera, microphone

[0727] software

[0728] Mobile Application Framework: React Native

[0729] Emotion recognition engine: Affectiva, Microsoft Azure Emotion API

[0730] Server: Node.js, AWS

[0731] Program Overview

[0732] 1. Data collection and sentiment analysis

[0733] The user device uses the smartphone's camera and microphone to collect the delivery person's facial expressions and voice in real time, and this collected data is sent to an emotion recognition engine (e.g., Affectiva, Microsoft Azure Emotion API) to analyze the delivery person's emotional state (e.g., stress, fatigue, joy).

[0734] 2. Providing Instructions

[0735] Prompt engineers input work instructions through a web interface or mobile app and send them to the server, such as "Please proceed to the next delivery destination" or "Please take note of the customer's special requests." The server receives these instructions and transmits them to the target user device in real time.

[0736] 3. Instructions and feedback

[0737] The user terminal displays the instructions received from the server on the screen and notifies the delivery person. The delivery person confirms the instructions and carries out the task. After completing the task, the delivery person presses the "Complete" button and sends the feedback to the server.

[0738] 4. Utilizing Emotional Data

[0739] The server receives the feedback sent from the user's device along with the emotional data collected and analyzed by the emotion recognition engine, allowing the prompt engineer to adjust the next instructions and support in real time according to the delivery person's emotional state.

[0740] Specific use cases

[0741] Food Delivery System

[0742] In food delivery work, delivery personnel receive instructions in real time via a smartphone app and carry out their work based on those instructions. For example, a prompt engineer inputs an instruction such as "Please head to the next delivery destination," which is sent to the delivery personnel's smartphone via the server. When the delivery personnel presses the "Done" button, feedback is sent to the server along with emotional data analyzed by the emotion engine. This data is analyzed by the prompt engineer, and if the delivery personnel is feeling stressed, instructions such as "Take a short break before your next delivery" are provided.

[0743] Prompt Sentence Examples

[0744] "Please proceed to the next delivery destination."

[0745] Pay attention to the customer's special requests

[0746] "Let's take a break for the next delivery."

[0747] In this way, collaboration between the emotion recognition engine and prompt engineers can improve delivery efficiency and customer satisfaction.

[0748] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0749] Step 1:

[0750] The user device uses the smartphone's camera and microphone to collect the delivery person's facial expressions and voice in real time. The input is the delivery person's facial image data and voice data, and the output is the collection of these data. Specifically, the system activates the user device's sensor and periodically captures images and voice.

[0751] Step 2:

[0752] The user device sends the collected facial image data and voice data to the emotion recognition engine. The input is the collected facial image data and voice data, and the output is the data sent to the emotion recognition engine. Specifically, the data is sent using the emotion recognition API and the analysis results are awaited.

[0753] Step 3:

[0754] The emotion recognition engine analyzes the received facial image data and voice data to identify the user's emotional state (e.g., stress, fatigue, joy). The input is facial image data and voice data, and the output is emotional state data. Specifically, it applies a recognition algorithm to analyze the data and generate a result.

[0755] Step 4:

[0756] The emotion recognition engine returns the analysis results to the user device. The input is emotional state data, and the output is data to be sent to the user device. Specifically, the analysis results are returned to the user device via an API.

[0757] Step 5:

[0758] Prompt engineers input instructions through a web interface or mobile app and send them to the server. The input is the prompt text (e.g., "Please proceed to the next delivery destination"), and the output is the data to be sent to the server. Specifically, instructions are input using a GUI and sent via the server's API.

[0759] Step 6:

[0760] The server receives instructions sent by the prompt engineer and transmits them to the relevant user terminal in real time. The input is the prompt text, and the output is the data to be sent to the user terminal. The specific operation is to receive the prompt text, identify the target user terminal, and transmit the data.

[0761] Step 7:

[0762] The user terminal displays the instructions received from the server and notifies the user. The input is the prompt sent from the server, and the output is the notification to the user. Specifically, the received prompt is displayed on the screen to notify the user.

[0763] Step 8:

[0764] The delivery person performs the task based on the instructions, and when complete, presses the "Done" button to send feedback. The input is the user action (clicking the "Done" button), and the output is sending feedback data to the server. Specifically, the system detects that the button has been clicked, generates feedback data, and sends it to the server.

[0765] Step 9:

[0766] The server receives the feedback sent from the user device as well as the emotion data collected by the emotion recognition engine. The input is the feedback data and emotion data, and the output is the storage and analysis of the data. Specifically, the received data is stored in a database and the necessary analysis is performed.

[0767] 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.

[0768] 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.

[0769] 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.

[0770] [Third embodiment]

[0771] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0772] 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.

[0773] 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).

[0774] 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.

[0775] 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.

[0776] 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).

[0777] 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. 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.

[0778] 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.

[0779] 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.

[0780] 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.

[0781] 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.

[0782] 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."

[0783] This invention is a system that supports performers in the entertainment industry by allowing them to receive instructions in real time and perform smoothly. It is realized through the cooperation of a platform, a server, user terminals, and prompt engineers.

[0784] Overall system overview

[0785] The system mainly consists of the following components:

[0786] Prompt An interface for engineers to enter instructions.

[0787] The server receives and stores the instructions and sends them to the appropriate user.

[0788] The user terminal displays the instructions and sends the feedback to the server.

[0789] Prompt engineer inputs instructions

[0790] Prompt engineers access the system through a web or mobile interface and enter specific instructions, such as "get ready to move to the next corner," which are then sent to the server.

[0791] Processing on the server

[0792] The server first receives instructions sent by the prompt engineer. It then stores the received instructions in a database along with associated metadata. After storing the instructions, the server analyzes the instructions and identifies the relevant user (performer). Once the target user is identified, the server sends the instructions to the user's device in real time.

[0793] Processing on the user terminal

[0794] The user device receives instructions sent from the server in real time and displays them on the screen. After the user confirms the instructions, they actually take action based on the instructions (for example, preparing to move to the next corner). After responding to the instructions, the user clicks the "Done" button on the device and sends feedback to the server.

[0795] Processing Feedback

[0796] The server analyzes the feedback received from the user terminal and stores it in the database, and the feedback information is notified to the prompt engineer for reference in adjusting the next instruction.

[0797] Specific examples

[0798] Examples from TV shows

[0799] The prompt engineer inputs the instruction "Please prepare to move to the next segment" and sends it to the server. The server receives this instruction and sends it to the device of the target user (performer). The performer's device displays the instruction, and the performer acts according to the instruction. When the performer clicks the "Done" button, the feedback is sent back to the server and the prompt engineer is notified. This process ensures that the entire performance is smooth and effective.

[0800] This system allows prompt engineers to quickly and accurately communicate instructions to users, improving the quality of their performance. Furthermore, it can provide flexible and effective support by adjusting subsequent instructions based on feedback.

[0801] The processing flow will be explained below.

[0802] Step 1:

[0803] A prompt engineer accesses the system through an interface and inputs instructions (e.g., "Prepare for the next corner").

[0804] Step 2:

[0805] The server receives instructions sent by prompt engineers and stores them in a database along with associated metadata (instruction ID, user ID, timestamp, etc.).

[0806] Step 3:

[0807] The server analyzes the stored instructions and identifies the content of the instructions and the target users, for example, identifying the performers based on the specified program and user ID.

[0808] Step 4:

[0809] The server sends instructions in real time to the target user's (performer's) device. The instructions are sent in an appropriate data format (e.g., JSON format).

[0810] Step 5:

[0811] The user's device receives the instructions sent from the server and displays them on the user interface, such as a message like "Prepare to move to the next corner."

[0812] Step 6:

[0813] The user checks the instructions displayed on the device and takes the necessary action (preparing to move to the next corner) according to those instructions.

[0814] Step 7:

[0815] After the user responds to the instructions, they click the "Done" button on the device screen, which sends feedback from the user to the server.

[0816] Step 8:

[0817] The feedback includes metadata such as instruction ID, user ID, and timestamp, which the server receives, analyzes, and stores in a database.

[0818] Step 9:

[0819] The server notifies the prompt engineer of the received feedback, who then adjusts the next instructions based on the feedback.

[0820] Step 10:

[0821] This series of processes ensures that prompt engineer instructions are conveyed to users quickly and accurately, maintaining excellent performance.

[0822] Example 1

[0823] 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."

[0824] Conventional systems for providing instructions to performers in the entertainment industry have suffered from delays in transmitting instructions and the cumbersome process of confirming instructions and providing feedback to performers. Furthermore, there have been cases where instructions were not properly assigned to specific users, resulting in a decline in the quality of the performance. The present invention aims to solve these problems and provide a system that allows performers to receive instructions in real time and perform smoothly.

[0825] 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.

[0826] In this invention, the server includes means for receiving instructions from a prompt engineer, means for saving the received instructions in a database, means for analyzing the saved instructions and identifying the relevant user, means for sending instructions to the identified user terminal in real time, means for displaying the instructions on the user terminal, means for sending feedback by clicking a "Done" button on the user terminal after responding to the instructions, means for receiving feedback from the user terminal and saving the feedback in a database, and means for notifying the prompt engineer of the feedback information, thereby enabling prompt and accurate transmission of instructions and flexible adjustment of instructions based on the feedback.

[0827] A "prompt engineer" is a person in the entertainment industry whose role is to input instructions to performers in real time and transmit them through the system.

[0828] "Instructions" are messages regarding actions and preparations that the prompt engineer sends to the performers.

[0829] A "database" is a system that organizes and stores data such as instructions and feedback, and makes it quickly accessible when needed.

[0830] "Analysis" is the process by which the server understands the content of the instructions received and distributes them to the appropriate user.

[0831] "User" refers to a performer who receives instructions from the system and acts accordingly.

[0832] A "user terminal" is a device, such as a smartphone, tablet, or PC, that a user uses to receive and display instructions.

[0833] "Real-time transmission means" refers to the technology and protocols for transmitting instructions to a user terminal almost instantaneously.

[0834] "Feedback" is information that notifies the server that the user has completed an action in response to an instruction.

[0835] "Notification" is a means by which the server notifies the prompt engineer of feedback information, etc.

[0836] This invention is a system for supporting performers in the entertainment industry to receive real-time instructions and perform smoothly. The system components include a server, a user terminal, and a prompt engineer.

[0837] Program processing overview

[0838] The system mainly consists of the following components:

[0839] Prompt An interface (web or mobile) for engineers to enter instructions.

[0840] The server receives, stores, parses, and transmits the instructions to the appropriate user terminal.

[0841] The user terminal receives and displays instructions in real time and sends feedback to the server after completing the action.

[0842] Server Roles and Operations

[0843] The server is built in Python, using frameworks like Flask or Django. The server has the following features:

[0844] 1. Receives an HTTP POST request from a prompt engineer and parses the instructions.

[0845] 2. Store the received instructions along with associated metadata in a PostgreSQL database.

[0846] 3. Analyze the saved instructions and identify the target user.

[0847] 4. Send instructions to the identified user device in real time via Firebase or Socket.io.

[0848] 5. Receive user feedback and store it back in the database.

[0849] 6. Use email and notification APIs to notify prompt engineers of feedback information.

[0850] Roles and operations of user terminals

[0851] User devices include a variety of devices, such as smartphones, tablets, and PCs. These devices run applications built with frameworks such as React Native and Flutter. Specific operations are as follows:

[0852] 1. Receive instructions sent from the server via a real-time communication protocol.

[0853] 2. Display the received instructions on the screen.

[0854] 3. After completing the instructions, click the "Done" button.

[0855] 4. Send the feedback to the server with an HTTP POST request.

[0856] User Roles

[0857] The user (performer) checks the instructions displayed on the device and takes action based on them. A specific example is the instruction "Please prepare to move to the next corner." After completing the action according to the instructions, the user clicks the "Done" button on the device and sends feedback to the server.

[0858] Specific examples of operation

[0859] The prompt engineer inputs the instruction "Please prepare to move to the next corner" through the web interface. The server receives this instruction and stores it in a database. It then analyzes the instruction and sends it to the user device of the relevant performer. The performer's device displays the instruction, and the performer acts according to it. When the performer clicks the "Done" button, feedback is sent to the server, which then notifies the prompt engineer of the feedback.

[0860] Examples of prompt statements

[0861] An example of a prompt sentence for a generative AI model is, "In this system, when the prompt engineer inputs the instruction 'Get ready to move to the next corner,' the server receives the instruction and sends it to the display terminal. The user (performer) checks the instruction, acts as instructed, and when completes, clicks the 'Done' button on the terminal to send feedback to the server."

[0862] With the above configuration and processing, this invention allows performers to receive instructions in real time and perform efficiently and smoothly.

[0863] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0864] Step 1:

[0865] A prompt engineer enters instructions. Using a web or mobile interface, the prompt engineer enters instructions such as "Get ready to move to the next corner." This entered instruction is sent to the server as an HTTP POST request. The input data is the textual instructions, and the output is the data sent to the server.

[0866] Step 2:

[0867] The server receives instructions from the prompt engineer. Using the Flask or Django framework, the server receives an HTTP POST request and parses the instructions. The input data is the HTTP request, and the output is the parsed text data. The server then stores the received instructions and associated metadata (such as a timestamp and the prompt engineer's ID) in a PostgreSQL database.

[0868] Step 3:

[0869] The server parses the stored instructions to identify the relevant users. It retrieves the stored database record and parses the instructions to identify the target users. This parsing uses specific rules and pattern matching. The input data is the database record, and the output is the target user's ID.

[0870] Step 4:

[0871] The server sends instructions to the identified user device in real time. Firebase or Socket.io is used to send instructions to the specified user device. Instructions are sent in JSON format and use real-time communication protocols. The input data is the user ID and the instruction content, and the output is the sent data.

[0872] Step 5:

[0873] The user device receives instructions sent from the server and displays them on the screen. The user device runs an application built with React Native or Flutter and receives instructions in real time via Firebase or Socket.io. When an instruction is received, the screen displays "Please prepare to move to the next corner." The input data is JSON data from the server, and the output is what is displayed on the device screen.

[0874] Step 6:

[0875] The user takes an action based on the instructions. For example, preparing to move to the next corner. When the action is complete, the user clicks the "Done" button on the device. The input data is the user's completion of the action, and the output is the click event of the "Done" button.

[0876] Step 7:

[0877] The user device sends the click of the "Done" button to the server as feedback. The feedback is sent as an HTTP POST request, and includes the user ID and the action completion status. The input data is the click event, and the output is an HTTP request.

[0878] Step 8:

[0879] The server receives feedback from the user device and stores it in a database. It parses the received feedback and stores it along with metadata (timestamp, user ID, etc.). The input data is an HTTP request, and the output is a database record.

[0880] Step 9:

[0881] The server notifies the prompt engineer of the saved feedback information. The prompt engineer is notified of the feedback using email API or notification API. The input data is a database record, and the output is a notification message.

[0882] (Application example 1)

[0883] 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."

[0884] Conventional factory work management systems lack the means to instantly notify robots and workers of work instructions, monitor progress in real time, and provide efficient feedback. As a result, work efficiency declines and productivity does not improve. In addition, it is difficult to accurately grasp the progress of work processes and issue the next instructions in a timely manner, making it difficult to manage the entire production line.

[0885] 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.

[0886] In this invention, the server includes a means for receiving instructions from a prompt engineer on the platform, a means for transmitting the received instructions to a related user terminal in real time, a means for displaying the instructions on the user terminal, a means for receiving feedback from the user terminal, a means for transmitting instructions to automated machinery and managing the work process, and a means for monitoring the progress of the work process based on the instructions. This allows work instructions in the factory to be quickly and accurately transmitted to robots and workers, progress to be monitored in real time, and the next instructions to be issued efficiently.

[0887] "Platform" refers to the platform through which prompt engineers input instructions and the server receives and processes the instructions.

[0888] A "prompt engineer" is a professional whose role is to input instructions into the system in real time.

[0889] "Instructions" are specific instructions for work or actions that are input by a prompt engineer and transmitted to a user terminal or automated machine device.

[0890] A "user terminal" is a device that displays received instructions and sends feedback, such as a tablet or smartphone.

[0891] "Feedback" refers to data sent back from the user terminal or robot to the server, such as reactions to executed instructions, completion reports, and progress status.

[0892] "Automated machinery" refers to robots and other automated equipment used to perform tasks automatically within a factory.

[0893] A "work process" is a series of steps for manufacturing or assembling an item according to a set procedure.

[0894] "Progress monitoring" refers to monitoring and understanding the progress of a work process in real time.

[0895] This invention applies a system that supports entertainment performers in receiving real-time instructions and performing smoothly to factory production line management. The main components of the system are realized through the cooperation of a platform, a server, user terminals (robots or worker devices), and a prompt engineer.

[0896] Overall system overview

[0897] The server receives instructions from the prompt engineer on the platform and transmits them to the relevant user device in real time. The user device displays the instructions and directs the automated machinery (robot) to perform the tasks based on the instructions. The server also monitors the progress of the work process, receives feedback from the user device, and adjusts the instructions.

[0898] Prompt engineer inputs instructions

[0899] A prompt engineer accesses the system through a web or mobile interface and enters specific work instructions, such as "Start assembly process on production line 1," which are then sent to the server.

[0900] Processing on the server

[0901] The server receives instructions sent by prompt engineers and stores them in a database along with associated metadata. After storing them, the server analyzes the instructions and identifies the specific user (robot or worker). Once the target user is identified, the server sends the instructions to the user's device in real time. The software to be used is planned to be Flask (a Python web framework).

[0902] Processing on the user terminal

[0903] The user device receives instructions sent from the server in real time and displays them on the screen. For example, a robot may receive the instruction "Please start the assembly process on production line 1." The robot will then begin work based on the instruction. Once the work is complete, the user clicks the "Done" button on the user device to send feedback to the server.

[0904] Processing Feedback

[0905] The server analyzes the feedback received from the user device and stores it in a database. Based on this feedback, the server adjusts the next instruction appropriately. For example, when it receives feedback such as "Assembly of production line 1 is completed," it notifies the prompt engineer and prepares to issue the next instruction.

[0906] Specific examples

[0907] For example, a prompt engineer inputs the instruction "Please start the assembly process on production line 1" into the system. This instruction is received by the server and sent to the robot on production line 1. The robot receives this instruction and starts the assembly process. When the work is completed, the robot reports "Assembly completed" to the system. The server receives this feedback and notifies the prompt engineer.

[0908] Prompt Sentence Examples

[0909] Prompt Engineer Instructions: Start assembly process on Production Line 1

[0910] Robot feedback: Assembly complete

[0911] This system allows work instructions within the factory to be transmitted quickly and accurately to robots and workers, monitors progress in real time, and efficiently issues subsequent instructions.

[0912] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0913] Step 1: Prompt engineer inputs instructions

[0914] A prompt engineer accesses the system through a web or mobile interface and enters specific work instructions, such as "Start assembly process on production line 1," which are then sent to the server in JSON format.

[0915] Input: prompt engineer instructions

[0916] Data processing: Convert instructions into JSON format

[0917] Output: Instruction data in JSON format

[0918] Step 2: Server receives and analyzes instructions

[0919] The server receives instructions in JSON format sent by the prompt engineer, stores them in a database, analyzes the instructions, and assigns them to specific users (robots or workers).

[0920] Input: Instruction data in JSON format

[0921] Data processing: Analysis of instruction data and saving to database

[0922] Output: Information on instruction distribution to specific users

[0923] Step 3: Server sends instructions

[0924] Based on the analysis results, the server sends instructions to the relevant user devices in real time, such as "Please start the assembly process for the robot on manufacturing line 1."

[0925] Input: Instruction distribution information for specific users

[0926] Data processing: Identifying user devices and sending real-time data

[0927] Output: Sends instruction data to the user terminal

[0928] Step 4: User terminal receives and displays instructions

[0929] The user terminal (e.g., a robot) receives instructions sent from the server in real time and displays them on its screen. The robot begins work according to the instructions. An instruction such as "Please start the assembly process on production line 1" is displayed.

[0930] Input: Instruction data from the server

[0931] Data processing: Decoding instruction data, displaying on screen

[0932] Output: On-screen instructions

[0933] Step 5: User performs task and provides feedback

[0934] The robot actually starts and completes the task based on the received instructions. When the task is completed, the user device clicks the "Done" button and sends feedback to the server. The feedback information "Assembly completed" is sent.

[0935] Input: Work progress, completion report

[0936] Data processing: Generate feedback information and send it to the server

[0937] Output: Feedback data to the server

[0938] Step 6: Server receives and analyzes feedback

[0939] The server analyzes the feedback received from the user terminal and stores it in the database. Based on the feedback information, it adjusts the next instruction and notifies the prompt engineer.

[0940] Input: Feedback data from user terminal

[0941] Data processing: Analysis of feedback data and storage in database

[0942] Output: Prompt engineer notification information

[0943] Step 7: Adjust and issue next instructions

[0944] The prompt engineer adjusts the next instructions based on the feedback notification from the server and inputs the new instructions into the system, thereby ensuring that the production line continues to operate efficiently.

[0945] Input: Feedback notification from the server

[0946] Data processing: creating new instructions

[0947] Output: System input for next instruction

[0948] 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.

[0949] This invention combines a prompt engineer's real-time instruction system, which displays, receives, and feeds back instructions via the user's terminal, with an emotion engine that recognizes the user's emotions, thereby improving the quality of instruction provision and realizing more effective performance support based on the user's emotional state.

[0950] Overall system overview

[0951] The system mainly consists of the following components:

[0952] Prompt An interface for engineers to enter instructions.

[0953] The server receives and stores the instructions and sends them to the appropriate users in real time.

[0954] The user terminal displays the instructions and sends the feedback to the server.

[0955] It is equipped with an emotion engine that recognizes the user's emotions and performs data analysis.

[0956] Prompt engineer inputs instructions

[0957] Prompt engineers access the system through a web or mobile interface and enter specific instructions, such as "get ready to move to the next corner," which are then sent to the server.

[0958] Processing on the server

[0959] The server first receives instructions sent by the prompt engineer. It then stores the received instructions in a database along with related metadata (instruction ID, user ID, timestamp, etc.). After storing the instructions, the server analyzes the instructions and identifies the corresponding user (performer). Once the target user is identified, the server sends the instructions to the user's device in real time.

[0960] Processing on the user terminal

[0961] The user device receives instructions sent from the server in real time and displays them on the screen. After the user confirms the instructions, they actually take action based on the instructions (for example, preparing to move to the next corner). After responding to the instructions, the user clicks the "Done" button on the device and sends feedback to the server.

[0962] Emotion engine processing

[0963] The emotion engine installed in the user's device uses sensors such as a camera and microphone to analyze the user's facial expressions, tone of voice, movements, etc. to grasp the user's emotional state. The emotion engine includes this emotional data in feedback and sends it to the server.

[0964] Processing feedback and adjusting next steps

[0965] The server analyzes the feedback and emotion data received from the user terminal and stores them in a database. This feedback information and emotion data are then notified to the prompt engineer, who uses it as a reference to adjust the next instruction based on the user's emotional state.

[0966] Specific examples

[0967] Examples from TV shows

[0968] The prompt engineer inputs the instruction "Please prepare to move to the next segment" and sends it to the server. The server receives this instruction and sends it to the device of the target user (performer). The instruction is displayed on the device of the performer, who then acts according to the instruction. When the performer clicks the "Done" button, feedback is sent to the server along with the emotional data collected by the emotion engine. The server analyzes this feedback and emotional data and notifies the prompt engineer. The prompt engineer can adjust the next instruction based on the feedback and emotional data to further improve the performer's performance.

[0969] This allows prompt engineers to quickly and accurately communicate their instructions to users, enabling flexible responses based on the user's emotional state. This improves the quality of the system's overall performance, reducing stress on performers and providing effective performance support.

[0970] The processing flow will be explained below.

[0971] Step 1:

[0972] A prompt engineer accesses the system through an interface and inputs instructions (e.g., "Prepare for the next corner").

[0973] Step 2:

[0974] The server receives instructions sent by prompt engineers and stores them in a database along with associated metadata (instruction ID, user ID, timestamp, etc.).

[0975] Step 3:

[0976] The server analyzes the stored instructions and identifies the content of the instructions and the target users, for example, identifying the performers based on the specified program and user ID.

[0977] Step 4:

[0978] The server sends instructions in real time to the target user's (performer's) device. The instructions are sent in an appropriate data format (e.g., JSON format).

[0979] Step 5:

[0980] The user's device receives the instructions sent from the server and displays them on the user interface, such as a message like "Prepare to move to the next corner."

[0981] Step 6:

[0982] The emotion engine uses the device's camera and microphone to analyze the user's facial expressions, tone of voice, movements, etc. in real time to determine the user's emotional state.

[0983] Step 7:

[0984] The user checks the instructions displayed on the device and takes the necessary action (preparing to move to the next corner) according to those instructions.

[0985] Step 8:

[0986] After responding to the instructions, the user clicks the "Done" button on the device screen, which sends feedback from the user to the server. At the same time, the feedback also includes emotional data analyzed by the emotion engine.

[0987] Step 9:

[0988] The server receives feedback and emotion data sent from the user device, analyzes the received data, and stores it in a database.

[0989] Step 10:

[0990] Based on the analysis results, the server notifies the prompt engineer of the feedback and emotional data, who then uses the feedback and emotional data to optimize the next instructions.

[0991] Step 11:

[0992] This series of processes allows prompt engineers to quickly and accurately convey instructions to users, and also enables flexible instructions to be provided according to the user's emotional state, improving the overall quality of the performance and providing effective performance support while reducing stress for performers.

[0993] Example 2

[0994] 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."

[0995] Conventional instruction systems require prompt and accurate delivery of instructions, but lack the ability to flexibly respond to the user's emotional state, which can result in reduced user performance and satisfaction. Furthermore, it is difficult to effectively utilize feedback and emotional data to adjust the next instruction. This has led to the issue of being unable to improve the overall performance of the system.

[0996] 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.

[0997] In this invention, the server includes means for receiving instructions from a prompt engineer, means for saving the received instructions in a database, means for analyzing the saved instruction data to identify the relevant user, means for sending instructions to the identified user terminal in real time, means for displaying the instructions on the user terminal, means for receiving feedback on the instructions on the user terminal, means for collecting emotion data using an emotion engine that analyzes the user's emotional state, and means for saving the feedback including the emotion data in the database. This enables prompt and accurate transmission of instructions and realizes flexible responses according to the user's emotional state. Furthermore, adjusting the content of the next instruction based on the feedback and emotion data improves the quality of overall system performance, enabling effective support while reducing user stress.

[0998] A "prompt engineer" refers to a person or role whose role is to input specific instructions into a system.

[0999] "Server" refers to a central control unit that receives, stores, analyzes, transmits, etc. instructions.

[1000] "Database" means a data storage area within a system for storing instruction data and associated metadata.

[1001] "User terminal" refers to the device used to display instructions and send feedback, such as a smartphone, tablet, or computer.

[1002] "Feedback" refers to response data sent to a server after a user completes an action in response to an instruction.

[1003] An "emotion engine" refers to a combination of software and hardware for analyzing a user's emotional state and collecting it as emotional data.

[1004] "Metadata" refers to additional information related to an instruction, such as an instruction ID, a user ID, a timestamp, etc.

[1005] "Instructions" refer to guidelines or tasks that prompt engineers provide to users through the system.

[1006] "User" refers to a person who uses the system to receive and accomplish instructions.

[1007] "Analysis" refers to the process of analyzing received data to extract specific information.

[1008] "Emotional Data" refers to data that indicates the emotional state of a user collected and analyzed by the Emotion Engine.

[1009] Overall system overview

[1010] This invention relates to a system in which a prompt engineer inputs instructions, provides the instructions to a user terminal in real time via a server, and adjusts the next instructions based on the user's emotional state. This system aims to achieve quick and accurate transmission of instructions and flexible response according to the user's emotional state, thereby improving overall performance.

[1011] Hardware and software used

[1012] 1. Web or mobile interface: Used by prompt engineers to enter instructions.

[1013] 2. Server: Receives, stores, analyzes and transmits instructions.

[1014] 3. Database: Stores instruction data and associated metadata.

[1015] 4. User device (smartphone, tablet, computer): Used to display instructions and send feedback.

[1016] 5. Emotion engine (camera, microphone): Analyzes the user's emotional state and collects it as emotional data.

[1017] Prompt engineer inputs instructions

[1018] Prompt engineers access the system through a web or mobile interface and enter specific instructions, such as "get ready to move to the next corner," which are then sent to the server.

[1019] Processing on the server

[1020] The server first receives instructions sent by the prompt engineer. Then, it stores the received instructions in a database along with related metadata (instruction ID, user ID, timestamp, etc.). After storing the instructions, the server analyzes the instructions and identifies the relevant user. Once the target user is identified, the server sends the instructions to the user device in real time.

[1021] Processing on the user terminal

[1022] The device receives instructions sent from the server in real time and displays them on the screen. After the user confirms the instructions, they actually take action based on them. After responding to the instructions, the user clicks the "Done" button on the device and sends feedback to the server. The emotion engine installed on the device also uses sensors such as a camera and microphone to analyze the user's facial expressions, tone of voice, and movements to understand the user's emotional state. The emotion engine then includes this emotional data in feedback and sends it to the server.

[1023] Processing feedback and adjusting next steps

[1024] The server analyzes the feedback and emotion data received from the user terminal and stores them in a database. This feedback information and emotion data are then notified to the prompt engineer, who uses it as a reference to adjust the next instruction based on the user's emotional state.

[1025] Specific examples

[1026] Examples from TV shows:

[1027] The prompt engineer inputs the instruction "Please prepare to move to the next segment" and sends it to the server. The server receives this instruction and sends it to the target performer's device. The performer's device displays the instruction, and the performer acts according to the instruction. When the performer clicks the "Done" button, feedback is sent to the server along with emotional data collected by the device's emotion engine. The server analyzes this feedback and emotional data and notifies the prompt engineer. The prompt engineer adjusts the next instruction based on this data.

[1028] Prompt Sentence Examples

[1029] 1. "Get ready to move to the next corner."

[1030] 2. "Please introduce the next performer."

[1031] 3. "Please be ready for rehearsal to begin."

[1032] In this way, the system enables prompt and accurate transmission of instructions and flexible responses according to the user's emotional state, improving overall system performance and providing effective support while reducing user stress.

[1033] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1034] Step 1: Prompt Engineer Enters Instructions

[1035] A user accesses a web or mobile interface and enters specific instructions (e.g., "Get ready to move around the next corner").

[1036] Input: The prompt engineer types in instructions.

[1037] Output: The entered instructions are sent to the server.

[1038] Step 2: Server receives instructions

[1039] The server receives the instructions sent by the prompt engineer.

[1040] Input: Instruction data from prompt engineer.

[1041] Output: The instruction data received.

[1042] Step 3: Server saves data

[1043] The server stores the received instruction in a database along with associated metadata (instruction ID, user ID, timestamp, etc.).

[1044] Input: Received instruction data and associated metadata.

[1045] Output: Instruction data and metadata stored in a database.

[1046] Step 4: Server analyzes instruction data

[1047] The server analyzes the stored instruction data and identifies the relevant user.

[1048] Input: Instruction data stored in the database.

[1049] Output: Identified target users.

[1050] Step 5: Server sends instructions

[1051] The server transmits instructions to the identified user's terminal in real time.

[1052] Input: Identified user and instruction data.

[1053] Output: Instruction data sent to the user terminal.

[1054] Step 6: Terminal receives and displays instructions

[1055] The terminal receives instructions sent from the server in real time and displays them on the screen.

[1056] Input: Instruction data sent from the server.

[1057] Output: The instructions displayed on the screen.

[1058] Step 7: User executes instructions

[1059] The user confirms and executes the instruction (e.g., prepares to move to the next corner).

[1060] Input: The instructions displayed on the screen.

[1061] Output: The task that was executed.

[1062] Step 8: Send feedback via device

[1063] The user clicks the "Done" button after completing the task.

[1064] The device sends "Complete" feedback and the emotion data collected by the emotion engine to the server.

[1065] Input: "Done" state and emotion data.

[1066] Output: Feedback and emotion data sent to the server.

[1067] Step 9: Collect and analyze emotion data using the emotion engine

[1068] The device uses a camera and microphone to analyze the user's facial expressions, tone of voice, movements, etc. to understand their emotional state.

[1069] Input: User facial expressions, tone of voice, movements, etc.

[1070] Output: Parsed emotion data.

[1071] Step 10: Server receives feedback and emotion data

[1072] The server receives the feedback and emotion data received from the user terminal.

[1073] Input: Feedback and emotion data sent from the user device.

[1074] Output: Received feedback and sentiment data.

[1075] Step 11: Server analyzes feedback and emotion data

[1076] The server analyzes the received feedback and emotion data and stores it in a database.

[1077] Input: Received feedback and sentiment data.

[1078] Output: Analysis results stored in a database.

[1079] Step 12: Adjust the following instructions

[1080] The server notifies the prompt engineer of the analysis results, and the prompt engineer adjusts the next instructions based on this.

[1081] Input: Feedback and sentiment data analysis results.

[1082] Output: Adjusted next instruction.

[1083] As described above, specific actions are performed at each step, enabling prompt and accurate transmission of instructions and flexible responses according to the user's emotions.

[1084] (Application example 2)

[1085] 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."

[1086] In conventional food delivery services, delivery personnel are required to respond appropriately and promptly to customers, but information about the delivery personnel's emotional state and stress level is not taken into consideration, which raises concerns about a decline in customer satisfaction and delivery efficiency. Furthermore, insufficient work efficiency and stress management for delivery personnel tend to increase employee turnover. It is necessary to solve this problem and improve customer satisfaction and work efficiency.

[1087] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving instructions from a prompt engineer, means for transmitting the received instructions to a related user terminal in real time, means for displaying the instructions on the user terminal, means for receiving feedback from the user terminal, means for analyzing the emotional state of the user using an emotion recognition engine, and means for transmitting the analyzed emotional data. This makes it possible to monitor the emotional state of delivery personnel in real time and provide appropriate instructions, thereby improving the quality of customer service and managing the stress of delivery personnel.

[1088] A "prompt engineer" is a specialized engineer whose role is to provide appropriate instructions to users and manage tasks while receiving feedback in real time.

[1089] A "user terminal" is a device for receiving and displaying instructions, and refers to an electronic device such as a smartphone or tablet.

[1090] "Real-time transmission means" refers to communication technologies and mechanisms that allow instructions to be transmitted immediately to a user terminal.

[1091] "Means for receiving feedback" refers to a mechanism for collecting responses and impressions from users and feeding them back to the system.

[1092] An "emotion recognition engine" refers to a software or hardware component that analyzes a user's facial expressions, tone of voice, etc. to identify their emotional state.

[1093] "Emotional state" refers to a psychological state related to emotions, such as stress or fatigue felt by a user.

[1094] "Analyzed Emotion Data" refers to information about a user's emotions acquired and analyzed by the emotion recognition engine.

[1095] MODE FOR CARRYING OUT THE INVENTION

[1096] This invention is a system in which a prompt engineer provides instructions and adjusts work instructions based on the user's emotional state. A specific embodiment for realizing this system is described below. This system is mainly composed of the following hardware and software:

[1097] Hardware

[1098] User devices: smartphones, tablets

[1099] Sensors: Camera, microphone

[1100] software

[1101] Mobile Application Framework: React Native

[1102] Emotion recognition engine: Affectiva, Microsoft Azure Emotion API

[1103] Server: Node.js, AWS

[1104] Program Overview

[1105] 1. Data collection and sentiment analysis

[1106] The user device uses the smartphone's camera and microphone to collect the delivery person's facial expressions and voice in real time, and this collected data is sent to an emotion recognition engine (e.g., Affectiva, Microsoft Azure Emotion API) to analyze the delivery person's emotional state (e.g., stress, fatigue, joy).

[1107] 2. Providing Instructions

[1108] Prompt engineers input work instructions through a web interface or mobile app and send them to the server, such as "Please proceed to the next delivery destination" or "Please take note of the customer's special requests." The server receives these instructions and transmits them to the target user device in real time.

[1109] 3. Instructions and feedback

[1110] The user terminal displays the instructions received from the server on the screen and notifies the delivery person. The delivery person confirms the instructions and carries out the task. After completing the task, the delivery person presses the "Complete" button and sends the feedback to the server.

[1111] 4. Utilizing Emotional Data

[1112] The server receives the feedback sent from the user's device along with the emotional data collected and analyzed by the emotion recognition engine, allowing the prompt engineer to adjust the next instructions and support in real time according to the delivery person's emotional state.

[1113] Specific use cases

[1114] Food Delivery System

[1115] In food delivery work, delivery personnel receive instructions in real time via a smartphone app and carry out their work based on those instructions. For example, a prompt engineer inputs an instruction such as "Please head to the next delivery destination," which is sent to the delivery personnel's smartphone via the server. When the delivery personnel presses the "Done" button, feedback is sent to the server along with emotional data analyzed by the emotion engine. This data is analyzed by the prompt engineer, and if the delivery personnel is feeling stressed, instructions such as "Take a short break before your next delivery" are provided.

[1116] Prompt Sentence Examples

[1117] "Please proceed to the next delivery destination."

[1118] Pay attention to the customer's special requests

[1119] "Let's take a break for the next delivery."

[1120] In this way, collaboration between the emotion recognition engine and prompt engineers can improve delivery efficiency and customer satisfaction.

[1121] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1122] Step 1:

[1123] The user device uses the smartphone's camera and microphone to collect the delivery person's facial expressions and voice in real time. The input is the delivery person's facial image data and voice data, and the output is the collection of these data. Specifically, the system activates the user device's sensor and periodically captures images and voice.

[1124] Step 2:

[1125] The user device sends the collected facial image data and voice data to the emotion recognition engine. The input is the collected facial image data and voice data, and the output is the data sent to the emotion recognition engine. Specifically, the data is sent using the emotion recognition API and the analysis results are awaited.

[1126] Step 3:

[1127] The emotion recognition engine analyzes the received facial image data and voice data to identify the user's emotional state (e.g., stress, fatigue, joy). The input is facial image data and voice data, and the output is emotional state data. Specifically, it applies a recognition algorithm to analyze the data and generate a result.

[1128] Step 4:

[1129] The emotion recognition engine returns the analysis results to the user device. The input is emotional state data, and the output is data to be sent to the user device. Specifically, the analysis results are returned to the user device via an API.

[1130] Step 5:

[1131] Prompt engineers input instructions through a web interface or mobile app and send them to the server. The input is the prompt text (e.g., "Please proceed to the next delivery destination"), and the output is the data to be sent to the server. Specifically, instructions are input using a GUI and sent via the server's API.

[1132] Step 6:

[1133] The server receives instructions sent by the prompt engineer and transmits them to the relevant user terminal in real time. The input is the prompt text, and the output is the data to be sent to the user terminal. The specific operation is to receive the prompt text, identify the target user terminal, and transmit the data.

[1134] Step 7:

[1135] The user terminal displays the instructions received from the server and notifies the user. The input is the prompt sent from the server, and the output is the notification to the user. Specifically, the received prompt is displayed on the screen to notify the user.

[1136] Step 8:

[1137] The delivery person performs the task based on the instructions, and when complete, presses the "Done" button to send feedback. The input is the user action (clicking the "Done" button), and the output is sending feedback data to the server. Specifically, the system detects that the button has been clicked, generates feedback data, and sends it to the server.

[1138] Step 9:

[1139] The server receives the feedback sent from the user device as well as the emotion data collected by the emotion recognition engine. The input is the feedback data and emotion data, and the output is the storage and analysis of the data. Specifically, the received data is stored in a database and the necessary analysis is performed.

[1140] 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.

[1141] 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.

[1142] 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.

[1143] [Fourth embodiment]

[1144] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1145] 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.

[1146] 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).

[1147] 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.

[1148] 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.

[1149] 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).

[1150] 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. 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.

[1151] 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.

[1152] 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.

[1153] 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.

[1154] 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.

[1155] 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.

[1156] 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."

[1157] This invention is a system that supports performers in the entertainment industry by allowing them to receive instructions in real time and perform smoothly. It is realized through the cooperation of a platform, a server, user terminals, and prompt engineers.

[1158] Overall system overview

[1159] The system mainly consists of the following components:

[1160] Prompt An interface for engineers to enter instructions.

[1161] The server receives and stores the instructions and sends them to the appropriate user.

[1162] The user terminal displays the instructions and sends the feedback to the server.

[1163] Prompt engineer inputs instructions

[1164] Prompt engineers access the system through a web or mobile interface and enter specific instructions, such as "get ready to move to the next corner," which are then sent to the server.

[1165] Processing on the server

[1166] The server first receives instructions sent by the prompt engineer. It then stores the received instructions in a database along with associated metadata. After storing the instructions, the server analyzes the instructions and identifies the relevant user (performer). Once the target user is identified, the server sends the instructions to the user's device in real time.

[1167] Processing on the user terminal

[1168] The user device receives instructions sent from the server in real time and displays them on the screen. After the user confirms the instructions, they actually take action based on the instructions (for example, preparing to move to the next corner). After responding to the instructions, the user clicks the "Done" button on the device and sends feedback to the server.

[1169] Processing Feedback

[1170] The server analyzes the feedback received from the user terminal and stores it in the database, and the feedback information is notified to the prompt engineer for reference in adjusting the next instruction.

[1171] Specific examples

[1172] Examples from TV shows

[1173] The prompt engineer inputs the instruction "Please prepare to move to the next segment" and sends it to the server. The server receives this instruction and sends it to the device of the target user (performer). The performer's device displays the instruction, and the performer acts according to the instruction. When the performer clicks the "Done" button, the feedback is sent back to the server and the prompt engineer is notified. This process ensures that the entire performance is smooth and effective.

[1174] This system allows prompt engineers to quickly and accurately communicate instructions to users, improving the quality of their performance. Furthermore, it can provide flexible and effective support by adjusting subsequent instructions based on feedback.

[1175] The processing flow will be explained below.

[1176] Step 1:

[1177] A prompt engineer accesses the system through an interface and inputs instructions (e.g., "Prepare for the next corner").

[1178] Step 2:

[1179] The server receives instructions sent by prompt engineers and stores them in a database along with associated metadata (instruction ID, user ID, timestamp, etc.).

[1180] Step 3:

[1181] The server analyzes the stored instructions and identifies the content of the instructions and the target users, for example, identifying the performers based on the specified program and user ID.

[1182] Step 4:

[1183] The server sends instructions in real time to the target user's (performer's) device. The instructions are sent in an appropriate data format (e.g., JSON format).

[1184] Step 5:

[1185] The user's device receives the instructions sent from the server and displays them on the user interface, such as a message like "Prepare to move to the next corner."

[1186] Step 6:

[1187] The user checks the instructions displayed on the device and takes the necessary action (preparing to move to the next corner) according to those instructions.

[1188] Step 7:

[1189] After the user responds to the instructions, they click the "Done" button on the device screen, which sends feedback from the user to the server.

[1190] Step 8:

[1191] The feedback includes metadata such as instruction ID, user ID, and timestamp, which the server receives, analyzes, and stores in a database.

[1192] Step 9:

[1193] The server notifies the prompt engineer of the received feedback, who then adjusts the next instructions based on the feedback.

[1194] Step 10:

[1195] This series of processes ensures that prompt engineer instructions are conveyed to users quickly and accurately, maintaining excellent performance.

[1196] Example 1

[1197] 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."

[1198] Conventional systems for providing instructions to performers in the entertainment industry have suffered from delays in transmitting instructions and the cumbersome process of confirming instructions and providing feedback to performers. Furthermore, there have been cases where instructions were not properly assigned to specific users, resulting in a decline in the quality of the performance. The present invention aims to solve these problems and provide a system that allows performers to receive instructions in real time and perform smoothly.

[1199] 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.

[1200] In this invention, the server includes means for receiving instructions from a prompt engineer, means for saving the received instructions in a database, means for analyzing the saved instructions and identifying the relevant user, means for sending instructions to the identified user terminal in real time, means for displaying the instructions on the user terminal, means for sending feedback by clicking a "Done" button on the user terminal after responding to the instructions, means for receiving feedback from the user terminal and saving the feedback in a database, and means for notifying the prompt engineer of the feedback information, thereby enabling prompt and accurate transmission of instructions and flexible adjustment of instructions based on the feedback.

[1201] A "prompt engineer" is a person in the entertainment industry whose role is to input instructions to performers in real time and transmit them through the system.

[1202] "Instructions" are messages regarding actions and preparations that the prompt engineer sends to the performers.

[1203] A "database" is a system that organizes and stores data such as instructions and feedback, and makes it quickly accessible when needed.

[1204] "Analysis" is the process by which the server understands the content of the instructions received and distributes them to the appropriate user.

[1205] "User" refers to a performer who receives instructions from the system and acts accordingly.

[1206] A "user terminal" is a device, such as a smartphone, tablet, or PC, that a user uses to receive and display instructions.

[1207] "Real-time transmission means" refers to the technology and protocols for transmitting instructions to a user terminal almost instantaneously.

[1208] "Feedback" is information that notifies the server that the user has completed an action in response to an instruction.

[1209] "Notification" is a means by which the server notifies the prompt engineer of feedback information, etc.

[1210] This invention is a system for supporting performers in the entertainment industry to receive real-time instructions and perform smoothly. The system components include a server, a user terminal, and a prompt engineer.

[1211] Program processing overview

[1212] The system mainly consists of the following components:

[1213] Prompt An interface (web or mobile) for engineers to enter instructions.

[1214] The server receives, stores, parses, and transmits the instructions to the appropriate user terminal.

[1215] The user terminal receives and displays instructions in real time and sends feedback to the server after completing the action.

[1216] Server Roles and Operations

[1217] The server is built in Python, using frameworks like Flask or Django. The server has the following features:

[1218] 1. Receives an HTTP POST request from a prompt engineer and parses the instructions.

[1219] 2. Store the received instructions along with associated metadata in a PostgreSQL database.

[1220] 3. Analyze the saved instructions and identify the target user.

[1221] 4. Send instructions to the identified user device in real time via Firebase or Socket.io.

[1222] 5. Receive user feedback and store it back in the database.

[1223] 6. Use email and notification APIs to notify prompt engineers of feedback information.

[1224] Roles and operations of user terminals

[1225] User devices include a variety of devices, such as smartphones, tablets, and PCs. These devices run applications built with frameworks such as React Native and Flutter. Specific operations are as follows:

[1226] 1. Receive instructions sent from the server via a real-time communication protocol.

[1227] 2. Display the received instructions on the screen.

[1228] 3. After completing the instructions, click the "Done" button.

[1229] 4. Send the feedback to the server with an HTTP POST request.

[1230] User Roles

[1231] The user (performer) checks the instructions displayed on the device and takes action based on them. A specific example is the instruction "Please prepare to move to the next corner." After completing the action according to the instructions, the user clicks the "Done" button on the device and sends feedback to the server.

[1232] Specific examples of operation

[1233] The prompt engineer inputs the instruction "Please prepare to move to the next corner" through the web interface. The server receives this instruction and stores it in a database. It then analyzes the instruction and sends it to the user device of the relevant performer. The performer's device displays the instruction, and the performer acts according to it. When the performer clicks the "Done" button, feedback is sent to the server, which then notifies the prompt engineer of the feedback.

[1234] Examples of prompt statements

[1235] An example of a prompt sentence for a generative AI model is, "In this system, when the prompt engineer inputs the instruction 'Get ready to move to the next corner,' the server receives the instruction and sends it to the display terminal. The user (performer) checks the instruction, acts as instructed, and when completes, clicks the 'Done' button on the terminal to send feedback to the server."

[1236] With the above configuration and processing, this invention allows performers to receive instructions in real time and perform efficiently and smoothly.

[1237] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1238] Step 1:

[1239] A prompt engineer enters instructions. Using a web or mobile interface, the prompt engineer enters instructions such as "Get ready to move to the next corner." This entered instruction is sent to the server as an HTTP POST request. The input data is the textual instructions, and the output is the data sent to the server.

[1240] Step 2:

[1241] The server receives instructions from the prompt engineer. Using the Flask or Django framework, the server receives an HTTP POST request and parses the instructions. The input data is the HTTP request, and the output is the parsed text data. The server then stores the received instructions and associated metadata (such as a timestamp and the prompt engineer's ID) in a PostgreSQL database.

[1242] Step 3:

[1243] The server parses the stored instructions to identify the relevant users. It retrieves the stored database record and parses the instructions to identify the target users. This parsing uses specific rules and pattern matching. The input data is the database record, and the output is the target user's ID.

[1244] Step 4:

[1245] The server sends instructions to the identified user device in real time. Firebase or Socket.io is used to send instructions to the specified user device. Instructions are sent in JSON format and use real-time communication protocols. The input data is the user ID and the instruction content, and the output is the sent data.

[1246] Step 5:

[1247] The user device receives instructions sent from the server and displays them on the screen. The user device runs an application built with React Native or Flutter and receives instructions in real time via Firebase or Socket.io. When an instruction is received, the screen displays "Please prepare to move to the next corner." The input data is JSON data from the server, and the output is what is displayed on the device screen.

[1248] Step 6:

[1249] The user takes an action based on the instructions. For example, preparing to move to the next corner. When the action is complete, the user clicks the "Done" button on the device. The input data is the user's completion of the action, and the output is the click event of the "Done" button.

[1250] Step 7:

[1251] The user device sends the click of the "Done" button to the server as feedback. The feedback is sent as an HTTP POST request, and includes the user ID and the action completion status. The input data is the click event, and the output is an HTTP request.

[1252] Step 8:

[1253] The server receives feedback from the user device and stores it in a database. It parses the received feedback and stores it along with metadata (timestamp, user ID, etc.). The input data is an HTTP request, and the output is a database record.

[1254] Step 9:

[1255] The server notifies the prompt engineer of the saved feedback information. The prompt engineer is notified of the feedback using email API or notification API. The input data is a database record, and the output is a notification message.

[1256] (Application example 1)

[1257] 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."

[1258] Conventional factory work management systems lack the means to instantly notify robots and workers of work instructions, monitor progress in real time, and provide efficient feedback. As a result, work efficiency declines and productivity does not improve. In addition, it is difficult to accurately grasp the progress of work processes and issue the next instructions in a timely manner, making it difficult to manage the entire production line.

[1259] 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.

[1260] In this invention, the server includes a means for receiving instructions from a prompt engineer on the platform, a means for transmitting the received instructions to a related user terminal in real time, a means for displaying the instructions on the user terminal, a means for receiving feedback from the user terminal, a means for transmitting instructions to automated machinery and managing the work process, and a means for monitoring the progress of the work process based on the instructions. This allows work instructions in the factory to be quickly and accurately transmitted to robots and workers, progress to be monitored in real time, and the next instructions to be issued efficiently.

[1261] "Platform" refers to the platform through which prompt engineers input instructions and the server receives and processes the instructions.

[1262] A "prompt engineer" is a professional whose role is to input instructions into the system in real time.

[1263] "Instructions" are specific instructions for work or actions that are input by a prompt engineer and transmitted to a user terminal or automated machine device.

[1264] A "user terminal" is a device that displays received instructions and sends feedback, such as a tablet or smartphone.

[1265] "Feedback" refers to data sent back from the user terminal or robot to the server, such as reactions to executed instructions, completion reports, and progress status.

[1266] "Automated machinery" refers to robots and other automated equipment used to perform tasks automatically within a factory.

[1267] A "work process" is a series of steps for manufacturing or assembling an item according to a set procedure.

[1268] "Progress monitoring" refers to monitoring and understanding the progress of a work process in real time.

[1269] This invention applies a system that supports entertainment performers in receiving real-time instructions and performing smoothly to factory production line management. The main components of the system are realized through the cooperation of a platform, a server, user terminals (robots or worker devices), and a prompt engineer.

[1270] Overall system overview

[1271] The server receives instructions from the prompt engineer on the platform and transmits them to the relevant user device in real time. The user device displays the instructions and directs the automated machinery (robot) to perform the tasks based on the instructions. The server also monitors the progress of the work process, receives feedback from the user device, and adjusts the instructions.

[1272] Prompt engineer inputs instructions

[1273] A prompt engineer accesses the system through a web or mobile interface and enters specific work instructions, such as "Start assembly process on production line 1," which are then sent to the server.

[1274] Processing on the server

[1275] The server receives instructions sent by prompt engineers and stores them in a database along with associated metadata. After storing them, the server analyzes the instructions and identifies the specific user (robot or worker). Once the target user is identified, the server sends the instructions to the user's device in real time. The software to be used is planned to be Flask (a Python web framework).

[1276] Processing on the user terminal

[1277] The user device receives instructions sent from the server in real time and displays them on the screen. For example, a robot may receive the instruction "Please start the assembly process on production line 1." The robot will then begin work based on the instruction. Once the work is complete, the user clicks the "Done" button on the user device to send feedback to the server.

[1278] Processing Feedback

[1279] The server analyzes the feedback received from the user device and stores it in a database. Based on this feedback, the server adjusts the next instruction appropriately. For example, when it receives feedback such as "Assembly of production line 1 is completed," it notifies the prompt engineer and prepares to issue the next instruction.

[1280] Specific examples

[1281] For example, a prompt engineer inputs the instruction "Please start the assembly process on production line 1" into the system. This instruction is received by the server and sent to the robot on production line 1. The robot receives this instruction and starts the assembly process. When the work is completed, the robot reports "Assembly completed" to the system. The server receives this feedback and notifies the prompt engineer.

[1282] Prompt Sentence Examples

[1283] Prompt Engineer Instructions: Start assembly process on Production Line 1

[1284] Robot feedback: Assembly complete

[1285] This system allows work instructions within the factory to be transmitted quickly and accurately to robots and workers, monitors progress in real time, and efficiently issues subsequent instructions.

[1286] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1287] Step 1: Prompt engineer inputs instructions

[1288] A prompt engineer accesses the system through a web or mobile interface and enters specific work instructions, such as "Start assembly process on production line 1," which are then sent to the server in JSON format.

[1289] Input: prompt engineer instructions

[1290] Data processing: Convert instructions into JSON format

[1291] Output: Instruction data in JSON format

[1292] Step 2: Server receives and analyzes instructions

[1293] The server receives instructions in JSON format sent by the prompt engineer, stores them in a database, analyzes the instructions, and assigns them to specific users (robots or workers).

[1294] Input: Instruction data in JSON format

[1295] Data processing: Analysis of instruction data and saving to database

[1296] Output: Information on instruction distribution to specific users

[1297] Step 3: Server sends instructions

[1298] Based on the analysis results, the server sends instructions to the relevant user devices in real time, such as "Please start the assembly process for the robot on manufacturing line 1."

[1299] Input: Instruction distribution information for specific users

[1300] Data processing: Identifying user devices and sending real-time data

[1301] Output: Sends instruction data to the user terminal

[1302] Step 4: User terminal receives and displays instructions

[1303] The user terminal (e.g., a robot) receives instructions sent from the server in real time and displays them on its screen. The robot begins work according to the instructions. An instruction such as "Please start the assembly process on production line 1" is displayed.

[1304] Input: Instruction data from the server

[1305] Data processing: Decoding instruction data, displaying on screen

[1306] Output: On-screen instructions

[1307] Step 5: User performs task and provides feedback

[1308] The robot actually starts and completes the task based on the received instructions. When the task is completed, the user device clicks the "Done" button and sends feedback to the server. The feedback information "Assembly completed" is sent.

[1309] Input: Work progress, completion report

[1310] Data processing: Generate feedback information and send it to the server

[1311] Output: Feedback data to the server

[1312] Step 6: Server receives and analyzes feedback

[1313] The server analyzes the feedback received from the user terminal and stores it in the database. Based on the feedback information, it adjusts the next instruction and notifies the prompt engineer.

[1314] Input: Feedback data from user terminal

[1315] Data processing: Analysis of feedback data and storage in database

[1316] Output: Prompt engineer notification information

[1317] Step 7: Adjust and issue next instructions

[1318] The prompt engineer adjusts the next instructions based on the feedback notification from the server and inputs the new instructions into the system, thereby ensuring that the production line continues to operate efficiently.

[1319] Input: Feedback notification from the server

[1320] Data processing: creating new instructions

[1321] Output: System input for next instruction

[1322] 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.

[1323] This invention combines a prompt engineer's real-time instruction system, which displays, receives, and feeds back instructions via the user's terminal, with an emotion engine that recognizes the user's emotions, thereby improving the quality of instruction provision and realizing more effective performance support based on the user's emotional state.

[1324] Overall system overview

[1325] The system mainly consists of the following components:

[1326] Prompt An interface for engineers to enter instructions.

[1327] The server receives and stores the instructions and sends them to the appropriate users in real time.

[1328] The user terminal displays the instructions and sends the feedback to the server.

[1329] It is equipped with an emotion engine that recognizes the user's emotions and performs data analysis.

[1330] Prompt engineer inputs instructions

[1331] Prompt engineers access the system through a web or mobile interface and enter specific instructions, such as "get ready to move to the next corner," which are then sent to the server.

[1332] Processing on the server

[1333] The server first receives instructions sent by the prompt engineer. It then stores the received instructions in a database along with related metadata (instruction ID, user ID, timestamp, etc.). After storing the instructions, the server analyzes the instructions and identifies the corresponding user (performer). Once the target user is identified, the server sends the instructions to the user's device in real time.

[1334] Processing on the user terminal

[1335] The user device receives instructions sent from the server in real time and displays them on the screen. After the user confirms the instructions, they actually take action based on the instructions (for example, preparing to move to the next corner). After responding to the instructions, the user clicks the "Done" button on the device and sends feedback to the server.

[1336] Emotion engine processing

[1337] The emotion engine installed in the user's device uses sensors such as a camera and microphone to analyze the user's facial expressions, tone of voice, movements, etc. to grasp the user's emotional state. The emotion engine includes this emotional data in feedback and sends it to the server.

[1338] Processing feedback and adjusting next steps

[1339] The server analyzes the feedback and emotion data received from the user terminal and stores them in a database. This feedback information and emotion data are then notified to the prompt engineer, who uses it as a reference to adjust the next instruction based on the user's emotional state.

[1340] Specific examples

[1341] Examples from TV shows

[1342] The prompt engineer inputs the instruction "Please prepare to move to the next segment" and sends it to the server. The server receives this instruction and sends it to the device of the target user (performer). The instruction is displayed on the device of the performer, who then acts according to the instruction. When the performer clicks the "Done" button, feedback is sent to the server along with the emotional data collected by the emotion engine. The server analyzes this feedback and emotional data and notifies the prompt engineer. The prompt engineer can adjust the next instruction based on the feedback and emotional data to further improve the performer's performance.

[1343] This allows prompt engineers to quickly and accurately communicate their instructions to users, enabling flexible responses based on the user's emotional state. This improves the quality of the system's overall performance, reducing stress on performers and providing effective performance support.

[1344] The processing flow will be explained below.

[1345] Step 1:

[1346] A prompt engineer accesses the system through an interface and inputs instructions (e.g., "Prepare for the next corner").

[1347] Step 2:

[1348] The server receives instructions sent by prompt engineers and stores them in a database along with associated metadata (instruction ID, user ID, timestamp, etc.).

[1349] Step 3:

[1350] The server analyzes the stored instructions and identifies the content of the instructions and the target users, for example, identifying the performers based on the specified program and user ID.

[1351] Step 4:

[1352] The server sends instructions in real time to the target user's (performer's) device. The instructions are sent in an appropriate data format (e.g., JSON format).

[1353] Step 5:

[1354] The user's device receives the instructions sent from the server and displays them on the user interface, such as a message like "Prepare to move to the next corner."

[1355] Step 6:

[1356] The emotion engine uses the device's camera and microphone to analyze the user's facial expressions, tone of voice, movements, etc. in real time to determine the user's emotional state.

[1357] Step 7:

[1358] The user checks the instructions displayed on the device and takes the necessary action (preparing to move to the next corner) according to those instructions.

[1359] Step 8:

[1360] After responding to the instructions, the user clicks the "Done" button on the device screen, which sends feedback from the user to the server. At the same time, the feedback also includes emotional data analyzed by the emotion engine.

[1361] Step 9:

[1362] The server receives feedback and emotion data sent from the user device, analyzes the received data, and stores it in a database.

[1363] Step 10:

[1364] Based on the analysis results, the server notifies the prompt engineer of the feedback and emotional data, who then uses the feedback and emotional data to optimize the next instructions.

[1365] Step 11:

[1366] This series of processes allows prompt engineers to quickly and accurately convey instructions to users, and also enables flexible instructions to be provided according to the user's emotional state, improving the overall quality of the performance and providing effective performance support while reducing stress for performers.

[1367] Example 2

[1368] 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."

[1369] Conventional instruction systems require prompt and accurate delivery of instructions, but lack the ability to flexibly respond to the user's emotional state, which can result in reduced user performance and satisfaction. Furthermore, it is difficult to effectively utilize feedback and emotional data to adjust the next instruction. This has led to the issue of being unable to improve the overall performance of the system.

[1370] 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.

[1371] In this invention, the server includes means for receiving instructions from a prompt engineer, means for saving the received instructions in a database, means for analyzing the saved instruction data to identify the relevant user, means for sending instructions to the identified user terminal in real time, means for displaying the instructions on the user terminal, means for receiving feedback on the instructions on the user terminal, means for collecting emotion data using an emotion engine that analyzes the user's emotional state, and means for saving the feedback including the emotion data in the database. This enables prompt and accurate transmission of instructions and realizes flexible responses according to the user's emotional state. Furthermore, adjusting the content of the next instruction based on the feedback and emotion data improves the quality of overall system performance, enabling effective support while reducing user stress.

[1372] A "prompt engineer" refers to a person or role whose role is to input specific instructions into a system.

[1373] "Server" refers to a central control unit that receives, stores, analyzes, transmits, etc. instructions.

[1374] "Database" means a data storage area within a system for storing instruction data and associated metadata.

[1375] "User terminal" refers to the device used to display instructions and send feedback, such as a smartphone, tablet, or computer.

[1376] "Feedback" refers to response data sent to a server after a user completes an action in response to an instruction.

[1377] An "emotion engine" refers to a combination of software and hardware for analyzing a user's emotional state and collecting it as emotional data.

[1378] "Metadata" refers to additional information related to an instruction, such as an instruction ID, a user ID, a timestamp, etc.

[1379] "Instructions" refer to guidelines or tasks that prompt engineers provide to users through the system.

[1380] "User" refers to a person who uses the system to receive and accomplish instructions.

[1381] "Analysis" refers to the process of analyzing received data to extract specific information.

[1382] "Emotional Data" refers to data that indicates the emotional state of a user collected and analyzed by the Emotion Engine.

[1383] Overall system overview

[1384] This invention relates to a system in which a prompt engineer inputs instructions, provides the instructions to a user terminal in real time via a server, and adjusts the next instructions based on the user's emotional state. This system aims to achieve quick and accurate transmission of instructions and flexible response according to the user's emotional state, thereby improving overall performance.

[1385] Hardware and software used

[1386] 1. Web or mobile interface: Used by prompt engineers to enter instructions.

[1387] 2. Server: Receives, stores, analyzes and transmits instructions.

[1388] 3. Database: Stores instruction data and associated metadata.

[1389] 4. User device (smartphone, tablet, computer): Used to display instructions and send feedback.

[1390] 5. Emotion engine (camera, microphone): Analyzes the user's emotional state and collects it as emotional data.

[1391] Prompt engineer inputs instructions

[1392] Prompt engineers access the system through a web or mobile interface and enter specific instructions, such as "get ready to move to the next corner," which are then sent to the server.

[1393] Processing on the server

[1394] The server first receives instructions sent by the prompt engineer. Then, it stores the received instructions in a database along with related metadata (instruction ID, user ID, timestamp, etc.). After storing the instructions, the server analyzes the instructions and identifies the relevant user. Once the target user is identified, the server sends the instructions to the user device in real time.

[1395] Processing on the user terminal

[1396] The device receives instructions sent from the server in real time and displays them on the screen. After the user confirms the instructions, they actually take action based on them. After responding to the instructions, the user clicks the "Done" button on the device and sends feedback to the server. The emotion engine installed on the device also uses sensors such as a camera and microphone to analyze the user's facial expressions, tone of voice, and movements to understand the user's emotional state. The emotion engine then includes this emotional data in feedback and sends it to the server.

[1397] Processing feedback and adjusting next steps

[1398] The server analyzes the feedback and emotion data received from the user terminal and stores them in a database. This feedback information and emotion data are then notified to the prompt engineer, who uses it as a reference to adjust the next instruction based on the user's emotional state.

[1399] Specific examples

[1400] Examples from TV shows:

[1401] The prompt engineer inputs the instruction "Please prepare to move to the next segment" and sends it to the server. The server receives this instruction and sends it to the target performer's device. The performer's device displays the instruction, and the performer acts according to the instruction. When the performer clicks the "Done" button, feedback is sent to the server along with emotional data collected by the device's emotion engine. The server analyzes this feedback and emotional data and notifies the prompt engineer. The prompt engineer adjusts the next instruction based on this data.

[1402] Prompt Sentence Examples

[1403] 1. "Get ready to move to the next corner."

[1404] 2. "Please introduce the next performer."

[1405] 3. "Please be ready for rehearsal to begin."

[1406] In this way, the system enables prompt and accurate transmission of instructions and flexible responses according to the user's emotional state, improving overall system performance and providing effective support while reducing user stress.

[1407] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1408] Step 1: Prompt Engineer Enters Instructions

[1409] A user accesses a web or mobile interface and enters specific instructions (e.g., "Get ready to move around the next corner").

[1410] Input: The prompt engineer types in instructions.

[1411] Output: The entered instructions are sent to the server.

[1412] Step 2: Server receives instructions

[1413] The server receives the instructions sent by the prompt engineer.

[1414] Input: Instruction data from prompt engineer.

[1415] Output: The instruction data received.

[1416] Step 3: Server saves data

[1417] The server stores the received instruction in a database along with associated metadata (instruction ID, user ID, timestamp, etc.).

[1418] Input: Received instruction data and associated metadata.

[1419] Output: Instruction data and metadata stored in a database.

[1420] Step 4: Server analyzes instruction data

[1421] The server analyzes the stored instruction data and identifies the relevant user.

[1422] Input: Instruction data stored in the database.

[1423] Output: Identified target users.

[1424] Step 5: Server sends instructions

[1425] The server transmits instructions to the identified user's terminal in real time.

[1426] Input: Identified user and instruction data.

[1427] Output: Instruction data sent to the user terminal.

[1428] Step 6: Terminal receives and displays instructions

[1429] The terminal receives instructions sent from the server in real time and displays them on the screen.

[1430] Input: Instruction data sent from the server.

[1431] Output: The instructions displayed on the screen.

[1432] Step 7: User executes instructions

[1433] The user confirms and executes the instruction (e.g., prepares to move to the next corner).

[1434] Input: The instructions displayed on the screen.

[1435] Output: The task that was executed.

[1436] Step 8: Send feedback via device

[1437] The user clicks the "Done" button after completing the task.

[1438] The device sends "Complete" feedback and the emotion data collected by the emotion engine to the server.

[1439] Input: "Done" state and emotion data.

[1440] Output: Feedback and emotion data sent to the server.

[1441] Step 9: Collect and analyze emotion data using the emotion engine

[1442] The device uses a camera and microphone to analyze the user's facial expressions, tone of voice, movements, etc. to understand their emotional state.

[1443] Input: User facial expressions, tone of voice, movements, etc.

[1444] Output: Parsed emotion data.

[1445] Step 10: Server receives feedback and emotion data

[1446] The server receives the feedback and emotion data received from the user terminal.

[1447] Input: Feedback and emotion data sent from the user device.

[1448] Output: Received feedback and sentiment data.

[1449] Step 11: Server analyzes feedback and emotion data

[1450] The server analyzes the received feedback and emotion data and stores it in a database.

[1451] Input: Received feedback and sentiment data.

[1452] Output: Analysis results stored in a database.

[1453] Step 12: Adjust the following instructions

[1454] The server notifies the prompt engineer of the analysis results, and the prompt engineer adjusts the next instructions based on this.

[1455] Input: Feedback and sentiment data analysis results.

[1456] Output: Adjusted next instruction.

[1457] As described above, specific actions are performed at each step, enabling prompt and accurate transmission of instructions and flexible responses according to the user's emotions.

[1458] (Application example 2)

[1459] 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."

[1460] In conventional food delivery services, delivery personnel are required to respond appropriately and promptly to customers, but information about the delivery personnel's emotional state and stress level is not taken into consideration, which raises concerns about a decline in customer satisfaction and delivery efficiency. Furthermore, insufficient work efficiency and stress management for delivery personnel tend to increase employee turnover. It is necessary to solve this problem and improve customer satisfaction and work efficiency.

[1461] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving instructions from a prompt engineer, means for transmitting the received instructions to a related user terminal in real time, means for displaying the instructions on the user terminal, means for receiving feedback from the user terminal, means for analyzing the emotional state of the user using an emotion recognition engine, and means for transmitting the analyzed emotional data. This makes it possible to monitor the emotional state of delivery personnel in real time and provide appropriate instructions, thereby improving the quality of customer service and managing the stress of delivery personnel.

[1462] A "prompt engineer" is a specialized engineer whose role is to provide appropriate instructions to users and manage tasks while receiving feedback in real time.

[1463] A "user terminal" is a device for receiving and displaying instructions, and refers to an electronic device such as a smartphone or tablet.

[1464] "Real-time transmission means" refers to communication technologies and mechanisms that allow instructions to be transmitted immediately to a user terminal.

[1465] "Means for receiving feedback" refers to a mechanism for collecting responses and impressions from users and feeding them back to the system.

[1466] An "emotion recognition engine" refers to a software or hardware component that analyzes a user's facial expressions, tone of voice, etc. to identify their emotional state.

[1467] "Emotional state" refers to a psychological state related to emotions, such as stress or fatigue felt by a user.

[1468] "Analyzed Emotion Data" refers to information about a user's emotions acquired and analyzed by the emotion recognition engine.

[1469] MODE FOR CARRYING OUT THE INVENTION

[1470] This invention is a system in which a prompt engineer provides instructions and adjusts work instructions based on the user's emotional state. A specific embodiment for realizing this system is described below. This system is mainly composed of the following hardware and software:

[1471] Hardware

[1472] User devices: smartphones, tablets

[1473] Sensors: Camera, microphone

[1474] software

[1475] Mobile Application Framework: React Native

[1476] Emotion recognition engine: Affectiva, Microsoft Azure Emotion API

[1477] Server: Node.js, AWS

[1478] Program Overview

[1479] 1. Data collection and sentiment analysis

[1480] The user device uses the smartphone's camera and microphone to collect the delivery person's facial expressions and voice in real time, and this collected data is sent to an emotion recognition engine (e.g., Affectiva, Microsoft Azure Emotion API) to analyze the delivery person's emotional state (e.g., stress, fatigue, joy).

[1481] 2. Providing Instructions

[1482] Prompt engineers input work instructions through a web interface or mobile app and send them to the server, such as "Please proceed to the next delivery destination" or "Please take note of the customer's special requests." The server receives these instructions and transmits them to the target user device in real time.

[1483] 3. Instructions and feedback

[1484] The user terminal displays the instructions received from the server on the screen and notifies the delivery person. The delivery person confirms the instructions and carries out the task. After completing the task, the delivery person presses the "Complete" button and sends the feedback to the server.

[1485] 4. Utilizing Emotional Data

[1486] The server receives the feedback sent from the user's device along with the emotional data collected and analyzed by the emotion recognition engine, allowing the prompt engineer to adjust the next instructions and support in real time according to the delivery person's emotional state.

[1487] Specific use cases

[1488] Food Delivery System

[1489] In food delivery work, delivery personnel receive instructions in real time via a smartphone app and carry out their work based on those instructions. For example, a prompt engineer inputs an instruction such as "Please head to the next delivery destination," which is sent to the delivery personnel's smartphone via the server. When the delivery personnel presses the "Done" button, feedback is sent to the server along with emotional data analyzed by the emotion engine. This data is analyzed by the prompt engineer, and if the delivery personnel is feeling stressed, instructions such as "Take a short break before your next delivery" are provided.

[1490] Prompt Sentence Examples

[1491] "Please proceed to the next delivery destination."

[1492] Pay attention to the customer's special requests

[1493] "Let's take a break for the next delivery."

[1494] In this way, collaboration between the emotion recognition engine and prompt engineers can improve delivery efficiency and customer satisfaction.

[1495] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1496] Step 1:

[1497] The user device uses the smartphone's camera and microphone to collect the delivery person's facial expressions and voice in real time. The input is the delivery person's facial image data and voice data, and the output is the collection of these data. Specifically, the system activates the user device's sensor and periodically captures images and voice.

[1498] Step 2:

[1499] The user device sends the collected facial image data and voice data to the emotion recognition engine. The input is the collected facial image data and voice data, and the output is the data sent to the emotion recognition engine. Specifically, the data is sent using the emotion recognition API and the analysis results are awaited.

[1500] Step 3:

[1501] The emotion recognition engine analyzes the received facial image data and voice data to identify the user's emotional state (e.g., stress, fatigue, joy). The input is facial image data and voice data, and the output is emotional state data. Specifically, it applies a recognition algorithm to analyze the data and generate a result.

[1502] Step 4:

[1503] The emotion recognition engine returns the analysis results to the user device. The input is emotional state data, and the output is data to be sent to the user device. Specifically, the analysis results are returned to the user device via an API.

[1504] Step 5:

[1505] Prompt engineers input instructions through a web interface or mobile app and send them to the server. The input is the prompt text (e.g., "Please proceed to the next delivery destination"), and the output is the data to be sent to the server. Specifically, instructions are input using a GUI and sent via the server's API.

[1506] Step 6:

[1507] The server receives instructions sent by the prompt engineer and transmits them to the relevant user terminal in real time. The input is the prompt text, and the output is the data to be sent to the user terminal. The specific operation is to receive the prompt text, identify the target user terminal, and transmit the data.

[1508] Step 7:

[1509] The user terminal displays the instructions received from the server and notifies the user. The input is the prompt sent from the server, and the output is the notification to the user. Specifically, the received prompt is displayed on the screen to notify the user.

[1510] Step 8:

[1511] The delivery person performs the task based on the instructions, and when complete, presses the "Done" button to send feedback. The input is the user action (clicking the "Done" button), and the output is sending feedback data to the server. Specifically, the system detects that the button has been clicked, generates feedback data, and sends it to the server.

[1512] Step 9:

[1513] The server receives the feedback sent from the user device as well as the emotion data collected by the emotion recognition engine. The input is the feedback data and emotion data, and the output is the storage and analysis of the data. Specifically, the received data is stored in a database and the necessary analysis is performed.

[1514] 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.

[1515] 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.

[1516] 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.

[1517] 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.

[1518] FIG. 9 is a diagram illustrating 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 actions 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.

[1519] 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.

[1520] 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).

[1521] 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.

[1522] 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."

[1523] 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.

[1524] 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).

[1525] 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.

[1526] 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.

[1527] 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.

[1528] 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.

[1529] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1530] 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.

[1531] 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.

[1532] 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.

[1533] 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.

[1534] 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.

[1535] The following is further disclosed regarding the above embodiment.

[1536] (Claim 1)

[1537] a means for receiving instructions from a prompt engineer on the platform;

[1538] means for transmitting the received instructions to an associated user terminal in real time;

[1539] means for displaying instructions at a user terminal;

[1540] A system including means for receiving feedback from a user terminal.

[1541] (Claim 2)

[1542] The system of claim 1 further comprising means for routing the instructions to a particular user.

[1543] (Claim 3)

[1544] 10. The system of claim 1, further comprising: means for adjusting a next instruction based on the feedback.

[1545] "Example 1"

[1546] (Claim 1)

[1547] means for receiving instructions from a prompt engineer;

[1548] means for storing the received instructions in a database;

[1549] means for analyzing the stored instructions to identify associated users;

[1550] means for transmitting instructions to the identified user terminal in real time;

[1551] means for displaying instructions at a user terminal;

[1552] A means for sending feedback by clicking a "Done" button on the user's device after responding to the instructions; and

[1553] means for receiving feedback from the user terminal and storing it in a database;

[1554] The system includes a means for communicating feedback information to a prompt engineer.

[1555] (Claim 2)

[1556] Further comprising means for analyzing the content of the instruction and distributing the instruction to a specific user.

[1557] 10. The system of claim 1.

[1558] (Claim 3)

[1559] and means for adjusting subsequent instructions based on the feedback.

[1560] 10. The system of claim 1.

[1561] "Application Example 1"

[1562] (Claim 1)

[1563] a means for receiving instructions from a prompt engineer on the platform;

[1564] means for transmitting the received instructions to an associated user terminal in real time;

[1565] means for displaying instructions at a user terminal;

[1566] means for receiving feedback from the user terminal;

[1567] means for transmitting instructions to the automated machinery and controlling the work process;

[1568] a means for monitoring the progress of work processes based on instructions;

[1569] A system including:

[1570] (Claim 2)

[1571] The system of claim 1 further comprising means for routing the instructions to a particular user.

[1572] (Claim 3)

[1573] 10. The system of claim 1, further comprising: means for adjusting a next instruction based on the feedback.

[1574] "Example 2: Combining Emotion Engines"

[1575] (Claim 1)

[1576] means for receiving instructions from a prompt engineer;

[1577] means for storing the received instructions in a database;

[1578] means for analyzing the stored instruction data to identify an associated user;

[1579] means for transmitting instructions to the identified user terminal in real time;

[1580] means for displaying instructions at a user terminal;

[1581] means for receiving feedback in response to the instruction at the user terminal;

[1582] means for collecting emotion data using an emotion engine that analyzes the user's emotional state;

[1583] a means for storing the feedback, including the emotional data, in a database;

[1584] A system including:

[1585] (Claim 2)

[1586] 10. The system of claim 1, further comprising means for analyzing the instruction data and directing it to a particular user.

[1587] (Claim 3)

[1588] 10. The system of claim 1, further comprising means for analyzing the feedback and emotion data and adjusting subsequent instruction content.

[1589] "Application example 2 when combining emotion engines"

[1590] (Claim 1)

[1591] means for receiving instructions from a prompt engineer;

[1592] means for transmitting the received instructions to an associated user terminal in real time;

[1593] means for displaying instructions at a user terminal;

[1594] means for receiving feedback from the user terminal;

[1595] means for analyzing the emotional state of a user by an emotion recognition engine;

[1596] The system includes a means for transmitting the analyzed emotion data.

[1597] (Claim 2)

[1598] The system of claim 1 further comprising means for routing the instructions to a particular user.

[1599] (Claim 3)

[1600] 10. The system of claim 1, further comprising: means for adjusting a next instruction based on the feedback.

[1601] (Claim 4)

[1602] 2. The system according to claim 1, further comprising means for transmitting the emotion data collected in the user terminal to a server, the server analyzing the emotion data, and adjusting the instruction content by a prompt engineer. [Explanation of symbols]

[1603] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for receiving instructions from a prompt engineer on the platform; means for transmitting the received instructions to an associated user terminal in real time; means for displaying instructions at a user terminal; A system including means for receiving feedback from a user terminal.

2. The system of claim 1 further comprising means for routing the instructions to a particular user.

3. The system of claim 1 further comprising means for adjusting a next instruction based on the feedback.

Images