System

Abstract

A system is provided.SOLUTION: This system includes a means for receiving play data provided by a user, a means for converting the received play data into an analyzable format, a means for comparing and analyzing the converted data with play data of a previously learned professional gamer, a means for extracting a problem and an improvement point of the user on the basis of an analysis result, and a means for presenting the extracted problem and improvement point to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] To improve their skills, current game players often rely solely on researching game strategy information or watching and imitating other players' videos. However, these methods lack appropriate advice for each player's specific problems, resulting in low efficiency in improving skills. Furthermore, scattered information makes it difficult to identify specific areas for improvement, resulting in a lack of means for players to effectively improve their skills. The present invention aims to solve these problems. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems with a system that includes: means for receiving play data provided by users; means for converting the received play data into an analyzable format; means for comparing and analyzing the converted data with play data of previously trained professional gamers; means for extracting issues and areas for improvement for the user based on the analysis results; and means for presenting the extracted issues and areas for improvement to the user. This system provides specific and quantitative feedback that is optimal for each individual player, enabling them to efficiently improve their skills.

[0006] "User" refers to an individual or legal entity that uses the system and provides their gameplay data.

[0007] "Play data" refers to data that records the user's operations and tactics during gameplay, as well as their actions within the game, and includes, for example, replay videos and operation logs.

[0008] "Means for receiving" refers to the process or mechanism by which the server receives play data sent by the user.

[0009] "Means for converting into an analyzable format" refers to the process of converting received play data into an appropriate format so that the AI ​​model can accurately parse it.

[0010] A "professional gamer" is a player who has high skills and experience in playing games and who plays them professionally to earn a living.

[0011] "Means of analysis" refers to the process by which the AI ​​model analyzes play data, extracts user actions and tactics, and compares them with the play of professional gamers.

[0012] "Means for extracting issues and areas for improvement" refers to the process of identifying problems with users' play and specific ways to improve them based on analysis.

[0013] "Means of presentation" refers to the method or interface that provides the extracted issues and areas for improvement to the user in an easy-to-understand manner.

[0014] "Visual display interface" refers to a graphical user interface that allows users to easily understand and implement issues and improvements. [Brief explanation of the drawings]

[0015] [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

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] The present invention is a system in which a user provides their own gameplay data, an AI model analyzes the data, and presents specific issues and areas for improvement. Specific embodiments of the system are described below.

[0037] System Configuration

[0038] This system consists of a user's terminal, a server, and an AI model.

[0039] 1. On the user's device:

[0040] Users play the game and create play data, which is also responsible for uploading the play data to the server.

[0041] Receive feedback and provide an interface for users to review.

[0042] 2. Server:

[0043] Receives and stores play data and converts it into an analyzable format.

[0044] The converted data is passed to the AI ​​model and the analysis results are received.

[0045] The analysis results are processed into a user-friendly format and sent to the terminal.

[0046] 3. AI model:

[0047] The system learns the play data of professional gamers in advance and analyzes the user's play data.

[0048] Compare user actions and tactics with professional gamer data to identify issues and areas for improvement.

[0049] System action

[0050] This system's processing consists of a series of steps, from uploading the user's play data to providing feedback. The specific operation of each component is as follows:

[0051] Server Operation

[0052] Receiving play data:

[0053] The server receives play data uploaded by users. The received data is first saved in a specified directory.

[0054] Transforming data:

[0055] The server converts the saved play data into an analyzable format, for example, by extracting specific frames from video data and converting operation log data into a time-stamped format.

[0056] Sending data:

[0057] The converted play data is sent to the AI ​​model, which then performs analysis based on this data.

[0058] Receiving and processing analysis results:

[0059] The server receives the analysis results from the AI ​​model and processes them into a user-friendly format, such as a text report, a graphical dashboard, or a list of specific improvements.

[0060] How AI models work

[0061] Analysis of gameplay data:

[0062] The AI ​​model analyzes the user's actions and tactics based on the play data received from the server. Specifically, it compares the play data with that of professional gamers and evaluates the user's movement patterns, reaction speed, tactical decisions, etc.

[0063] Identifying issues and areas for improvement:

[0064] Based on the analysis results, the system extracts issues in the user's gameplay and specific areas for improvement, such as "the timing of the shot is 0.2 seconds late" or "moving to cover in a specific area is inappropriate."

[0065] Device behavior

[0066] Uploading gameplay data:

[0067] The user uploads their gameplay data from their device to the server, which then begins analysis on the server side.

[0068] Receiving and viewing feedback:

[0069] The terminal receives the feedback sent from the server and presents it to the user. The feedback is displayed visually and is provided in a form that is easy for the user to understand and put into action.

[0070] Specific examples

[0071] Example 1: Analysis of play data in FPS games

[0072] Users upload their FPS gameplay videos from their devices to a server.

[0073] The server receives the video data, extracts specific frames, and converts them into an analyzable format.

[0074] The AI ​​model analyzes gameplay data and discovers that the user's shooting timing is slower than that of professional gamers, and identifies improper cover movements.

[0075] Based on the analysis results received from the AI ​​model, the server generates a feedback report containing specific improvements, such as "the timing of the shot should be advanced by 0.2 seconds" or "quickly move to cover in specific areas," and sends it to the device.

[0076] Users can view the feedback on their device and put it into practice the next time they play the game.

[0077] The processing flow will be explained below.

[0078] Step 1:

[0079] After finishing a game, the user prepares the gameplay data (such as a replay video or operation log), and then uploads the gameplay data to the server using a dedicated application or web interface on the device.

[0080] Step 2:

[0081] The server receives play data uploaded by users and stores it in a storage directory. This storage process includes checking the integrity of the data when it is received.

[0082] Step 3:

[0083] The server converts the saved gameplay data into an analyzable format. For example, it extracts specific frames from video data and adds necessary metadata (timestamps, event logs, etc.). It also converts the operation log data into a unified format.

[0084] Step 4:

[0085] The server passes the converted data to the AI ​​model, and at the same time issues an analysis request.

[0086] Step 5:

[0087] The AI ​​model receives the transmitted play data and analyzes the user's movement patterns. For example, it compares the play data of professional gamers to evaluate the user's movements (shooting timing, movement patterns, etc.). The AI ​​model also compares the user's play data with the professional gamer's standards to perform a discrepancy analysis.

[0088] Step 6:

[0089] The AI ​​model generates analysis results and identifies the user's issues and areas for improvement. For example, specific problems such as "firing timing is 0.2 seconds late" or "cover movement is slow in certain areas" are summarized in text format along with how to improve them.

[0090] Step 7:

[0091] Based on the analysis results received from the AI ​​model, the server generates feedback reports for the user, including text reports, graphical dashboards, and lists of specific areas for improvement, as well as graphs and heat maps for visual coaching.

[0092] Step 8:

[0093] The server sends the generated feedback report to the user's device, and the analysis results are reflected on the user's personal dashboard.

[0094] Step 9:

[0095] The device receives the feedback report sent from the server and displays it in an interface that the user can view. The user can refer to this to identify problems with their gameplay and use the suggested improvements to prepare for their next gameplay.

[0096] Step 10:

[0097] Users use the feedback to implement specific improvements in their next gameplay, and then upload their gameplay data again to receive continuous feedback using the server and AI model to improve their skills.

[0098] Example 1

[0099] 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."

[0100] Conventional gameplay data analysis systems have struggled to efficiently and effectively analyze user-provided play data and identify specific issues and areas for improvement to improve the user's skills. Furthermore, there has been a lack of a way to present the analysis results in a format that users can easily understand and apply. This has resulted in users being unable to effectively utilize their play data, which has prevented them from improving their skills.

[0101] 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.

[0102] In this invention, the server includes means for receiving play data provided by a user, means for converting the received play data into an analyzable format, means for comparing and analyzing the converted data with play data of previously learned professional gamers, means for extracting issues and areas for improvement for the user based on the analysis results, means for presenting the extracted issues and areas for improvement to the user, means for the user to upload the play data to the server, means for saving the play data in a storage directory, means for extracting specific frames from the play data, means for converting operation log data into a timestamp-added format, means for receiving the analysis results from the server and processing them into a format that is easy for the user to understand, and means for providing an interface for visually displaying feedback to the user. This makes it possible to effectively analyze the user's play data, allowing the user to easily understand specific issues and areas for improvement and put them into action.

[0103] "Play data" refers to information such as operation logs and video files that are generated by the user while playing the game.

[0104] A "server" is a device that receives play data provided by users, stores it, converts it into an analyzable format, sends it to an AI model, and receives the analysis results.

[0105] A "terminal" is a computer device that a user operates to create play data, upload it to a server, and receive and check the analysis results.

[0106] An "AI model" is an artificial intelligence program that learns the play data of professional gamers in advance, analyzes the user's play data, and extracts issues and areas for improvement.

[0107] "Professional gamer play data" refers to information such as operation logs and video files generated by professional gamers while playing games.

[0108] A "parseable format" is a specific data format that an AI model requires to parse play data.

[0109] "Operation log data" is data that records operations and actions performed by a user while playing a game.

[0110] The "time stamped format" is a data format in which time information is added to the operation log.

[0111] "Analysis results" are information on issues and areas for improvement derived after the AI ​​model analyzes the user's play data.

[0112] "Feedback" is information used to present analysis results and areas for improvement to the user.

[0113] The "interface" is the part of the software that allows the user to send and receive data to and from the server and view feedback.

[0114] This system allows users to provide their own gameplay data, which is then analyzed by an AI model, which then presents specific issues and areas for improvement. This system consists of a user's device, a server, and an AI model.

[0115] System Configuration

[0116] 1. User's device

[0117] The user's terminal is a device for playing games and creating game data. The user records their gameplay and saves the play data on the terminal. The saved play data is uploaded to the server via the terminal. The terminal also receives feedback from the server and provides an interface that the user can check.

[0118] 2. Server

[0119] The server receives gameplay data uploaded by users and saves it in a designated directory. The received data is converted into an analyzable format, and the converted data is sent to the AI ​​model. The server then processes the analysis results from the AI ​​model into a format that is easy for users to understand. Examples include text reports, graphical dashboards, and lists of specific improvements.

[0120] 3. AI Model

[0121] The AI ​​model learns from professional gamer play data in advance and analyzes the user's play data. The AI ​​model compares the user's actions and tactics with the professional gamer data to identify issues and areas for improvement. For example, these include "shooting timing is 0.2 seconds late" or "moving to cover in a specific area is inappropriate."

[0122] Example of a system

[0123] Taking an FPS game as an example, a user uploads a video of their FPS gameplay from their device to a server. The server receives the video data, extracts specific frames, and converts them into an analyzable format. The AI ​​model analyzes the play data and identifies that the user's shooting timing is slower than that of professional gamers or that their cover movement is inappropriate. Based on these analysis results, the server generates a feedback report containing specific improvements, such as "shoot 0.2 seconds earlier" or "move to cover more quickly in certain areas," and sends it to the device. The user can then review the feedback on their device and put it into practice the next time they play the game.

[0124] Prompt Sentence Examples

[0125] You can request an analysis from the AI ​​model by entering a prompt like the one below.

[0126] "Please analyze my latest FPS gameplay video and let me know what specific improvements I can make."

[0127] "Based on this play data, please tell me what I need to improve on compared to professional gamers."

[0128] The present invention allows users to effectively analyze their own gameplay data and understand specific issues and areas for improvement, thereby providing specific guidance for users to improve their gaming skills.

[0129] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0130] Step 1: Creating and uploading user play data

[0131] Users record their own gameplay and save the play data on their device. Then, they upload the recorded play data to the server through the device interface. The input is the user's gameplay data (e.g., "gameplay.mp4"), and the output is the play data uploaded to the server. Specifically, users press the "Upload" button, select a file, and send it to the server.

[0132] Step 2: Receiving and saving your play data

[0133] The server receives the play data sent by the user and saves it in a temporary buffer. It then moves and saves the received play data to a specified save directory. The input is the play data sent by the user, and the output is the play data stored in the save directory. Specifically, the play data is saved in the " / uploads" directory and is finally moved to the " / processed_data" directory.

[0134] Step 3: Convert your game data

[0135] The server converts the saved play data into an analyzable format. Specifically, it extracts specific frames from the video data and converts them into image files, and converts the operation log data into a format with a timestamp. The input is the play data saved on the server, and the output is the data converted into an analyzable format. Specifically, it extracts one image every 30 frames and saves it as "frame_0001.png" or similar.

[0136] Step 4: Request data analysis

[0137] The server sends the converted play data to the AI ​​model and requests it to analyze it. A specific API is used for sending the data. The input is the converted play data, and the output is the analysis results from the AI ​​model. Specifically, a POST request is sent to "http: / / aimodelserver / analyze" and the converted data is attached and sent.

[0138] Step 5: Receiving and processing the analysis results

[0139] The server receives the analysis results from the AI ​​model and processes them into a format that is easy for users to understand. The input is the analysis results obtained from the AI ​​model, and the output is feedback that can be viewed by the user. Specific operations include generating text reports, graphical dashboards, and lists of specific areas for improvement. For example, information such as "insufficient cover movement" can be expressed as "rapid cover movement should be performed in specific areas."

[0140] Step 6: Submit and view feedback

[0141] The server sends the generated feedback report to the user's device. The device then visually displays the received feedback to the user. The input is the processed feedback, and the output is the feedback information viewed by the user. Specifically, the feedback report is saved as "feedback_username_timestamp.pdf" and displayed to the user. For example, graphs and text explanations can be displayed using a PDF viewer.

[0142] The above are the specific processing steps of the program for this system.

[0143] (Application example 1)

[0144] 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."

[0145] Conventional factory robot operation management systems have had difficulty providing specific feedback to optimize robot operation efficiency and productivity, which has resulted in insufficient improvement in production efficiency and robot operating efficiency within the factory, making it difficult to achieve an optimized production process.

[0146] 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.

[0147] In this invention, the server includes means for receiving operation data provided by a user, means for converting the received operation data into an analyzable format, means for comparing and analyzing the converted data with pre-trained professional operation data, means for collecting operation data from a factory robot and analyzing it in real time to improve specific work efficiency, means for extracting user issues and areas for improvement based on the analysis results, and means for presenting the extracted issues and areas for improvement to the user. This makes it possible to analyze the operation efficiency of a factory robot in real time and provide specific areas for improvement to the user.

[0148] "User-provided operational data" refers to data about specific operations and behaviors collected from devices or systems operated by users.

[0149] "Converting into an analyzable format" refers to converting the collected raw data into a data format that can be interpreted and analyzed by AI or machine learning models.

[0150] "Comparative analysis" refers to comparing newly collected data with data from professionals who have already studied it, and evaluating and analyzing it using the same standards.

[0151] "Extracting issues and areas for improvement" refers to identifying, from the analysis results, problems with user behavior and operations and specific areas for improvement to improve efficiency.

[0152] "Presenting to the user" means providing the analysis results to the user in an easy-to-understand format so that the user can easily understand and use the results.

[0153] "Real-time analysis" refers to processing collected data immediately and generating analysis results without delay.

[0154] A "factory robot" refers to an automated machine installed to automate manufacturing operations and tasks.

[0155] The present invention provides a system that analyzes the operation data of a factory robot and presents problems and areas for improvement in real time. Specific embodiments of the system will be described below.

[0156] System Configuration

[0157] The system consists of a user's device, a server, and an AI model.

[0158] 1. On the user's device:

[0159] Tablet terminal: Used in the factory to collect robot operation data and send it to a server.

[0160] Data collection software using the MQTT protocol is used to collect data.

[0161] Additionally, an interface is provided that visually displays feedback from the server.

[0162] 2. Server:

[0163] Data reception and storage: Receives and stores operational data sent from the user terminal.

[0164] Data conversion: Converts received data into a parsable format (JSON format).

[0165] Software used: Dedicated server software is used for data collection and conversion.

[0166] Execution of AI models: Run AI models using deep learning frameworks such as TensorFlow and perform analysis.

[0167] Feedback generation: Based on the analysis results, a detailed feedback report is generated and sent to the user's device.

[0168] 3. AI model:

[0169] Data analysis: Based on the converted data, compare it with professional operational data to identify bottlenecks and issues.

[0170] Extraction of issues and improvements: Identify problems and improvements in the user's behavior and send them back to the server.

[0171] System Operation

[0172] The server receives the operational data provided by the user and converts it into an analyzable format. The converted data is sent to the AI ​​model and compared with professional data. Based on the analysis results, the user's issues and areas for improvement are extracted and the results are presented to the user. Specifically, it works as follows:

[0173] Hardware and Software

[0174] 1. Hardware:

[0175] Factory robots: Used as a source of operational data.

[0176] Tablet device: For data collection and feedback display.

[0177] 2. Software:

[0178] Data collection software: Software for collecting operational data from factory robots in real time and sending it to a server.

[0179] Server software: receives, stores, converts, and analyzes data.

[0180] AI model: Utilizes TensorFlow framework to analyze behavioral data and compare it with professional data.

[0181] Specific examples

[0182] For example, if a factory robot's operations are delayed, collecting operational data and analyzing it in real time will reveal that certain operations are slower than others. As a result of the analysis, feedback such as "The robot is slow when moving a specific part. The operation speed should be reduced by 0.5 seconds" is provided.

[0183] Prompt Sentence Examples

[0184] Here are some example prompts to input to the generative AI model:

[0185] Based on the operation data of a factory robot, please propose specific improvements to improve efficiency. The following is an example of operation data: {"Operation Data": [{"Operation 1": 1.2 seconds, "Operation 2": 0.8 seconds, ...}]}

[0186] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0187] Step 1:

[0188] Collecting user behavior data

[0189] Input: Factory robot operation data

[0190] The server receives real-time robot operation data from the user's device (tablet) via the MQTT protocol. This data is sent as raw data.

[0191] Output: raw data collected

[0192] Step 2:

[0193] Saving operation data

[0194] Input: Raw data collected

[0195] The server saves the received operational data in the specified directory in the format used for secondary storage of raw data.

[0196] Output: Saved operation data file

[0197] Step 3:

[0198] Data transformation

[0199] Input: Saved motion data file

[0200] The server converts the raw data into a JSON format that can be analyzed. For example, it extracts necessary metrics (such as operation time, distance traveled, and number of operations) from the raw data and converts them into log data with timestamps.

[0201] Output: Parsable data in JSON format

[0202] Step 4:

[0203] Sending data to the AI ​​model

[0204] Input: Parsable data in JSON format

[0205] The server then sends the converted data to the AI ​​model, typically using HTTP or gRPC as the transmission protocol.

[0206] Output: Send request to AI model

[0207] Step 5:

[0208] Analysis using AI models

[0209] Input: Parsable data sent by the server

[0210] The AI ​​model compares the received data with that of the professional, evaluating, for example, movement timing, efficiency, and movement patterns, and identifies discrepancies.

[0211] Output: Analysis results including issues and improvements

[0212] Step 6:

[0213] Generate feedback

[0214] Input: Analysis results including issues and improvements

[0215] The server generates a detailed feedback report based on the analysis results, which includes text instructions, graphs, and charts.

[0216] Output: Feedback report

[0217] Step 7:

[0218] Providing feedback to the user

[0219] Input: Feedback Report

[0220] The terminal visually displays the feedback reports received from the server, laid out on an interface that is easy for the user to understand.

[0221] Output: Feedback displayed on the user interface

[0222] 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.

[0223] The present invention relates to a system that uses an AI model to analyze play data provided by a user and presents the user with issues and areas for improvement. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide feedback that combines the analysis results with the user's emotional state. Specific embodiments of the system are described below.

[0224] System Configuration

[0225] This system consists of a user's device, a server, an AI model, and an emotion engine.

[0226] 1. On the user's device:

[0227] The user plays the game and creates play data.

[0228] Its role is to upload play data to the server and receive and check feedback.

[0229] The camera and microphone are used to capture the user's facial expressions and voice and send them to the emotion engine.

[0230] 2. Server:

[0231] Receives and stores play data and converts it into an analyzable format.

[0232] The converted data is passed to the AI ​​model and the analysis results are received.

[0233] Receives user emotion data and passes it to the emotion engine.

[0234] The analysis results are integrated with emotional data to generate a feedback report for the user.

[0235] 3. AI model:

[0236] The system learns the play data of professional gamers in advance and analyzes the user's play data.

[0237] Evaluate user actions and tactics to identify issues and areas for improvement.

[0238] 4. Emotion Engine:

[0239] It analyzes the user's facial expressions and voice while playing to recognize their emotional state (e.g., joy, anger, surprise, etc.).

[0240] The recognized emotion data is sent to the server.

[0241] System action

[0242] The system has a series of steps from uploading the user's play data to providing feedback. The specific operation of each component is as follows:

[0243] Server Operation

[0244] Receiving play data:

[0245] The server receives play data uploaded by the user and stores it in a storage directory. It also receives emotion data based on the user's facial expressions and voice data.

[0246] Transforming data:

[0247] The server converts the saved gameplay data into an analyzable format. For example, it extracts specific frames from video data and adds necessary metadata (timestamps, event logs, etc.). It also converts the operation log data into a unified format.

[0248] Sending data:

[0249] The converted play data is sent to the AI ​​model, and the emotion data is sent to the emotion engine, at the same time issuing an analysis request.

[0250] Receiving and processing analysis results:

[0251] The server receives the analysis results from the AI ​​model and the emotion data from the emotion engine, and combines them to generate feedback for the user, such as a text report, a graphical dashboard, or a list of areas for improvement.

[0252] How AI models work

[0253] Analysis of gameplay data:

[0254] The AI ​​model analyzes the user's movement patterns based on the play data sent from the server, compares it with the play data of professional gamers, and evaluates the user's movements (e.g., shooting timing, movement patterns).

[0255] Identifying issues and areas for improvement:

[0256] Based on the analysis results, the system extracts issues and specific areas for improvement in the user's gameplay, such as "the timing of the shot is 0.2 seconds late" or "moving to cover in a specific area is inappropriate."

[0257] Emotion Engine Operation

[0258] Emotional Data Analysis:

[0259] The emotion engine analyzes the user's facial expressions and voice data sent from the server to recognize the user's emotional state. For example, it quantifies the degree of "joy," "anger," or "surprise" expressed during gameplay.

[0260] Emotional Feedback:

[0261] After recognizing the emotional state, the data is sent to the server, which then integrates it with the analysis results and provides feedback according to the user's emotions.

[0262] Device behavior

[0263] Uploading gameplay and emotion data:

[0264] Users upload their play data and emotional data (facial expressions and voice) from their devices to the server, which then begins analysis on the server side.

[0265] Receiving and viewing feedback:

[0266] The terminal receives the feedback report sent from the server and presents it to the user. The feedback is displayed visually and is provided in a form that is easy for the user to understand and act on.

[0267] Specific examples

[0268] Example 1: Analysis of play data and emotion data in FPS games

[0269] User: Uploads video of their own FPS gameplay, along with facial expressions and audio data from their device to the server.

[0270] Server: Receives video data and converts it into an analyzable format. It also receives facial expression and voice data and sends them to the emotion engine.

[0271] AI model: Analyzes gameplay data and discovers that the user's shooting timing is slower than that of professional gamers, and identifies inappropriate cover movements.

[0272] Emotion engine: Based on facial expressions and voices during gameplay, it recognizes when the user is feeling stressed in a particular situation.

[0273] Server: Integrates the analysis results received from the AI ​​model and emotion engine, generates a feedback report containing specific improvement suggestions such as "You should shoot 0.2 seconds earlier," as well as emotion-based advice such as "You should try breathing exercises to reduce stress in specific areas," and sends it to the device.

[0274] User: Checks the feedback on their device and puts it into practice the next time they play the game. They then upload their play data and emotional data again, and receive continuous feedback using the server and AI model to improve their skills and mental state.

[0275] The processing flow will be explained below.

[0276] Step 1:

[0277] After finishing a game, the user saves the gameplay data (such as replay videos and operation logs) and facial expressions and voice data recorded during gameplay on the device, and then uploads this data to the server using a dedicated application or web interface.

[0278] Step 2:

[0279] The server receives play data uploaded by the user and saves it in a specified directory. It also receives the user's facial expression and voice data and prepares them for transmission to the emotion engine.

[0280] Step 3:

[0281] The server converts the saved gameplay data into an analyzable format. For example, it extracts specific frames from video data and adds necessary metadata (timestamps, event logs, etc.). It also converts the operation log data into a unified format.

[0282] Step 4:

[0283] The server sends the converted play data to the AI ​​model. At the same time, it sends the user's facial expressions and voice data to the emotion engine, and issues an analysis request.

[0284] Step 5:

[0285] The AI ​​model receives the transmitted play data and analyzes the user's movement patterns. It compares this with the play data of professional gamers, evaluates the user's movements (shooting timing, movement patterns, etc.), and analyzes the differences.

[0286] Step 6:

[0287] The emotion engine analyzes the facial and voice data sent, recognizes the user's emotional state (happiness, anger, surprise, etc.), and converts it into numerical data.

[0288] Step 7:

[0289] Based on the analysis results, the AI ​​model identifies the user's issues and areas for improvement, such as "the timing of the shot is 0.2 seconds late" or "the cover movement in a specific area is inappropriate."

[0290] Step 8:

[0291] The emotion engine sends the recognized emotion data to the server, which evaluates the user's stress level and concentration level in a particular situation based on the emotional state.

[0292] Step 9:

[0293] The server receives the analysis results from the AI ​​model and the emotional data from the emotion engine, and integrates them. For example, it associates the user's challenges in specific actions during gameplay with their emotional state at that time.

[0294] Step 10:

[0295] The server generates a feedback report for the user based on the integrated data, including suggestions for improvement such as "You should shoot 0.2 seconds earlier" and emotion-based advice such as "Try breathing exercises to reduce stress in certain areas."

[0296] Step 11:

[0297] The server generates and sends the feedback report to the user's device, which may include text reports, graphs, heat maps, etc.

[0298] Step 12:

[0299] The device receives the feedback report sent from the server and displays it in an interface that can be viewed by the user. The user can then review the presented issues and improvements and implement them in their next gameplay.

[0300] Step 13:

[0301] Users can use the feedback to implement specific improvements in their next gameplay, upload their play data and emotional data again, and use the server and AI model to receive continuous feedback and improve their skills and mental state.

[0302] Example 2

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

[0304] Conventional play data analysis systems focus on analyzing a user's playing performance and do not consider their emotional state, resulting in insufficient feedback to the user. As a result, it is difficult for users to comprehensively understand both their emotional state and technical issues during play, making it difficult to improve efficiently. This invention aims to integrate and analyze play data and user emotional data to more accurately and comprehensively present users' issues and areas for improvement.

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

[0306] In this invention, the server includes means for receiving data provided by the user, means for converting the received data into an analyzable format, means for comparing and analyzing the converted data with data from experts previously trained, means for extracting the user's issues and areas for improvement based on the analysis results, means for presenting the extracted issues and areas for improvement to the user, means for recognizing the user's emotional state and analyzing the data, and means for integrating the analyzed emotional data with the results of the comparative analysis and providing feedback to the user. This allows the user to comprehensively understand their technical issues and emotional reactions and efficiently improve their performance.

[0307] "Data provided by the user" refers to video data and operation log data that the user records of their own playing status and emotional state.

[0308] "Means for receiving" refers to the software and hardware configuration that allows the server to receive data from the user via the Internet.

[0309] "Means of converting into an analyzable format" refers to the process of converting data received from users into a format that can be analyzed by an AI model, such as by extracting specific frames from videos or standardizing the format of operation logs.

[0310] "Means for comparative analysis" refers to algorithms and AI models that compare the converted data with pre-trained professional data to identify users' playing patterns and technical issues.

[0311] "Means for extracting issues and areas for improvement" refers to the process for automatically identifying technical issues and specific ways to improve users' play data from the analysis results of the AI ​​model.

[0312] "Means of presenting to the user" refers to a user interface and report generation function that displays the extracted issues and areas for improvement in a format that is easy for the user to understand.

[0313] "Means for recognizing emotional state" refers to an algorithm and analysis engine for analyzing and quantifying the emotional state based on the user's facial expressions and voice data while playing.

[0314] "Means for providing feedback" refers to software and hardware configurations for generating text reports and graphical dashboards that integrate technical issues and emotional states to provide easy-to-understand feedback to users.

[0315] MODE FOR CARRYING OUT THE INVENTION

[0316] This invention relates to a system that analyzes play data and emotional data provided by users, extracts and presents the user's issues and areas for improvement. This system is composed of a user terminal, a server, an AI model, and an emotional engine.

[0317] System Configuration

[0318] 1. On the user's device:

[0319] A user plays a game and creates play data (video data and operation log data).

[0320] Its role is to upload play data and emotional data (facial expressions and voice data) to the server and receive and confirm feedback. Files are selected and uploaded via a dedicated application or web interface.

[0321] At this time, the user's facial expressions and voice are captured using a camera and microphone and sent to the server as emotional data.

[0322] 2. Server:

[0323] The server receives gameplay data uploaded by users and saves it in a specified directory. The saved data is then converted into an analyzable format. For example, specific frames are extracted from video data, necessary metadata is added, and operation log data is converted into a unified format.

[0324] The converted play data is sent to the AI ​​model, which issues an analysis request. Emotion data is also sent to the emotion engine, which issues an emotion analysis request.

[0325] It receives the analysis results from the AI ​​model and the emotion engine, integrates them, and generates a feedback report for the user, which is provided in a format that is easy for the user to understand.

[0326] 3. AI model:

[0327] Based on the play data sent from the server, the user's movement patterns are analyzed by comparing them with the play data of professionals, using an AI model that has been trained in advance using the play data of professionals.

[0328] Based on the analysis results, technical issues and specific areas for improvement can be identified. For example, specific suggestions such as "the timing of shooting is delayed" or "moving to cover in a specific area is inappropriate" can be made.

[0329] 4. Emotion Engine:

[0330] The system analyzes the user's facial expressions and voice data sent from the server to recognize the user's emotional state. For example, it quantifies emotional states such as "joy," "anger," and "surprise" while playing.

[0331] The recognized emotion data is sent to the server, which then integrates it with the analysis results and provides feedback that takes the user's emotion data into account.

[0332] Specific examples

[0333] Example 1: Analysis of play data and emotion data in FPS games

[0334] User: After playing an FPS game, upload the gameplay video and facial expressions and voice data (emotion data) recorded during the gameplay to the server using a dedicated app. Click the upload button in the app, select the file, and then use the "Upload" button.

[0335] Server: Receives video data and converts it into an analyzable format. It adds metadata (timestamps, event logs) and converts operation log data into a unified format. It also sends facial expression and voice data to the emotion engine.

[0336] AI model: Analyzes gameplay data and detects when a user's shooting timing is delayed compared to a professional. It also identifies inappropriate cover movement. For example, it detects when a user's shooting timing is delayed by 0.2 seconds.

[0337] Emotion engine: Based on facial expressions and voices during gameplay, it recognizes when a user is feeling stressed in a particular situation. For example, it recognizes that "stress levels are high in a particular area."

[0338] Server: Integrates the analysis results from the AI ​​model and emotion engine to generate a feedback report with specific improvements such as "the timing of the shot should be advanced by 0.2 seconds" as well as emotion-based advice such as "try breathing exercises to reduce stress in specific areas."

[0339] User: Checks the feedback on their device and puts it into practice the next time they play the game. They then upload their play data and emotional data again, and receive continuous feedback using the server and AI model to improve their skills and mental state.

[0340] Examples of prompt statements

[0341] "Based on gameplay data and emotional data from FPS games, analyze users' issues and areas for improvement and provide specific feedback. For example, if a user's shooting timing is slow, provide specific ways to improve, and include advice on how to relax for users who are feeling stressed."

[0342] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0343] Step 1: Upload your gameplay data

[0344] Users upload gameplay videos and emotional data (facial expressions and voice) from their own devices to the server. Specifically, they use a dedicated application or web interface to select the gameplay data file and emotional data and click the "Upload" button.

[0345] Input: Gameplay video, operation log data, facial expression and voice data.

[0346] Output: The data uploaded to the server.

[0347] Step 2: Saving gameplay data and emotion data

[0348] The server receives play data and emotion data uploaded by users and temporarily stores them in a specified directory. It manages the data by dividing it into folders based on the user's identification information.

[0349] Input: Uploaded data.

[0350] Output: Data saved in the save directory.

[0351] Step 3: Convert your game data

[0352] The server converts the saved gameplay data into an analyzable format. Specifically, it extracts specific frames from the video data, adds necessary metadata (timestamps, event logs), and converts the operation log data into a unified format.

[0353] Input: Saved play data.

[0354] Output: Transformed, parseable data.

[0355] Step 4: Issue an analysis request and send data

[0356] The server sends the converted play data to the AI ​​model and issues an analysis request. At the same time, it also sends the emotion data to the emotion engine and issues an emotion analysis request. Specifically, it sends the data to the AI ​​model and emotion engine via an API request.

[0357] Input: Converted play data, emotion data.

[0358] Output: Data sent to the AI ​​model and emotion engine.

[0359] Step 5: Analyzing play data with an AI model

[0360] The AI ​​model receives play data sent from the server and compares it with professional play data to analyze the user's movement patterns, specifically evaluating shooting timing and movement patterns to identify the user's technical issues.

[0361] Input: Play data sent to the AI ​​model.

[0362] Output: Analysis results including technical issues and improvements.

[0363] Step 6: Analyze the sentiment data

[0364] The emotion engine analyzes the user's facial expressions and voice data sent from the server to recognize the user's emotional state, quantifying the degree of the emotional state and identifying the emotional response in a specific situation.

[0365] Input: Facial and speech data sent to the emotion engine.

[0366] Output: Quantified data indicating emotional state.

[0367] Step 7: Integrating analysis results with emotion data

[0368] The server receives the analysis results from the AI ​​model and the emotional data from the emotion engine, and then integrates them to generate a feedback report for the user. Specifically, it creates feedback that encompasses both technical and emotional issues.

[0369] Input: Analysis results, emotion data.

[0370] Output: Consolidated feedback report.

[0371] Step 8: Generate and display feedback

[0372] The server sends the generated feedback report to the user's device, which visually displays the received feedback and provides it to the user in a format that is easy for the user to understand, such as through a text report or a graphical dashboard.

[0373] Input: Consolidated feedback report.

[0374] Output: Feedback displayed on the user's terminal.

[0375] (Application example 2)

[0376] 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."

[0377] Simply analyzing motion data is insufficient for improving user performance and solving problems. More effective feedback is needed, especially by taking into account the operator's emotional state. However, currently there is no system that can integrate and analyze motion data and emotional data and provide accurate feedback based on that. Therefore, the realization of a system that can simultaneously analyze a user's motion and emotional state and provide comprehensive feedback that takes both into account is a challenge.

[0378] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving motion data provided by the user, means for converting the received motion data into an analyzable format, means for comparing and analyzing the converted data with pre-trained reference data, means for extracting the user's issues and areas for improvement based on the analysis results, means for analyzing the user's facial expression and voice data to recognize their emotional state, and means for integrating the analysis results and the emotional data and presenting feedback to the user. This enables comprehensive and effective feedback that takes into account both the user's motion performance and emotional state.

[0379] "Operation data" refers to data relating to actions and operations provided by the user, and includes the patterns and timing of those actions, error information, and the like.

[0380] An "analyzable format" is data received that has been converted into a format suitable for analysis by machine learning models and algorithms.

[0381] "Reference data" refers to data that has been learned in advance, and includes, as specific standards, best practices from other users and data from professionals.

[0382] "Issues" refer to problems or areas that need improvement in the user's actions or operations.

[0383] "Improvements" refer to specific methods or suggestions for making user actions or operations more efficient and effective.

[0384] "Facial expression data" is data obtained from the user's facial expressions, and serves as a basis for analyzing the emotional state.

[0385] "Voice data" is data obtained from the user's vocalizations and tone of voice, and serves as the basis for analyzing the emotional state.

[0386] "Emotional state" refers to the user's emotional state, and is expressed as numerical values ​​or categories of emotions such as stress, joy, surprise, etc.

[0387] "Feedback" refers to specific improvement suggestions and advice provided to users based on the analysis results and emotional data.

[0388] The present invention is a system that integrates and analyzes motion data and emotion data, and provides feedback to the user on areas for improvement based on the results. Specifically, the system receives the user's motion data and emotion data and analyzes them on a server to improve the user's performance. The specific system configuration and operation are described below.

[0389] System Configuration

[0390] This system consists of the following elements:

[0391] 1. On the user's device:

[0392] Operational data: Collecting data on user operations and behavior. Specific examples include operation logs on a manufacturing line and machine operation logs.

[0393] Emotion data: The camera and microphone are used to capture the user's facial expressions and voice.

[0394] 2. Server:

[0395] Data reception: Receives and stores the motion data and emotion data sent from the user's device.

[0396] Data conversion: Converts received data into an analyzable format. This process involves extracting specific frames from video data and adding timestamps and event logs.

[0397] Data analysis: The converted data is analyzed using an AI model and emotion engine to identify the user's issues and areas for improvement. The AI ​​model compares the user's movements with those of professionals and evaluates their movements.

[0398] Feedback generation: Integrates analysis results and emotional data to generate feedback for users, including specific improvements and advice.

[0399] 3. AI model:

[0400] Movement data analysis: An AI model that has learned from professional movement data performs comparative analysis with the user's movement data.

[0401] Identifying issues: Identifying delays and errors in user actions and extracting areas for improvement.

[0402] 4. Emotion Engine:

[0403] Emotion analysis: Analyzes the user's facial expression and voice data to quantify their emotional state.

[0404] Emotional feedback: Based on the user's emotional state, the areas where the user is feeling stressed or tired are identified and reflected in the analysis results.

[0405] System Operation

[0406] The server receives the user's motion and emotion data, integrates it, and converts it into an analyzable format. It then analyzes the data using an AI model and emotion engine, identifying issues and areas for improvement based on the analysis results. It then integrates the analysis results with the emotion data and provides feedback to the user. The feedback includes not only specific improvements for improving motion efficiency and reducing errors, but also advice that takes into account the operator's emotional aspects, such as stress management and improving concentration.

[0407] Specific examples

[0408] For example, if the system performs analysis based on data provided by an operator working on a production line, it may generate the following feedback: "Operation delay time: 0.2 seconds. Number of operation errors: 5. Stress level: High. Suggested improvement: Increase operator breaks to increase operation speed and reduce the occurrence of errors."

[0409] Prompt Sentence Examples

[0410] An example prompt for using a generative model: "Analyze the robot operation data and the operator's emotional data, and generate specific feedback for operational efficiency and error correction."

[0411] The present invention enables comprehensive and effective feedback that takes into account both the user's motion performance and emotional state.

[0412] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0413] Step 1:

[0414] Users collect their own motion data and emotional data on their devices. Motion data includes operation logs and machine operation logs. Emotion data is captured using a camera and microphone to capture facial expressions and voice. The collected data is temporarily stored in the device (input: user motion data, facial expression data, voice data / output: temporarily stored data).

[0415] Step 2:

[0416] The device uploads the collected motion and emotion data to a server, which receives the data and stores it in dedicated storage (input: temporary data / output: server storage).

[0417] Step 3:

[0418] The server converts the received motion data into an analyzable format. For example, it extracts specific frames from video data and adds timestamps and event logs. It also converts the operation log into a unified format (input: motion data, emotion data / output: analyzable format data).

[0419] Step 4:

[0420] The server sends the converted motion data to the AI ​​model, which then compares it with the professional's motion data to analyze the user's motion and identify issues and areas for improvement (input: data in an analyzable format / output: list of issues and areas for improvement).

[0421] Step 5:

[0422] The server sends facial expression data and voice data to the emotion engine, which analyzes the user's emotional state and expresses it in numerical values ​​and categories (input: facial expression data, voice data / output: emotional state data).

[0423] Step 6:

[0424] The server integrates the motion analysis results from the AI ​​model with the emotional state data from the emotion engine. Based on this integrated data, it generates feedback for the user. The feedback includes specific improvements to improve motion efficiency and reduce errors, as well as advice that takes emotional aspects into consideration (input: list of issues and improvements, emotional state data; output: feedback report).

[0425] Step 7:

[0426] The server sends the generated feedback report to the user's device, where the user can check the report and implement specific improvement measures (input: feedback report / output: user checks and implements feedback).

[0427] These steps provide comprehensive feedback that takes into account the user's motion performance and emotional state, resulting in motion efficiency and error improvement.

[0428] 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.

[0429] 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.

[0430] 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.

[0431] [Second embodiment]

[0432] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0433] 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.

[0434] 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).

[0435] 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.

[0436] 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.

[0437] 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).

[0438] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0439] 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.

[0440] 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.

[0441] 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.

[0442] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0443] 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."

[0444] The present invention is a system in which a user provides their own gameplay data, an AI model analyzes the data, and presents specific issues and areas for improvement. Specific embodiments of the system are described below.

[0445] System Configuration

[0446] This system consists of a user's terminal, a server, and an AI model.

[0447] 1. On the user's device:

[0448] Users play the game and create play data, which is also responsible for uploading the play data to the server.

[0449] Receive feedback and provide an interface for users to review.

[0450] 2. Server:

[0451] Receives and stores play data and converts it into an analyzable format.

[0452] The converted data is passed to the AI ​​model and the analysis results are received.

[0453] The analysis results are processed into a user-friendly format and sent to the terminal.

[0454] 3. AI model:

[0455] The system learns the play data of professional gamers in advance and analyzes the user's play data.

[0456] Compare user actions and tactics with professional gamer data to identify issues and areas for improvement.

[0457] System action

[0458] This system's processing consists of a series of steps, from uploading the user's play data to providing feedback. The specific operation of each component is as follows:

[0459] Server Operation

[0460] Receiving play data:

[0461] The server receives play data uploaded by users. The received data is first saved in a specified directory.

[0462] Transforming data:

[0463] The server converts the saved play data into an analyzable format, for example, by extracting specific frames from video data and converting operation log data into a time-stamped format.

[0464] Sending data:

[0465] The converted play data is sent to the AI ​​model, which then performs analysis based on this data.

[0466] Receiving and processing analysis results:

[0467] The server receives the analysis results from the AI ​​model and processes them into a user-friendly format, such as a text report, a graphical dashboard, or a list of specific improvements.

[0468] How AI models work

[0469] Analysis of gameplay data:

[0470] The AI ​​model analyzes the user's actions and tactics based on the play data received from the server. Specifically, it compares the play data with that of professional gamers and evaluates the user's movement patterns, reaction speed, tactical decisions, etc.

[0471] Identifying issues and areas for improvement:

[0472] Based on the analysis results, the system extracts issues in the user's gameplay and specific areas for improvement, such as "the timing of the shot is 0.2 seconds late" or "moving to cover in a specific area is inappropriate."

[0473] Device behavior

[0474] Uploading gameplay data:

[0475] The user uploads their gameplay data from their device to the server, which then begins analysis on the server side.

[0476] Receiving and viewing feedback:

[0477] The terminal receives the feedback sent from the server and presents it to the user. The feedback is displayed visually and is provided in a form that is easy for the user to understand and put into action.

[0478] Specific examples

[0479] Example 1: Analysis of play data in FPS games

[0480] Users upload their FPS gameplay videos from their devices to a server.

[0481] The server receives the video data, extracts specific frames, and converts them into an analyzable format.

[0482] The AI ​​model analyzes gameplay data and discovers that the user's shooting timing is slower than that of professional gamers, and identifies improper cover movements.

[0483] Based on the analysis results received from the AI ​​model, the server generates a feedback report containing specific improvements, such as "the timing of the shot should be advanced by 0.2 seconds" or "quickly move to cover in specific areas," and sends it to the device.

[0484] Users can view the feedback on their device and put it into practice the next time they play the game.

[0485] The processing flow will be explained below.

[0486] Step 1:

[0487] After finishing a game, the user prepares the gameplay data (such as a replay video or operation log), and then uploads the gameplay data to the server using a dedicated application or web interface on the device.

[0488] Step 2:

[0489] The server receives play data uploaded by users and stores it in a storage directory. This storage process includes checking the integrity of the data when it is received.

[0490] Step 3:

[0491] The server converts the saved gameplay data into an analyzable format. For example, it extracts specific frames from video data and adds necessary metadata (timestamps, event logs, etc.). It also converts the operation log data into a unified format.

[0492] Step 4:

[0493] The server passes the converted data to the AI ​​model, and at the same time issues an analysis request.

[0494] Step 5:

[0495] The AI ​​model receives the transmitted play data and analyzes the user's movement patterns. For example, it compares the play data of professional gamers to evaluate the user's movements (shooting timing, movement patterns, etc.). The AI ​​model also compares the user's play data with the professional gamer's standards to perform a discrepancy analysis.

[0496] Step 6:

[0497] The AI ​​model generates analysis results and identifies the user's issues and areas for improvement. For example, specific problems such as "firing timing is 0.2 seconds late" or "cover movement is slow in certain areas" are summarized in text format along with how to improve them.

[0498] Step 7:

[0499] Based on the analysis results received from the AI ​​model, the server generates feedback reports for the user, including text reports, graphical dashboards, and lists of specific areas for improvement, as well as graphs and heat maps for visual coaching.

[0500] Step 8:

[0501] The server sends the generated feedback report to the user's device, and the analysis results are reflected on the user's personal dashboard.

[0502] Step 9:

[0503] The device receives the feedback report sent from the server and displays it in an interface that the user can view. The user can refer to this to identify problems with their gameplay and use the suggested improvements to prepare for their next gameplay.

[0504] Step 10:

[0505] Users use the feedback to implement specific improvements in their next gameplay, and then upload their gameplay data again to receive continuous feedback using the server and AI model to improve their skills.

[0506] Example 1

[0507] 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."

[0508] Conventional gameplay data analysis systems have struggled to efficiently and effectively analyze user-provided play data and identify specific issues and areas for improvement to improve the user's skills. Furthermore, there has been a lack of a way to present the analysis results in a format that users can easily understand and apply. This has resulted in users being unable to effectively utilize their play data, which has prevented them from improving their skills.

[0509] 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.

[0510] In this invention, the server includes means for receiving play data provided by a user, means for converting the received play data into an analyzable format, means for comparing and analyzing the converted data with play data of previously learned professional gamers, means for extracting issues and areas for improvement for the user based on the analysis results, means for presenting the extracted issues and areas for improvement to the user, means for the user to upload the play data to the server, means for saving the play data in a storage directory, means for extracting specific frames from the play data, means for converting operation log data into a timestamp-added format, means for receiving the analysis results from the server and processing them into a format that is easy for the user to understand, and means for providing an interface for visually displaying feedback to the user. This makes it possible to effectively analyze the user's play data, allowing the user to easily understand specific issues and areas for improvement and put them into action.

[0511] "Play data" refers to information such as operation logs and video files that are generated by the user while playing the game.

[0512] A "server" is a device that receives play data provided by users, stores it, converts it into an analyzable format, sends it to an AI model, and receives the analysis results.

[0513] A "terminal" is a computer device that a user operates to create play data, upload it to a server, and receive and check the analysis results.

[0514] An "AI model" is an artificial intelligence program that learns the play data of professional gamers in advance, analyzes the user's play data, and extracts issues and areas for improvement.

[0515] "Professional gamer play data" refers to information such as operation logs and video files generated by professional gamers while playing games.

[0516] A "parseable format" is a specific data format that an AI model requires to parse play data.

[0517] "Operation log data" is data that records operations and actions performed by a user while playing a game.

[0518] The "time stamped format" is a data format in which time information is added to the operation log.

[0519] "Analysis results" are information on issues and areas for improvement derived after the AI ​​model analyzes the user's play data.

[0520] "Feedback" is information used to present analysis results and areas for improvement to the user.

[0521] The "interface" is the part of the software that allows the user to send and receive data to and from the server and view feedback.

[0522] This system allows users to provide their own gameplay data, which is then analyzed by an AI model, which then presents specific issues and areas for improvement. This system consists of a user's device, a server, and an AI model.

[0523] System Configuration

[0524] 1. User's device

[0525] The user's terminal is a device for playing games and creating game data. The user records their gameplay and saves the play data on the terminal. The saved play data is uploaded to the server via the terminal. The terminal also receives feedback from the server and provides an interface that the user can check.

[0526] 2. Server

[0527] The server receives gameplay data uploaded by users and saves it in a designated directory. The received data is converted into an analyzable format, and the converted data is sent to the AI ​​model. The server then processes the analysis results from the AI ​​model into a format that is easy for users to understand. Examples include text reports, graphical dashboards, and lists of specific improvements.

[0528] 3. AI Model

[0529] The AI ​​model learns from professional gamer play data in advance and analyzes the user's play data. The AI ​​model compares the user's actions and tactics with the professional gamer data to identify issues and areas for improvement. For example, these include "shooting timing is 0.2 seconds late" or "moving to cover in a specific area is inappropriate."

[0530] Example of a system

[0531] Taking an FPS game as an example, a user uploads a video of their FPS gameplay from their device to a server. The server receives the video data, extracts specific frames, and converts them into an analyzable format. The AI ​​model analyzes the play data and identifies that the user's shooting timing is slower than that of professional gamers or that their cover movement is inappropriate. Based on these analysis results, the server generates a feedback report containing specific improvements, such as "shoot 0.2 seconds earlier" or "move to cover more quickly in certain areas," and sends it to the device. The user can then review the feedback on their device and put it into practice the next time they play the game.

[0532] Prompt Sentence Examples

[0533] You can request an analysis from the AI ​​model by entering a prompt like the one below.

[0534] "Please analyze my latest FPS gameplay video and let me know what specific improvements I can make."

[0535] "Based on this play data, please tell me what I need to improve on compared to professional gamers."

[0536] The present invention allows users to effectively analyze their own gameplay data and understand specific issues and areas for improvement, thereby providing specific guidance for users to improve their gaming skills.

[0537] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0538] Step 1: Creating and uploading user play data

[0539] Users record their own gameplay and save the play data on their device. Then, they upload the recorded play data to the server through the device interface. The input is the user's gameplay data (e.g., "gameplay.mp4"), and the output is the play data uploaded to the server. Specifically, users press the "Upload" button, select a file, and send it to the server.

[0540] Step 2: Receiving and saving your play data

[0541] The server receives the play data sent by the user and saves it in a temporary buffer. It then moves and saves the received play data to a specified save directory. The input is the play data sent by the user, and the output is the play data stored in the save directory. Specifically, the play data is saved in the " / uploads" directory and is finally moved to the " / processed_data" directory.

[0542] Step 3: Convert your game data

[0543] The server converts the saved play data into an analyzable format. Specifically, it extracts specific frames from the video data and converts them into image files, and converts the operation log data into a format with a timestamp. The input is the play data saved on the server, and the output is the data converted into an analyzable format. Specifically, it extracts one image every 30 frames and saves it as "frame_0001.png" or similar.

[0544] Step 4: Request data analysis

[0545] The server sends the converted play data to the AI ​​model and requests it to analyze it. A specific API is used for sending the data. The input is the converted play data, and the output is the analysis results from the AI ​​model. Specifically, a POST request is sent to "http: / / aimodelserver / analyze" and the converted data is attached and sent.

[0546] Step 5: Receiving and processing the analysis results

[0547] The server receives the analysis results from the AI ​​model and processes them into a format that is easy for users to understand. The input is the analysis results obtained from the AI ​​model, and the output is feedback that can be viewed by the user. Specific operations include generating text reports, graphical dashboards, and lists of specific areas for improvement. For example, information such as "insufficient cover movement" can be expressed as "rapid cover movement should be performed in specific areas."

[0548] Step 6: Submit and view feedback

[0549] The server sends the generated feedback report to the user's device. The device then visually displays the received feedback to the user. The input is the processed feedback, and the output is the feedback information viewed by the user. Specifically, the feedback report is saved as "feedback_username_timestamp.pdf" and displayed to the user. For example, graphs and text explanations can be displayed using a PDF viewer.

[0550] The above are the specific processing steps of the program for this system.

[0551] (Application example 1)

[0552] 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."

[0553] Conventional factory robot operation management systems have had difficulty providing specific feedback to optimize robot operation efficiency and productivity, which has resulted in insufficient improvement in production efficiency and robot operating efficiency within the factory, making it difficult to achieve an optimized production process.

[0554] 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.

[0555] In this invention, the server includes means for receiving operation data provided by a user, means for converting the received operation data into an analyzable format, means for comparing and analyzing the converted data with pre-trained professional operation data, means for collecting operation data from a factory robot and analyzing it in real time to improve specific work efficiency, means for extracting user issues and areas for improvement based on the analysis results, and means for presenting the extracted issues and areas for improvement to the user. This makes it possible to analyze the operation efficiency of a factory robot in real time and provide specific areas for improvement to the user.

[0556] "User-provided operational data" refers to data about specific operations and behaviors collected from devices or systems operated by users.

[0557] "Converting into an analyzable format" refers to converting the collected raw data into a data format that can be interpreted and analyzed by AI or machine learning models.

[0558] "Comparative analysis" refers to comparing newly collected data with data from professionals who have already studied it, and evaluating and analyzing it using the same standards.

[0559] "Extracting issues and areas for improvement" refers to identifying, from the analysis results, problems with user behavior and operations and specific areas for improvement to improve efficiency.

[0560] "Presenting to the user" means providing the analysis results to the user in an easy-to-understand format so that the user can easily understand and use the results.

[0561] "Real-time analysis" refers to processing collected data immediately and generating analysis results without delay.

[0562] A "factory robot" refers to an automated machine installed to automate manufacturing operations and tasks.

[0563] The present invention provides a system that analyzes the operation data of a factory robot and presents problems and areas for improvement in real time. Specific embodiments of the system will be described below.

[0564] System Configuration

[0565] The system consists of a user's device, a server, and an AI model.

[0566] 1. On the user's device:

[0567] Tablet terminal: Used in the factory to collect robot operation data and send it to a server.

[0568] Data collection software using the MQTT protocol is used to collect data.

[0569] Additionally, an interface is provided that visually displays feedback from the server.

[0570] 2. Server:

[0571] Data reception and storage: Receives and stores operational data sent from the user terminal.

[0572] Data conversion: Converts received data into a parsable format (JSON format).

[0573] Software used: Dedicated server software is used for data collection and conversion.

[0574] Execution of AI models: Run AI models using deep learning frameworks such as TensorFlow and perform analysis.

[0575] Feedback generation: Based on the analysis results, a detailed feedback report is generated and sent to the user's device.

[0576] 3. AI model:

[0577] Data analysis: Based on the converted data, compare it with professional operational data to identify bottlenecks and issues.

[0578] Extraction of issues and improvements: Identify problems and improvements in the user's behavior and send them back to the server.

[0579] System Operation

[0580] The server receives the operational data provided by the user and converts it into an analyzable format. The converted data is sent to the AI ​​model and compared with professional data. Based on the analysis results, the user's issues and areas for improvement are extracted and the results are presented to the user. Specifically, it works as follows:

[0581] Hardware and Software

[0582] 1. Hardware:

[0583] Factory robots: Used as a source of operational data.

[0584] Tablet device: For data collection and feedback display.

[0585] 2. Software:

[0586] Data collection software: Software for collecting operational data from factory robots in real time and sending it to a server.

[0587] Server software: receives, stores, converts, and analyzes data.

[0588] AI model: Utilizes TensorFlow framework to analyze behavioral data and compare it with professional data.

[0589] Specific examples

[0590] For example, if a factory robot's operations are delayed, collecting operational data and analyzing it in real time will reveal that certain operations are slower than others. As a result of the analysis, feedback such as "The robot is slow when moving a specific part. The operation speed should be reduced by 0.5 seconds" is provided.

[0591] Prompt Sentence Examples

[0592] Here are some example prompts to input to the generative AI model:

[0593] Based on the operation data of a factory robot, please propose specific improvements to improve efficiency. The following is an example of operation data: {"Operation Data": [{"Operation 1": 1.2 seconds, "Operation 2": 0.8 seconds, ...}]}

[0594] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0595] Step 1:

[0596] Collecting user behavior data

[0597] Input: Factory robot operation data

[0598] The server receives real-time robot operation data from the user's device (tablet) via the MQTT protocol. This data is sent as raw data.

[0599] Output: raw data collected

[0600] Step 2:

[0601] Saving operation data

[0602] Input: Raw data collected

[0603] The server saves the received operational data in the specified directory in the format used for secondary storage of raw data.

[0604] Output: Saved operation data file

[0605] Step 3:

[0606] Data transformation

[0607] Input: Saved motion data file

[0608] The server converts the raw data into a JSON format that can be analyzed. For example, it extracts necessary metrics (such as operation time, distance traveled, and number of operations) from the raw data and converts them into log data with timestamps.

[0609] Output: Parsable data in JSON format

[0610] Step 4:

[0611] Sending data to the AI ​​model

[0612] Input: Parsable data in JSON format

[0613] The server then sends the converted data to the AI ​​model, typically using HTTP or gRPC as the transmission protocol.

[0614] Output: Send request to AI model

[0615] Step 5:

[0616] Analysis using AI models

[0617] Input: Parsable data sent by the server

[0618] The AI ​​model compares the received data with that of the professional, evaluating, for example, movement timing, efficiency, and movement patterns, and identifies discrepancies.

[0619] Output: Analysis results including issues and improvements

[0620] Step 6:

[0621] Generate feedback

[0622] Input: Analysis results including issues and improvements

[0623] The server generates a detailed feedback report based on the analysis results, which includes text instructions, graphs, and charts.

[0624] Output: Feedback report

[0625] Step 7:

[0626] Providing feedback to the user

[0627] Input: Feedback Report

[0628] The terminal visually displays the feedback reports received from the server, laid out on an interface that is easy for the user to understand.

[0629] Output: Feedback displayed on the user interface

[0630] 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.

[0631] The present invention relates to a system that uses an AI model to analyze play data provided by a user and presents the user with issues and areas for improvement. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide feedback that combines the analysis results with the user's emotional state. Specific embodiments of the system are described below.

[0632] System Configuration

[0633] This system consists of a user's device, a server, an AI model, and an emotion engine.

[0634] 1. On the user's device:

[0635] The user plays the game and creates play data.

[0636] Its role is to upload play data to the server and receive and check feedback.

[0637] The camera and microphone are used to capture the user's facial expressions and voice and send them to the emotion engine.

[0638] 2. Server:

[0639] Receives and stores play data and converts it into an analyzable format.

[0640] The converted data is passed to the AI ​​model and the analysis results are received.

[0641] Receives user emotion data and passes it to the emotion engine.

[0642] The analysis results are integrated with emotional data to generate a feedback report for the user.

[0643] 3. AI model:

[0644] The system learns the play data of professional gamers in advance and analyzes the user's play data.

[0645] Evaluate user actions and tactics to identify issues and areas for improvement.

[0646] 4. Emotion Engine:

[0647] It analyzes the user's facial expressions and voice while playing to recognize their emotional state (e.g., joy, anger, surprise, etc.).

[0648] The recognized emotion data is sent to the server.

[0649] System action

[0650] The system has a series of steps from uploading the user's play data to providing feedback. The specific operation of each component is as follows:

[0651] Server Operation

[0652] Receiving play data:

[0653] The server receives play data uploaded by the user and stores it in a storage directory. It also receives emotion data based on the user's facial expressions and voice data.

[0654] Transforming data:

[0655] The server converts the saved gameplay data into an analyzable format. For example, it extracts specific frames from video data and adds necessary metadata (timestamps, event logs, etc.). It also converts the operation log data into a unified format.

[0656] Sending data:

[0657] The converted play data is sent to the AI ​​model, and the emotion data is sent to the emotion engine, at the same time issuing an analysis request.

[0658] Receiving and processing analysis results:

[0659] The server receives the analysis results from the AI ​​model and the emotion data from the emotion engine, and combines them to generate feedback for the user, such as a text report, a graphical dashboard, or a list of areas for improvement.

[0660] How AI models work

[0661] Analysis of gameplay data:

[0662] The AI ​​model analyzes the user's movement patterns based on the play data sent from the server, compares it with the play data of professional gamers, and evaluates the user's movements (e.g., shooting timing, movement patterns).

[0663] Identifying issues and areas for improvement:

[0664] Based on the analysis results, the system extracts issues and specific areas for improvement in the user's gameplay, such as "the timing of the shot is 0.2 seconds late" or "moving to cover in a specific area is inappropriate."

[0665] Emotion Engine Operation

[0666] Emotional Data Analysis:

[0667] The emotion engine analyzes the user's facial expressions and voice data sent from the server to recognize the user's emotional state. For example, it quantifies the degree of "joy," "anger," or "surprise" expressed during gameplay.

[0668] Emotional Feedback:

[0669] After recognizing the emotional state, the data is sent to the server, which then integrates it with the analysis results and provides feedback according to the user's emotions.

[0670] Device behavior

[0671] Uploading gameplay and emotion data:

[0672] Users upload their play data and emotional data (facial expressions and voice) from their devices to the server, which then begins analysis on the server side.

[0673] Receiving and viewing feedback:

[0674] The terminal receives the feedback report sent from the server and presents it to the user. The feedback is displayed visually and is provided in a form that is easy for the user to understand and act on.

[0675] Specific examples

[0676] Example 1: Analysis of play data and emotion data in FPS games

[0677] User: Uploads video of their own FPS gameplay, along with facial expressions and audio data from their device to the server.

[0678] Server: Receives video data and converts it into an analyzable format. It also receives facial expression and voice data and sends them to the emotion engine.

[0679] AI model: Analyzes gameplay data and discovers that the user's shooting timing is slower than that of professional gamers, and identifies inappropriate cover movements.

[0680] Emotion engine: Based on facial expressions and voices during gameplay, it recognizes when the user is feeling stressed in a particular situation.

[0681] Server: Integrates the analysis results received from the AI ​​model and emotion engine, generates a feedback report containing specific improvement suggestions such as "You should shoot 0.2 seconds earlier," as well as emotion-based advice such as "You should try breathing exercises to reduce stress in specific areas," and sends it to the device.

[0682] User: Checks the feedback on their device and puts it into practice the next time they play the game. They then upload their play data and emotional data again, and receive continuous feedback using the server and AI model to improve their skills and mental state.

[0683] The processing flow will be explained below.

[0684] Step 1:

[0685] After finishing a game, the user saves the gameplay data (such as replay videos and operation logs) and facial expressions and voice data recorded during gameplay on the device, and then uploads this data to the server using a dedicated application or web interface.

[0686] Step 2:

[0687] The server receives play data uploaded by the user and saves it in a specified directory. It also receives the user's facial expression and voice data and prepares them for transmission to the emotion engine.

[0688] Step 3:

[0689] The server converts the saved gameplay data into an analyzable format. For example, it extracts specific frames from video data and adds necessary metadata (timestamps, event logs, etc.). It also converts the operation log data into a unified format.

[0690] Step 4:

[0691] The server sends the converted play data to the AI ​​model. At the same time, it sends the user's facial expressions and voice data to the emotion engine, and issues an analysis request.

[0692] Step 5:

[0693] The AI ​​model receives the transmitted play data and analyzes the user's movement patterns. It compares this with the play data of professional gamers, evaluates the user's movements (shooting timing, movement patterns, etc.), and analyzes the differences.

[0694] Step 6:

[0695] The emotion engine analyzes the facial and voice data sent, recognizes the user's emotional state (happiness, anger, surprise, etc.), and converts it into numerical data.

[0696] Step 7:

[0697] Based on the analysis results, the AI ​​model identifies the user's issues and areas for improvement, such as "the timing of the shot is 0.2 seconds late" or "the cover movement in a specific area is inappropriate."

[0698] Step 8:

[0699] The emotion engine sends the recognized emotion data to the server, which evaluates the user's stress level and concentration level in a particular situation based on the emotional state.

[0700] Step 9:

[0701] The server receives the analysis results from the AI ​​model and the emotional data from the emotion engine, and integrates them. For example, it associates the user's challenges in specific actions during gameplay with their emotional state at that time.

[0702] Step 10:

[0703] The server generates a feedback report for the user based on the integrated data, including suggestions for improvement such as "You should shoot 0.2 seconds earlier" and emotion-based advice such as "Try breathing exercises to reduce stress in certain areas."

[0704] Step 11:

[0705] The server generates and sends the feedback report to the user's device, which may include text reports, graphs, heat maps, etc.

[0706] Step 12:

[0707] The device receives the feedback report sent from the server and displays it in an interface that can be viewed by the user. The user can then review the presented issues and improvements and implement them in their next gameplay.

[0708] Step 13:

[0709] Users can use the feedback to implement specific improvements in their next gameplay, upload their play data and emotional data again, and use the server and AI model to receive continuous feedback and improve their skills and mental state.

[0710] Example 2

[0711] 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."

[0712] Conventional play data analysis systems focus on analyzing a user's playing performance and do not consider their emotional state, resulting in insufficient feedback to the user. As a result, it is difficult for users to comprehensively understand both their emotional state and technical issues during play, making it difficult to improve efficiently. This invention aims to integrate and analyze play data and user emotional data to more accurately and comprehensively present users' issues and areas for improvement.

[0713] 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.

[0714] In this invention, the server includes means for receiving data provided by the user, means for converting the received data into an analyzable format, means for comparing and analyzing the converted data with data from experts previously trained, means for extracting the user's issues and areas for improvement based on the analysis results, means for presenting the extracted issues and areas for improvement to the user, means for recognizing the user's emotional state and analyzing the data, and means for integrating the analyzed emotional data with the results of the comparative analysis and providing feedback to the user. This allows the user to comprehensively understand their technical issues and emotional reactions and efficiently improve their performance.

[0715] "Data provided by the user" refers to video data and operation log data that the user records of their own playing status and emotional state.

[0716] "Means for receiving" refers to the software and hardware configuration that allows the server to receive data from the user via the Internet.

[0717] "Means of converting into an analyzable format" refers to the process of converting data received from users into a format that can be analyzed by an AI model, such as by extracting specific frames from videos or standardizing the format of operation logs.

[0718] "Means for comparative analysis" refers to algorithms and AI models that compare the converted data with pre-trained professional data to identify users' playing patterns and technical issues.

[0719] "Means for extracting issues and areas for improvement" refers to the process for automatically identifying technical issues and specific ways to improve users' play data from the analysis results of the AI ​​model.

[0720] "Means of presenting to the user" refers to a user interface and report generation function that displays the extracted issues and areas for improvement in a format that is easy for the user to understand.

[0721] "Means for recognizing emotional state" refers to an algorithm and analysis engine for analyzing and quantifying the emotional state based on the user's facial expressions and voice data while playing.

[0722] "Means for providing feedback" refers to software and hardware configurations for generating text reports and graphical dashboards that integrate technical issues and emotional states to provide easy-to-understand feedback to users.

[0723] MODE FOR CARRYING OUT THE INVENTION

[0724] This invention relates to a system that analyzes play data and emotional data provided by users, extracts and presents the user's issues and areas for improvement. This system is composed of a user terminal, a server, an AI model, and an emotional engine.

[0725] System Configuration

[0726] 1. On the user's device:

[0727] A user plays a game and creates play data (video data and operation log data).

[0728] Its role is to upload play data and emotional data (facial expressions and voice data) to the server and receive and confirm feedback. Files are selected and uploaded via a dedicated application or web interface.

[0729] At this time, the user's facial expressions and voice are captured using a camera and microphone and sent to the server as emotional data.

[0730] 2. Server:

[0731] The server receives gameplay data uploaded by users and saves it in a specified directory. The saved data is then converted into an analyzable format. For example, specific frames are extracted from video data, necessary metadata is added, and operation log data is converted into a unified format.

[0732] The converted play data is sent to the AI ​​model, which issues an analysis request. Emotion data is also sent to the emotion engine, which issues an emotion analysis request.

[0733] It receives the analysis results from the AI ​​model and the emotion engine, integrates them, and generates a feedback report for the user, which is provided in a format that is easy for the user to understand.

[0734] 3. AI model:

[0735] Based on the play data sent from the server, the user's movement patterns are analyzed by comparing them with the play data of professionals, using an AI model that has been trained in advance using the play data of professionals.

[0736] Based on the analysis results, technical issues and specific areas for improvement can be identified. For example, specific suggestions such as "the timing of shooting is delayed" or "moving to cover in a specific area is inappropriate" can be made.

[0737] 4. Emotion Engine:

[0738] The system analyzes the user's facial expressions and voice data sent from the server to recognize the user's emotional state. For example, it quantifies emotional states such as "joy," "anger," and "surprise" while playing.

[0739] The recognized emotion data is sent to the server, which then integrates it with the analysis results and provides feedback that takes the user's emotion data into account.

[0740] Specific examples

[0741] Example 1: Analysis of play data and emotion data in FPS games

[0742] User: After playing an FPS game, upload the gameplay video and facial expressions and voice data (emotion data) recorded during the gameplay to the server using a dedicated app. Click the upload button in the app, select the file, and then use the "Upload" button.

[0743] Server: Receives video data and converts it into an analyzable format. It adds metadata (timestamps, event logs) and converts operation log data into a unified format. It also sends facial expression and voice data to the emotion engine.

[0744] AI model: Analyzes gameplay data and detects when a user's shooting timing is delayed compared to a professional. It also identifies inappropriate cover movement. For example, it detects when a user's shooting timing is delayed by 0.2 seconds.

[0745] Emotion engine: Based on facial expressions and voices during gameplay, it recognizes when a user is feeling stressed in a particular situation. For example, it recognizes that "stress levels are high in a particular area."

[0746] Server: Integrates the analysis results from the AI ​​model and emotion engine to generate a feedback report with specific improvements such as "the timing of the shot should be advanced by 0.2 seconds" as well as emotion-based advice such as "try breathing exercises to reduce stress in specific areas."

[0747] User: Checks the feedback on their device and puts it into practice the next time they play the game. They then upload their play data and emotional data again, and receive continuous feedback using the server and AI model to improve their skills and mental state.

[0748] Examples of prompt statements

[0749] "Based on gameplay data and emotional data from FPS games, analyze users' issues and areas for improvement and provide specific feedback. For example, if a user's shooting timing is slow, provide specific ways to improve, and include advice on how to relax for users who are feeling stressed."

[0750] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0751] Step 1: Upload your gameplay data

[0752] Users upload gameplay videos and emotional data (facial expressions and voice) from their own devices to the server. Specifically, they use a dedicated application or web interface to select the gameplay data file and emotional data and click the "Upload" button.

[0753] Input: Gameplay video, operation log data, facial expression and voice data.

[0754] Output: The data uploaded to the server.

[0755] Step 2: Saving gameplay data and emotion data

[0756] The server receives play data and emotion data uploaded by users and temporarily stores them in a specified directory. It manages the data by dividing it into folders based on the user's identification information.

[0757] Input: Uploaded data.

[0758] Output: Data saved in the save directory.

[0759] Step 3: Convert your game data

[0760] The server converts the saved gameplay data into an analyzable format. Specifically, it extracts specific frames from the video data, adds necessary metadata (timestamps, event logs), and converts the operation log data into a unified format.

[0761] Input: Saved play data.

[0762] Output: Transformed, parseable data.

[0763] Step 4: Issue an analysis request and send data

[0764] The server sends the converted play data to the AI ​​model and issues an analysis request. At the same time, it also sends the emotion data to the emotion engine and issues an emotion analysis request. Specifically, it sends the data to the AI ​​model and emotion engine via an API request.

[0765] Input: Converted play data, emotion data.

[0766] Output: Data sent to the AI ​​model and emotion engine.

[0767] Step 5: Analyzing play data with an AI model

[0768] The AI ​​model receives play data sent from the server and compares it with professional play data to analyze the user's movement patterns, specifically evaluating shooting timing and movement patterns to identify the user's technical issues.

[0769] Input: Play data sent to the AI ​​model.

[0770] Output: Analysis results including technical issues and improvements.

[0771] Step 6: Analyze the sentiment data

[0772] The emotion engine analyzes the user's facial expressions and voice data sent from the server to recognize the user's emotional state, quantifying the degree of the emotional state and identifying the emotional response in a specific situation.

[0773] Input: Facial and speech data sent to the emotion engine.

[0774] Output: Quantified data indicating emotional state.

[0775] Step 7: Integrating analysis results with emotion data

[0776] The server receives the analysis results from the AI ​​model and the emotional data from the emotion engine, and then integrates them to generate a feedback report for the user. Specifically, it creates feedback that encompasses both technical and emotional issues.

[0777] Input: Analysis results, emotion data.

[0778] Output: Consolidated feedback report.

[0779] Step 8: Generate and display feedback

[0780] The server sends the generated feedback report to the user's device, which visually displays the received feedback and provides it to the user in a format that is easy for the user to understand, such as through a text report or a graphical dashboard.

[0781] Input: Consolidated feedback report.

[0782] Output: Feedback displayed on the user's terminal.

[0783] (Application example 2)

[0784] 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."

[0785] Simply analyzing motion data is insufficient for improving user performance and solving problems. More effective feedback is needed, especially by taking into account the operator's emotional state. However, currently there is no system that can integrate and analyze motion data and emotional data and provide accurate feedback based on that. Therefore, the realization of a system that can simultaneously analyze a user's motion and emotional state and provide comprehensive feedback that takes both into account is a challenge.

[0786] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving motion data provided by the user, means for converting the received motion data into an analyzable format, means for comparing and analyzing the converted data with pre-trained reference data, means for extracting the user's issues and areas for improvement based on the analysis results, means for analyzing the user's facial expression and voice data to recognize their emotional state, and means for integrating the analysis results and the emotional data and presenting feedback to the user. This enables comprehensive and effective feedback that takes into account both the user's motion performance and emotional state.

[0787] "Operation data" refers to data relating to actions and operations provided by the user, and includes the patterns and timing of those actions, error information, and the like.

[0788] An "analyzable format" is data received that has been converted into a format suitable for analysis by machine learning models and algorithms.

[0789] "Reference data" refers to data that has been learned in advance, and includes, as specific standards, best practices from other users and data from professionals.

[0790] "Issues" refer to problems or areas that need improvement in the user's actions or operations.

[0791] "Improvements" refer to specific methods or suggestions for making user actions or operations more efficient and effective.

[0792] "Facial expression data" is data obtained from the user's facial expressions, and serves as a basis for analyzing the emotional state.

[0793] "Voice data" is data obtained from the user's vocalizations and tone of voice, and serves as the basis for analyzing the emotional state.

[0794] "Emotional state" refers to the user's emotional state, and is expressed as numerical values ​​or categories of emotions such as stress, joy, surprise, etc.

[0795] "Feedback" refers to specific improvement suggestions and advice provided to users based on the analysis results and emotional data.

[0796] The present invention is a system that integrates and analyzes motion data and emotion data, and provides feedback to the user on areas for improvement based on the results. Specifically, the system receives the user's motion data and emotion data and analyzes them on a server to improve the user's performance. The specific system configuration and operation are described below.

[0797] System Configuration

[0798] This system consists of the following elements:

[0799] 1. On the user's device:

[0800] Operational data: Collecting data on user operations and behavior. Specific examples include operation logs on a manufacturing line and machine operation logs.

[0801] Emotion data: The camera and microphone are used to capture the user's facial expressions and voice.

[0802] 2. Server:

[0803] Data reception: Receives and stores the motion data and emotion data sent from the user's device.

[0804] Data conversion: Converts received data into an analyzable format. This process involves extracting specific frames from video data and adding timestamps and event logs.

[0805] Data analysis: The converted data is analyzed using an AI model and emotion engine to identify the user's issues and areas for improvement. The AI ​​model compares the user's movements with those of professionals and evaluates their movements.

[0806] Feedback generation: Integrates analysis results and emotional data to generate feedback for users, including specific improvements and advice.

[0807] 3. AI model:

[0808] Movement data analysis: An AI model that has learned from professional movement data performs comparative analysis with the user's movement data.

[0809] Identifying issues: Identifying delays and errors in user actions and extracting areas for improvement.

[0810] 4. Emotion Engine:

[0811] Emotion analysis: Analyzes the user's facial expression and voice data to quantify their emotional state.

[0812] Emotional feedback: Based on the user's emotional state, the areas where the user is feeling stressed or tired are identified and reflected in the analysis results.

[0813] System Operation

[0814] The server receives the user's motion and emotion data, integrates it, and converts it into an analyzable format. It then analyzes the data using an AI model and emotion engine, identifying issues and areas for improvement based on the analysis results. It then integrates the analysis results with the emotion data and provides feedback to the user. The feedback includes not only specific improvements for improving motion efficiency and reducing errors, but also advice that takes into account the operator's emotional aspects, such as stress management and improving concentration.

[0815] Specific examples

[0816] For example, if the system performs analysis based on data provided by an operator working on a production line, it may generate the following feedback: "Operation delay time: 0.2 seconds. Number of operation errors: 5. Stress level: High. Suggested improvement: Increase operator breaks to increase operation speed and reduce the occurrence of errors."

[0817] Prompt Sentence Examples

[0818] An example prompt for using a generative model: "Analyze the robot operation data and the operator's emotional data, and generate specific feedback for operational efficiency and error correction."

[0819] The present invention enables comprehensive and effective feedback that takes into account both the user's motion performance and emotional state.

[0820] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0821] Step 1:

[0822] Users collect their own motion data and emotional data on their devices. Motion data includes operation logs and machine operation logs. Emotion data is captured using a camera and microphone to capture facial expressions and voice. The collected data is temporarily stored in the device (input: user motion data, facial expression data, voice data / output: temporarily stored data).

[0823] Step 2:

[0824] The device uploads the collected motion and emotion data to a server, which receives the data and stores it in dedicated storage (input: temporary data / output: server storage).

[0825] Step 3:

[0826] The server converts the received motion data into an analyzable format. For example, it extracts specific frames from video data and adds timestamps and event logs. It also converts the operation log into a unified format (input: motion data, emotion data / output: analyzable format data).

[0827] Step 4:

[0828] The server sends the converted motion data to the AI ​​model, which then compares it with the professional's motion data to analyze the user's motion and identify issues and areas for improvement (input: data in an analyzable format / output: list of issues and areas for improvement).

[0829] Step 5:

[0830] The server sends facial expression data and voice data to the emotion engine, which analyzes the user's emotional state and expresses it in numerical values ​​and categories (input: facial expression data, voice data / output: emotional state data).

[0831] Step 6:

[0832] The server integrates the motion analysis results from the AI ​​model with the emotional state data from the emotion engine. Based on this integrated data, it generates feedback for the user. The feedback includes specific improvements to improve motion efficiency and reduce errors, as well as advice that takes emotional aspects into consideration (input: list of issues and improvements, emotional state data; output: feedback report).

[0833] Step 7:

[0834] The server sends the generated feedback report to the user's device, where the user can check the report and implement specific improvement measures (input: feedback report / output: user checks and implements feedback).

[0835] These steps provide comprehensive feedback that takes into account the user's motion performance and emotional state, resulting in motion efficiency and error improvement.

[0836] 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.

[0837] 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.

[0838] 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.

[0839] [Third embodiment]

[0840] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0841] 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.

[0842] 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).

[0843] 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.

[0844] 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.

[0845] 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).

[0846] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] 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.

[0851] 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."

[0852] The present invention is a system in which a user provides their own gameplay data, an AI model analyzes the data, and presents specific issues and areas for improvement. Specific embodiments of the system are described below.

[0853] System Configuration

[0854] This system consists of a user's terminal, a server, and an AI model.

[0855] 1. On the user's device:

[0856] Users play the game and create play data, which is also responsible for uploading the play data to the server.

[0857] Receive feedback and provide an interface for users to review.

[0858] 2. Server:

[0859] Receives and stores play data and converts it into an analyzable format.

[0860] The converted data is passed to the AI ​​model and the analysis results are received.

[0861] The analysis results are processed into a user-friendly format and sent to the terminal.

[0862] 3. AI model:

[0863] The system learns the play data of professional gamers in advance and analyzes the user's play data.

[0864] Compare user actions and tactics with professional gamer data to identify issues and areas for improvement.

[0865] System action

[0866] This system's processing consists of a series of steps, from uploading the user's play data to providing feedback. The specific operation of each component is as follows:

[0867] Server Operation

[0868] Receiving play data:

[0869] The server receives play data uploaded by users. The received data is first saved in a specified directory.

[0870] Transforming data:

[0871] The server converts the saved play data into an analyzable format, for example, by extracting specific frames from video data and converting operation log data into a time-stamped format.

[0872] Sending data:

[0873] The converted play data is sent to the AI ​​model, which then performs analysis based on this data.

[0874] Receiving and processing analysis results:

[0875] The server receives the analysis results from the AI ​​model and processes them into a user-friendly format, such as a text report, a graphical dashboard, or a list of specific improvements.

[0876] How AI models work

[0877] Analysis of gameplay data:

[0878] The AI ​​model analyzes the user's actions and tactics based on the play data received from the server. Specifically, it compares the play data with that of professional gamers and evaluates the user's movement patterns, reaction speed, tactical decisions, etc.

[0879] Identifying issues and areas for improvement:

[0880] Based on the analysis results, the system extracts issues in the user's gameplay and specific areas for improvement, such as "the timing of the shot is 0.2 seconds late" or "moving to cover in a specific area is inappropriate."

[0881] Device behavior

[0882] Uploading gameplay data:

[0883] The user uploads their gameplay data from their device to the server, which then begins analysis on the server side.

[0884] Receiving and viewing feedback:

[0885] The terminal receives the feedback sent from the server and presents it to the user. The feedback is displayed visually and is provided in a form that is easy for the user to understand and put into action.

[0886] Specific examples

[0887] Example 1: Analysis of play data in FPS games

[0888] Users upload their FPS gameplay videos from their devices to a server.

[0889] The server receives the video data, extracts specific frames, and converts them into an analyzable format.

[0890] The AI ​​model analyzes gameplay data and discovers that the user's shooting timing is slower than that of professional gamers, and identifies improper cover movements.

[0891] Based on the analysis results received from the AI ​​model, the server generates a feedback report containing specific improvements, such as "the timing of the shot should be advanced by 0.2 seconds" or "quickly move to cover in specific areas," and sends it to the device.

[0892] Users can view the feedback on their device and put it into practice the next time they play the game.

[0893] The processing flow will be explained below.

[0894] Step 1:

[0895] After finishing a game, the user prepares the gameplay data (such as a replay video or operation log), and then uploads the gameplay data to the server using a dedicated application or web interface on the device.

[0896] Step 2:

[0897] The server receives play data uploaded by users and stores it in a storage directory. This storage process includes checking the integrity of the data when it is received.

[0898] Step 3:

[0899] The server converts the saved gameplay data into an analyzable format. For example, it extracts specific frames from video data and adds necessary metadata (timestamps, event logs, etc.). It also converts the operation log data into a unified format.

[0900] Step 4:

[0901] The server passes the converted data to the AI ​​model, and at the same time issues an analysis request.

[0902] Step 5:

[0903] The AI ​​model receives the transmitted play data and analyzes the user's movement patterns. For example, it compares the play data of professional gamers to evaluate the user's movements (shooting timing, movement patterns, etc.). The AI ​​model also compares the user's play data with the professional gamer's standards to perform a discrepancy analysis.

[0904] Step 6:

[0905] The AI ​​model generates analysis results and identifies the user's issues and areas for improvement. For example, specific problems such as "firing timing is 0.2 seconds late" or "cover movement is slow in certain areas" are summarized in text format along with how to improve them.

[0906] Step 7:

[0907] Based on the analysis results received from the AI ​​model, the server generates feedback reports for the user, including text reports, graphical dashboards, and lists of specific areas for improvement, as well as graphs and heat maps for visual coaching.

[0908] Step 8:

[0909] The server sends the generated feedback report to the user's device, and the analysis results are reflected on the user's personal dashboard.

[0910] Step 9:

[0911] The device receives the feedback report sent from the server and displays it in an interface that the user can view. The user can refer to this to identify problems with their gameplay and use the suggested improvements to prepare for their next gameplay.

[0912] Step 10:

[0913] Users use the feedback to implement specific improvements in their next gameplay, and then upload their gameplay data again to receive continuous feedback using the server and AI model to improve their skills.

[0914] Example 1

[0915] 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."

[0916] Conventional gameplay data analysis systems have struggled to efficiently and effectively analyze user-provided play data and identify specific issues and areas for improvement to improve the user's skills. Furthermore, there has been a lack of a way to present the analysis results in a format that users can easily understand and apply. This has resulted in users being unable to effectively utilize their play data, which has prevented them from improving their skills.

[0917] 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.

[0918] In this invention, the server includes means for receiving play data provided by a user, means for converting the received play data into an analyzable format, means for comparing and analyzing the converted data with play data of previously learned professional gamers, means for extracting issues and areas for improvement for the user based on the analysis results, means for presenting the extracted issues and areas for improvement to the user, means for the user to upload the play data to the server, means for saving the play data in a storage directory, means for extracting specific frames from the play data, means for converting operation log data into a timestamp-added format, means for receiving the analysis results from the server and processing them into a format that is easy for the user to understand, and means for providing an interface for visually displaying feedback to the user. This makes it possible to effectively analyze the user's play data, allowing the user to easily understand specific issues and areas for improvement and put them into action.

[0919] "Play data" refers to information such as operation logs and video files that are generated by the user while playing the game.

[0920] A "server" is a device that receives play data provided by users, stores it, converts it into an analyzable format, sends it to an AI model, and receives the analysis results.

[0921] A "terminal" is a computer device that a user operates to create play data, upload it to a server, and receive and check the analysis results.

[0922] An "AI model" is an artificial intelligence program that learns the play data of professional gamers in advance, analyzes the user's play data, and extracts issues and areas for improvement.

[0923] "Professional gamer play data" refers to information such as operation logs and video files generated by professional gamers while playing games.

[0924] A "parseable format" is a specific data format that an AI model requires to parse play data.

[0925] "Operation log data" is data that records operations and actions performed by a user while playing a game.

[0926] The "time stamped format" is a data format in which time information is added to the operation log.

[0927] "Analysis results" are information on issues and areas for improvement derived after the AI ​​model analyzes the user's play data.

[0928] "Feedback" is information used to present analysis results and areas for improvement to the user.

[0929] The "interface" is the part of the software that allows the user to send and receive data to and from the server and view feedback.

[0930] This system allows users to provide their own gameplay data, which is then analyzed by an AI model, which then presents specific issues and areas for improvement. This system consists of a user's device, a server, and an AI model.

[0931] System Configuration

[0932] 1. User's device

[0933] The user's terminal is a device for playing games and creating game data. The user records their gameplay and saves the play data on the terminal. The saved play data is uploaded to the server via the terminal. The terminal also receives feedback from the server and provides an interface that the user can check.

[0934] 2. Server

[0935] The server receives gameplay data uploaded by users and saves it in a designated directory. The received data is converted into an analyzable format, and the converted data is sent to the AI ​​model. The server then processes the analysis results from the AI ​​model into a format that is easy for users to understand. Examples include text reports, graphical dashboards, and lists of specific improvements.

[0936] 3. AI Model

[0937] The AI ​​model learns from professional gamer play data in advance and analyzes the user's play data. The AI ​​model compares the user's actions and tactics with the professional gamer data to identify issues and areas for improvement. For example, these include "shooting timing is 0.2 seconds late" or "moving to cover in a specific area is inappropriate."

[0938] Example of a system

[0939] Taking an FPS game as an example, a user uploads a video of their FPS gameplay from their device to a server. The server receives the video data, extracts specific frames, and converts them into an analyzable format. The AI ​​model analyzes the play data and identifies that the user's shooting timing is slower than that of professional gamers or that their cover movement is inappropriate. Based on these analysis results, the server generates a feedback report containing specific improvements, such as "shoot 0.2 seconds earlier" or "move to cover more quickly in certain areas," and sends it to the device. The user can then review the feedback on their device and put it into practice the next time they play the game.

[0940] Prompt Sentence Examples

[0941] You can request an analysis from the AI ​​model by entering a prompt like the one below.

[0942] "Please analyze my latest FPS gameplay video and let me know what specific improvements I can make."

[0943] "Based on this play data, please tell me what I need to improve on compared to professional gamers."

[0944] The present invention allows users to effectively analyze their own gameplay data and understand specific issues and areas for improvement, thereby providing specific guidance for users to improve their gaming skills.

[0945] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0946] Step 1: Creating and uploading user play data

[0947] Users record their own gameplay and save the play data on their device. Then, they upload the recorded play data to the server through the device interface. The input is the user's gameplay data (e.g., "gameplay.mp4"), and the output is the play data uploaded to the server. Specifically, users press the "Upload" button, select a file, and send it to the server.

[0948] Step 2: Receiving and saving your play data

[0949] The server receives the play data sent by the user and saves it in a temporary buffer. It then moves and saves the received play data to a specified save directory. The input is the play data sent by the user, and the output is the play data stored in the save directory. Specifically, the play data is saved in the " / uploads" directory and is finally moved to the " / processed_data" directory.

[0950] Step 3: Convert your game data

[0951] The server converts the saved play data into an analyzable format. Specifically, it extracts specific frames from the video data and converts them into image files, and converts the operation log data into a format with a timestamp. The input is the play data saved on the server, and the output is the data converted into an analyzable format. Specifically, it extracts one image every 30 frames and saves it as "frame_0001.png" or similar.

[0952] Step 4: Request data analysis

[0953] The server sends the converted play data to the AI ​​model and requests it to analyze it. A specific API is used for sending the data. The input is the converted play data, and the output is the analysis results from the AI ​​model. Specifically, a POST request is sent to "http: / / aimodelserver / analyze" and the converted data is attached and sent.

[0954] Step 5: Receiving and processing the analysis results

[0955] The server receives the analysis results from the AI ​​model and processes them into a format that is easy for users to understand. The input is the analysis results obtained from the AI ​​model, and the output is feedback that can be viewed by the user. Specific operations include generating text reports, graphical dashboards, and lists of specific areas for improvement. For example, information such as "insufficient cover movement" can be expressed as "rapid cover movement should be performed in specific areas."

[0956] Step 6: Submit and view feedback

[0957] The server sends the generated feedback report to the user's device. The device then visually displays the received feedback to the user. The input is the processed feedback, and the output is the feedback information viewed by the user. Specifically, the feedback report is saved as "feedback_username_timestamp.pdf" and displayed to the user. For example, graphs and text explanations can be displayed using a PDF viewer.

[0958] The above are the specific processing steps of the program for this system.

[0959] (Application example 1)

[0960] 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."

[0961] Conventional factory robot operation management systems have had difficulty providing specific feedback to optimize robot operation efficiency and productivity, which has resulted in insufficient improvement in production efficiency and robot operating efficiency within the factory, making it difficult to achieve an optimized production process.

[0962] 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.

[0963] In this invention, the server includes means for receiving operation data provided by a user, means for converting the received operation data into an analyzable format, means for comparing and analyzing the converted data with pre-trained professional operation data, means for collecting operation data from a factory robot and analyzing it in real time to improve specific work efficiency, means for extracting user issues and areas for improvement based on the analysis results, and means for presenting the extracted issues and areas for improvement to the user. This makes it possible to analyze the operation efficiency of a factory robot in real time and provide specific areas for improvement to the user.

[0964] "User-provided operational data" refers to data about specific operations and behaviors collected from devices or systems operated by users.

[0965] "Converting into an analyzable format" refers to converting the collected raw data into a data format that can be interpreted and analyzed by AI or machine learning models.

[0966] "Comparative analysis" refers to comparing newly collected data with data from professionals who have already studied it, and evaluating and analyzing it using the same standards.

[0967] "Extracting issues and areas for improvement" refers to identifying, from the analysis results, problems with user behavior and operations and specific areas for improvement to improve efficiency.

[0968] "Presenting to the user" means providing the analysis results to the user in an easy-to-understand format so that the user can easily understand and use the results.

[0969] "Real-time analysis" refers to processing collected data immediately and generating analysis results without delay.

[0970] A "factory robot" refers to an automated machine installed to automate manufacturing operations and tasks.

[0971] The present invention provides a system that analyzes the operation data of a factory robot and presents problems and areas for improvement in real time. Specific embodiments of the system will be described below.

[0972] System Configuration

[0973] The system consists of a user's device, a server, and an AI model.

[0974] 1. On the user's device:

[0975] Tablet terminal: Used in the factory to collect robot operation data and send it to a server.

[0976] Data collection software using the MQTT protocol is used to collect data.

[0977] Additionally, an interface is provided that visually displays feedback from the server.

[0978] 2. Server:

[0979] Data reception and storage: Receives and stores operational data sent from the user terminal.

[0980] Data conversion: Converts received data into a parsable format (JSON format).

[0981] Software used: Dedicated server software is used for data collection and conversion.

[0982] Execution of AI models: Run AI models using deep learning frameworks such as TensorFlow and perform analysis.

[0983] Feedback generation: Based on the analysis results, a detailed feedback report is generated and sent to the user's device.

[0984] 3. AI model:

[0985] Data analysis: Based on the converted data, compare it with professional operational data to identify bottlenecks and issues.

[0986] Extraction of issues and improvements: Identify problems and improvements in the user's behavior and send them back to the server.

[0987] System Operation

[0988] The server receives the operational data provided by the user and converts it into an analyzable format. The converted data is sent to the AI ​​model and compared with professional data. Based on the analysis results, the user's issues and areas for improvement are extracted and the results are presented to the user. Specifically, it works as follows:

[0989] Hardware and Software

[0990] 1. Hardware:

[0991] Factory robots: Used as a source of operational data.

[0992] Tablet device: For data collection and feedback display.

[0993] 2. Software:

[0994] Data collection software: Software for collecting operational data from factory robots in real time and sending it to a server.

[0995] Server software: receives, stores, converts, and analyzes data.

[0996] AI model: Utilizes TensorFlow framework to analyze behavioral data and compare it with professional data.

[0997] Specific examples

[0998] For example, if a factory robot's operations are delayed, collecting operational data and analyzing it in real time will reveal that certain operations are slower than others. As a result of the analysis, feedback such as "The robot is slow when moving a specific part. The operation speed should be reduced by 0.5 seconds" is provided.

[0999] Prompt Sentence Examples

[1000] Here are some example prompts to input to the generative AI model:

[1001] Based on the operation data of a factory robot, please propose specific improvements to improve efficiency. The following is an example of operation data: {"Operation Data": [{"Operation 1": 1.2 seconds, "Operation 2": 0.8 seconds, ...}]}

[1002] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1003] Step 1:

[1004] Collecting user behavior data

[1005] Input: Factory robot operation data

[1006] The server receives real-time robot operation data from the user's device (tablet) via the MQTT protocol. This data is sent as raw data.

[1007] Output: raw data collected

[1008] Step 2:

[1009] Saving operation data

[1010] Input: Raw data collected

[1011] The server saves the received operational data in the specified directory in the format used for secondary storage of raw data.

[1012] Output: Saved operation data file

[1013] Step 3:

[1014] Data transformation

[1015] Input: Saved motion data file

[1016] The server converts the raw data into a JSON format that can be analyzed. For example, it extracts necessary metrics (such as operation time, distance traveled, and number of operations) from the raw data and converts them into log data with timestamps.

[1017] Output: Parsable data in JSON format

[1018] Step 4:

[1019] Sending data to the AI ​​model

[1020] Input: Parsable data in JSON format

[1021] The server then sends the converted data to the AI ​​model, typically using HTTP or gRPC as the transmission protocol.

[1022] Output: Send request to AI model

[1023] Step 5:

[1024] Analysis using AI models

[1025] Input: Parsable data sent by the server

[1026] The AI ​​model compares the received data with that of the professional, evaluating, for example, movement timing, efficiency, and movement patterns, and identifies discrepancies.

[1027] Output: Analysis results including issues and improvements

[1028] Step 6:

[1029] Generate feedback

[1030] Input: Analysis results including issues and improvements

[1031] The server generates a detailed feedback report based on the analysis results, which includes text instructions, graphs, and charts.

[1032] Output: Feedback report

[1033] Step 7:

[1034] Providing feedback to the user

[1035] Input: Feedback Report

[1036] The terminal visually displays the feedback reports received from the server, laid out on an interface that is easy for the user to understand.

[1037] Output: Feedback displayed on the user interface

[1038] 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.

[1039] The present invention relates to a system that uses an AI model to analyze play data provided by a user and presents the user with issues and areas for improvement. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide feedback that combines the analysis results with the user's emotional state. Specific embodiments of the system are described below.

[1040] System Configuration

[1041] This system consists of a user's device, a server, an AI model, and an emotion engine.

[1042] 1. On the user's device:

[1043] The user plays the game and creates play data.

[1044] Its role is to upload play data to the server and receive and check feedback.

[1045] The camera and microphone are used to capture the user's facial expressions and voice and send them to the emotion engine.

[1046] 2. Server:

[1047] Receives and stores play data and converts it into an analyzable format.

[1048] The converted data is passed to the AI ​​model and the analysis results are received.

[1049] Receives user emotion data and passes it to the emotion engine.

[1050] The analysis results are integrated with emotional data to generate a feedback report for the user.

[1051] 3. AI model:

[1052] The system learns the play data of professional gamers in advance and analyzes the user's play data.

[1053] Evaluate user actions and tactics to identify issues and areas for improvement.

[1054] 4. Emotion Engine:

[1055] It analyzes the user's facial expressions and voice while playing to recognize their emotional state (e.g., joy, anger, surprise, etc.).

[1056] The recognized emotion data is sent to the server.

[1057] System action

[1058] The system has a series of steps from uploading the user's play data to providing feedback. The specific operation of each component is as follows:

[1059] Server Operation

[1060] Receiving play data:

[1061] The server receives play data uploaded by the user and stores it in a storage directory. It also receives emotion data based on the user's facial expressions and voice data.

[1062] Transforming data:

[1063] The server converts the saved gameplay data into an analyzable format. For example, it extracts specific frames from video data and adds necessary metadata (timestamps, event logs, etc.). It also converts the operation log data into a unified format.

[1064] Sending data:

[1065] The converted play data is sent to the AI ​​model, and the emotion data is sent to the emotion engine, at the same time issuing an analysis request.

[1066] Receiving and processing analysis results:

[1067] The server receives the analysis results from the AI ​​model and the emotion data from the emotion engine, and combines them to generate feedback for the user, such as a text report, a graphical dashboard, or a list of areas for improvement.

[1068] How AI models work

[1069] Analysis of gameplay data:

[1070] The AI ​​model analyzes the user's movement patterns based on the play data sent from the server, compares it with the play data of professional gamers, and evaluates the user's movements (e.g., shooting timing, movement patterns).

[1071] Identifying issues and areas for improvement:

[1072] Based on the analysis results, the system extracts issues and specific areas for improvement in the user's gameplay, such as "the timing of the shot is 0.2 seconds late" or "moving to cover in a specific area is inappropriate."

[1073] Emotion Engine Operation

[1074] Emotional Data Analysis:

[1075] The emotion engine analyzes the user's facial expressions and voice data sent from the server to recognize the user's emotional state. For example, it quantifies the degree of "joy," "anger," or "surprise" expressed during gameplay.

[1076] Emotional Feedback:

[1077] After recognizing the emotional state, the data is sent to the server, which then integrates it with the analysis results and provides feedback according to the user's emotions.

[1078] Device behavior

[1079] Uploading gameplay and emotion data:

[1080] Users upload their play data and emotional data (facial expressions and voice) from their devices to the server, which then begins analysis on the server side.

[1081] Receiving and viewing feedback:

[1082] The terminal receives the feedback report sent from the server and presents it to the user. The feedback is displayed visually and is provided in a form that is easy for the user to understand and act on.

[1083] Specific examples

[1084] Example 1: Analysis of play data and emotion data in FPS games

[1085] User: Uploads video of their own FPS gameplay, along with facial expressions and audio data from their device to the server.

[1086] Server: Receives video data and converts it into an analyzable format. It also receives facial expression and voice data and sends them to the emotion engine.

[1087] AI model: Analyzes gameplay data and discovers that the user's shooting timing is slower than that of professional gamers, and identifies inappropriate cover movements.

[1088] Emotion engine: Based on facial expressions and voices during gameplay, it recognizes when the user is feeling stressed in a particular situation.

[1089] Server: Integrates the analysis results received from the AI ​​model and emotion engine, generates a feedback report containing specific improvement suggestions such as "You should shoot 0.2 seconds earlier," as well as emotion-based advice such as "You should try breathing exercises to reduce stress in specific areas," and sends it to the device.

[1090] User: Checks the feedback on their device and puts it into practice the next time they play the game. They then upload their play data and emotional data again, and receive continuous feedback using the server and AI model to improve their skills and mental state.

[1091] The processing flow will be explained below.

[1092] Step 1:

[1093] After finishing a game, the user saves the gameplay data (such as replay videos and operation logs) and facial expressions and voice data recorded during gameplay on the device, and then uploads this data to the server using a dedicated application or web interface.

[1094] Step 2:

[1095] The server receives play data uploaded by the user and saves it in a specified directory. It also receives the user's facial expression and voice data and prepares them for transmission to the emotion engine.

[1096] Step 3:

[1097] The server converts the saved gameplay data into an analyzable format. For example, it extracts specific frames from video data and adds necessary metadata (timestamps, event logs, etc.). It also converts the operation log data into a unified format.

[1098] Step 4:

[1099] The server sends the converted play data to the AI ​​model. At the same time, it sends the user's facial expressions and voice data to the emotion engine, and issues an analysis request.

[1100] Step 5:

[1101] The AI ​​model receives the transmitted play data and analyzes the user's movement patterns. It compares this with the play data of professional gamers, evaluates the user's movements (shooting timing, movement patterns, etc.), and analyzes the differences.

[1102] Step 6:

[1103] The emotion engine analyzes the facial and voice data sent, recognizes the user's emotional state (happiness, anger, surprise, etc.), and converts it into numerical data.

[1104] Step 7:

[1105] Based on the analysis results, the AI ​​model identifies the user's issues and areas for improvement, such as "the timing of the shot is 0.2 seconds late" or "the cover movement in a specific area is inappropriate."

[1106] Step 8:

[1107] The emotion engine sends the recognized emotion data to the server, which evaluates the user's stress level and concentration level in a particular situation based on the emotional state.

[1108] Step 9:

[1109] The server receives the analysis results from the AI ​​model and the emotional data from the emotion engine, and integrates them. For example, it associates the user's challenges in specific actions during gameplay with their emotional state at that time.

[1110] Step 10:

[1111] The server generates a feedback report for the user based on the integrated data, including suggestions for improvement such as "You should shoot 0.2 seconds earlier" and emotion-based advice such as "Try breathing exercises to reduce stress in certain areas."

[1112] Step 11:

[1113] The server generates and sends the feedback report to the user's device, which may include text reports, graphs, heat maps, etc.

[1114] Step 12:

[1115] The device receives the feedback report sent from the server and displays it in an interface that can be viewed by the user. The user can then review the presented issues and improvements and implement them in their next gameplay.

[1116] Step 13:

[1117] Users can use the feedback to implement specific improvements in their next gameplay, upload their play data and emotional data again, and use the server and AI model to receive continuous feedback and improve their skills and mental state.

[1118] Example 2

[1119] 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."

[1120] Conventional play data analysis systems focus on analyzing a user's playing performance and do not consider their emotional state, resulting in insufficient feedback to the user. As a result, it is difficult for users to comprehensively understand both their emotional state and technical issues during play, making it difficult to improve efficiently. This invention aims to integrate and analyze play data and user emotional data to more accurately and comprehensively present users' issues and areas for improvement.

[1121] 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.

[1122] In this invention, the server includes means for receiving data provided by the user, means for converting the received data into an analyzable format, means for comparing and analyzing the converted data with data from experts previously trained, means for extracting the user's issues and areas for improvement based on the analysis results, means for presenting the extracted issues and areas for improvement to the user, means for recognizing the user's emotional state and analyzing the data, and means for integrating the analyzed emotional data with the results of the comparative analysis and providing feedback to the user. This allows the user to comprehensively understand their technical issues and emotional reactions and efficiently improve their performance.

[1123] "Data provided by the user" refers to video data and operation log data that the user records of their own playing status and emotional state.

[1124] "Means for receiving" refers to the software and hardware configuration that allows the server to receive data from the user via the Internet.

[1125] "Means of converting into an analyzable format" refers to the process of converting data received from users into a format that can be analyzed by an AI model, such as by extracting specific frames from videos or standardizing the format of operation logs.

[1126] "Means for comparative analysis" refers to algorithms and AI models that compare the converted data with pre-trained professional data to identify users' playing patterns and technical issues.

[1127] "Means for extracting issues and areas for improvement" refers to the process for automatically identifying technical issues and specific ways to improve users' play data from the analysis results of the AI ​​model.

[1128] "Means of presenting to the user" refers to a user interface and report generation function that displays the extracted issues and areas for improvement in a format that is easy for the user to understand.

[1129] "Means for recognizing emotional state" refers to an algorithm and analysis engine for analyzing and quantifying the emotional state based on the user's facial expressions and voice data while playing.

[1130] "Means for providing feedback" refers to software and hardware configurations for generating text reports and graphical dashboards that integrate technical issues and emotional states to provide easy-to-understand feedback to users.

[1131] MODE FOR CARRYING OUT THE INVENTION

[1132] This invention relates to a system that analyzes play data and emotional data provided by users, extracts and presents the user's issues and areas for improvement. This system is composed of a user terminal, a server, an AI model, and an emotional engine.

[1133] System Configuration

[1134] 1. On the user's device:

[1135] A user plays a game and creates play data (video data and operation log data).

[1136] Its role is to upload play data and emotional data (facial expressions and voice data) to the server and receive and confirm feedback. Files are selected and uploaded via a dedicated application or web interface.

[1137] At this time, the user's facial expressions and voice are captured using a camera and microphone and sent to the server as emotional data.

[1138] 2. Server:

[1139] The server receives gameplay data uploaded by users and saves it in a specified directory. The saved data is then converted into an analyzable format. For example, specific frames are extracted from video data, necessary metadata is added, and operation log data is converted into a unified format.

[1140] The converted play data is sent to the AI ​​model, which issues an analysis request. Emotion data is also sent to the emotion engine, which issues an emotion analysis request.

[1141] It receives the analysis results from the AI ​​model and the emotion engine, integrates them, and generates a feedback report for the user, which is provided in a format that is easy for the user to understand.

[1142] 3. AI model:

[1143] Based on the play data sent from the server, the user's movement patterns are analyzed by comparing them with the play data of professionals, using an AI model that has been trained in advance using the play data of professionals.

[1144] Based on the analysis results, technical issues and specific areas for improvement can be identified. For example, specific suggestions such as "the timing of shooting is delayed" or "moving to cover in a specific area is inappropriate" can be made.

[1145] 4. Emotion Engine:

[1146] The system analyzes the user's facial expressions and voice data sent from the server to recognize the user's emotional state. For example, it quantifies emotional states such as "joy," "anger," and "surprise" while playing.

[1147] The recognized emotion data is sent to the server, which then integrates it with the analysis results and provides feedback that takes the user's emotion data into account.

[1148] Specific examples

[1149] Example 1: Analysis of play data and emotion data in FPS games

[1150] User: After playing an FPS game, upload the gameplay video and facial expressions and voice data (emotion data) recorded during the gameplay to the server using a dedicated app. Click the upload button in the app, select the file, and then use the "Upload" button.

[1151] Server: Receives video data and converts it into an analyzable format. It adds metadata (timestamps, event logs) and converts operation log data into a unified format. It also sends facial expression and voice data to the emotion engine.

[1152] AI model: Analyzes gameplay data and detects when a user's shooting timing is delayed compared to a professional. It also identifies inappropriate cover movement. For example, it detects when a user's shooting timing is delayed by 0.2 seconds.

[1153] Emotion engine: Based on facial expressions and voices during gameplay, it recognizes when a user is feeling stressed in a particular situation. For example, it recognizes that "stress levels are high in a particular area."

[1154] Server: Integrates the analysis results from the AI ​​model and emotion engine to generate a feedback report with specific improvements such as "the timing of the shot should be advanced by 0.2 seconds" as well as emotion-based advice such as "try breathing exercises to reduce stress in specific areas."

[1155] User: Checks the feedback on their device and puts it into practice the next time they play the game. They then upload their play data and emotional data again, and receive continuous feedback using the server and AI model to improve their skills and mental state.

[1156] Examples of prompt statements

[1157] "Based on gameplay data and emotional data from FPS games, analyze users' issues and areas for improvement and provide specific feedback. For example, if a user's shooting timing is slow, provide specific ways to improve, and include advice on how to relax for users who are feeling stressed."

[1158] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1159] Step 1: Upload your gameplay data

[1160] Users upload gameplay videos and emotional data (facial expressions and voice) from their own devices to the server. Specifically, they use a dedicated application or web interface to select the gameplay data file and emotional data and click the "Upload" button.

[1161] Input: Gameplay video, operation log data, facial expression and voice data.

[1162] Output: The data uploaded to the server.

[1163] Step 2: Saving gameplay data and emotion data

[1164] The server receives play data and emotion data uploaded by users and temporarily stores them in a specified directory. It manages the data by dividing it into folders based on the user's identification information.

[1165] Input: Uploaded data.

[1166] Output: Data saved in the save directory.

[1167] Step 3: Convert your game data

[1168] The server converts the saved gameplay data into an analyzable format. Specifically, it extracts specific frames from the video data, adds necessary metadata (timestamps, event logs), and converts the operation log data into a unified format.

[1169] Input: Saved play data.

[1170] Output: Transformed, parseable data.

[1171] Step 4: Issue an analysis request and send data

[1172] The server sends the converted play data to the AI ​​model and issues an analysis request. At the same time, it also sends the emotion data to the emotion engine and issues an emotion analysis request. Specifically, it sends the data to the AI ​​model and emotion engine via an API request.

[1173] Input: Converted play data, emotion data.

[1174] Output: Data sent to the AI ​​model and emotion engine.

[1175] Step 5: Analyzing play data with an AI model

[1176] The AI ​​model receives play data sent from the server and compares it with professional play data to analyze the user's movement patterns, specifically evaluating shooting timing and movement patterns to identify the user's technical issues.

[1177] Input: Play data sent to the AI ​​model.

[1178] Output: Analysis results including technical issues and improvements.

[1179] Step 6: Analyze the sentiment data

[1180] The emotion engine analyzes the user's facial expressions and voice data sent from the server to recognize the user's emotional state, quantifying the degree of the emotional state and identifying the emotional response in a specific situation.

[1181] Input: Facial and speech data sent to the emotion engine.

[1182] Output: Quantified data indicating emotional state.

[1183] Step 7: Integrating analysis results with emotion data

[1184] The server receives the analysis results from the AI ​​model and the emotional data from the emotion engine, and then integrates them to generate a feedback report for the user. Specifically, it creates feedback that encompasses both technical and emotional issues.

[1185] Input: Analysis results, emotion data.

[1186] Output: Consolidated feedback report.

[1187] Step 8: Generate and display feedback

[1188] The server sends the generated feedback report to the user's device, which visually displays the received feedback and provides it to the user in a format that is easy for the user to understand, such as through a text report or a graphical dashboard.

[1189] Input: Consolidated feedback report.

[1190] Output: Feedback displayed on the user's terminal.

[1191] (Application example 2)

[1192] 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."

[1193] Simply analyzing motion data is insufficient for improving user performance and solving problems. More effective feedback is needed, especially by taking into account the operator's emotional state. However, currently there is no system that can integrate and analyze motion data and emotional data and provide accurate feedback based on that. Therefore, the realization of a system that can simultaneously analyze a user's motion and emotional state and provide comprehensive feedback that takes both into account is a challenge.

[1194] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving motion data provided by the user, means for converting the received motion data into an analyzable format, means for comparing and analyzing the converted data with pre-trained reference data, means for extracting the user's issues and areas for improvement based on the analysis results, means for analyzing the user's facial expression and voice data to recognize their emotional state, and means for integrating the analysis results and the emotional data and presenting feedback to the user. This enables comprehensive and effective feedback that takes into account both the user's motion performance and emotional state.

[1195] "Operation data" refers to data relating to actions and operations provided by the user, and includes the patterns and timing of those actions, error information, and the like.

[1196] An "analyzable format" is data received that has been converted into a format suitable for analysis by machine learning models and algorithms.

[1197] "Reference data" refers to data that has been learned in advance, and includes, as specific standards, best practices from other users and data from professionals.

[1198] "Issues" refer to problems or areas that need improvement in the user's actions or operations.

[1199] "Improvements" refer to specific methods or suggestions for making user actions or operations more efficient and effective.

[1200] "Facial expression data" is data obtained from the user's facial expressions, and serves as a basis for analyzing the emotional state.

[1201] "Voice data" is data obtained from the user's vocalizations and tone of voice, and serves as the basis for analyzing the emotional state.

[1202] "Emotional state" refers to the user's emotional state, and is expressed as numerical values ​​or categories of emotions such as stress, joy, surprise, etc.

[1203] "Feedback" refers to specific improvement suggestions and advice provided to users based on the analysis results and emotional data.

[1204] The present invention is a system that integrates and analyzes motion data and emotion data, and provides feedback to the user on areas for improvement based on the results. Specifically, the system receives the user's motion data and emotion data and analyzes them on a server to improve the user's performance. The specific system configuration and operation are described below.

[1205] System Configuration

[1206] This system consists of the following elements:

[1207] 1. On the user's device:

[1208] Operational data: Collecting data on user operations and behavior. Specific examples include operation logs on a manufacturing line and machine operation logs.

[1209] Emotion data: The camera and microphone are used to capture the user's facial expressions and voice.

[1210] 2. Server:

[1211] Data reception: Receives and stores the motion data and emotion data sent from the user's device.

[1212] Data conversion: Converts received data into an analyzable format. This process involves extracting specific frames from video data and adding timestamps and event logs.

[1213] Data analysis: The converted data is analyzed using an AI model and emotion engine to identify the user's issues and areas for improvement. The AI ​​model compares the user's movements with those of professionals and evaluates their movements.

[1214] Feedback generation: Integrates analysis results and emotional data to generate feedback for users, including specific improvements and advice.

[1215] 3. AI model:

[1216] Movement data analysis: An AI model that has learned from professional movement data performs comparative analysis with the user's movement data.

[1217] Identifying issues: Identifying delays and errors in user actions and extracting areas for improvement.

[1218] 4. Emotion Engine:

[1219] Emotion analysis: Analyzes the user's facial expression and voice data to quantify their emotional state.

[1220] Emotional feedback: Based on the user's emotional state, the areas where the user is feeling stressed or tired are identified and reflected in the analysis results.

[1221] System Operation

[1222] The server receives the user's motion and emotion data, integrates it, and converts it into an analyzable format. It then analyzes the data using an AI model and emotion engine, identifying issues and areas for improvement based on the analysis results. It then integrates the analysis results with the emotion data and provides feedback to the user. The feedback includes not only specific improvements for improving motion efficiency and reducing errors, but also advice that takes into account the operator's emotional aspects, such as stress management and improving concentration.

[1223] Specific examples

[1224] For example, if the system performs analysis based on data provided by an operator working on a production line, it may generate the following feedback: "Operation delay time: 0.2 seconds. Number of operation errors: 5. Stress level: High. Suggested improvement: Increase operator breaks to increase operation speed and reduce the occurrence of errors."

[1225] Prompt Sentence Examples

[1226] An example prompt for using a generative model: "Analyze the robot operation data and the operator's emotional data, and generate specific feedback for operational efficiency and error correction."

[1227] The present invention enables comprehensive and effective feedback that takes into account both the user's motion performance and emotional state.

[1228] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1229] Step 1:

[1230] Users collect their own motion data and emotional data on their devices. Motion data includes operation logs and machine operation logs. Emotion data is captured using a camera and microphone to capture facial expressions and voice. The collected data is temporarily stored in the device (input: user motion data, facial expression data, voice data / output: temporarily stored data).

[1231] Step 2:

[1232] The device uploads the collected motion and emotion data to a server, which receives the data and stores it in dedicated storage (input: temporary data / output: server storage).

[1233] Step 3:

[1234] The server converts the received motion data into an analyzable format. For example, it extracts specific frames from video data and adds timestamps and event logs. It also converts the operation log into a unified format (input: motion data, emotion data / output: analyzable format data).

[1235] Step 4:

[1236] The server sends the converted motion data to the AI ​​model, which then compares it with the professional's motion data to analyze the user's motion and identify issues and areas for improvement (input: data in an analyzable format / output: list of issues and areas for improvement).

[1237] Step 5:

[1238] The server sends facial expression data and voice data to the emotion engine, which analyzes the user's emotional state and expresses it in numerical values ​​and categories (input: facial expression data, voice data / output: emotional state data).

[1239] Step 6:

[1240] The server integrates the motion analysis results from the AI ​​model with the emotional state data from the emotion engine. Based on this integrated data, it generates feedback for the user. The feedback includes specific improvements to improve motion efficiency and reduce errors, as well as advice that takes emotional aspects into consideration (input: list of issues and improvements, emotional state data; output: feedback report).

[1241] Step 7:

[1242] The server sends the generated feedback report to the user's device, where the user can check the report and implement specific improvement measures (input: feedback report / output: user checks and implements feedback).

[1243] These steps provide comprehensive feedback that takes into account the user's motion performance and emotional state, resulting in motion efficiency and error improvement.

[1244] 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.

[1245] 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.

[1246] 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.

[1247] [Fourth embodiment]

[1248] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1249] 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.

[1250] 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).

[1251] 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.

[1252] 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.

[1253] 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).

[1254] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1255] 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.

[1256] 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.

[1257] 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.

[1258] 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.

[1259] 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.

[1260] 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."

[1261] The present invention is a system in which a user provides their own gameplay data, an AI model analyzes the data, and presents specific issues and areas for improvement. Specific embodiments of the system are described below.

[1262] System Configuration

[1263] This system consists of a user's terminal, a server, and an AI model.

[1264] 1. On the user's device:

[1265] Users play the game and create play data, which is also responsible for uploading the play data to the server.

[1266] Receive feedback and provide an interface for users to review.

[1267] 2. Server:

[1268] Receives and stores play data and converts it into an analyzable format.

[1269] The converted data is passed to the AI ​​model and the analysis results are received.

[1270] The analysis results are processed into a user-friendly format and sent to the terminal.

[1271] 3. AI model:

[1272] The system learns the play data of professional gamers in advance and analyzes the user's play data.

[1273] Compare user actions and tactics with professional gamer data to identify issues and areas for improvement.

[1274] System action

[1275] This system's processing consists of a series of steps, from uploading the user's play data to providing feedback. The specific operation of each component is as follows:

[1276] Server Operation

[1277] Receiving play data:

[1278] The server receives play data uploaded by users. The received data is first saved in a specified directory.

[1279] Transforming data:

[1280] The server converts the saved play data into an analyzable format, for example, by extracting specific frames from video data and converting operation log data into a time-stamped format.

[1281] Sending data:

[1282] The converted play data is sent to the AI ​​model, which then performs analysis based on this data.

[1283] Receiving and processing analysis results:

[1284] The server receives the analysis results from the AI ​​model and processes them into a user-friendly format, such as a text report, a graphical dashboard, or a list of specific improvements.

[1285] How AI models work

[1286] Analysis of gameplay data:

[1287] The AI ​​model analyzes the user's actions and tactics based on the play data received from the server. Specifically, it compares the play data with that of professional gamers and evaluates the user's movement patterns, reaction speed, tactical decisions, etc.

[1288] Identifying issues and areas for improvement:

[1289] Based on the analysis results, the system extracts issues in the user's gameplay and specific areas for improvement, such as "the timing of the shot is 0.2 seconds late" or "moving to cover in a specific area is inappropriate."

[1290] Device behavior

[1291] Uploading gameplay data:

[1292] The user uploads their gameplay data from their device to the server, which then begins analysis on the server side.

[1293] Receiving and viewing feedback:

[1294] The terminal receives the feedback sent from the server and presents it to the user. The feedback is displayed visually and is provided in a form that is easy for the user to understand and put into action.

[1295] Specific examples

[1296] Example 1: Analysis of play data in FPS games

[1297] Users upload their FPS gameplay videos from their devices to a server.

[1298] The server receives the video data, extracts specific frames, and converts them into an analyzable format.

[1299] The AI ​​model analyzes gameplay data and discovers that the user's shooting timing is slower than that of professional gamers, and identifies improper cover movements.

[1300] Based on the analysis results received from the AI ​​model, the server generates a feedback report containing specific improvements, such as "the timing of the shot should be advanced by 0.2 seconds" or "quickly move to cover in specific areas," and sends it to the device.

[1301] Users can view the feedback on their device and put it into practice the next time they play the game.

[1302] The processing flow will be explained below.

[1303] Step 1:

[1304] After finishing a game, the user prepares the gameplay data (such as a replay video or operation log), and then uploads the gameplay data to the server using a dedicated application or web interface on the device.

[1305] Step 2:

[1306] The server receives play data uploaded by users and stores it in a storage directory. This storage process includes checking the integrity of the data when it is received.

[1307] Step 3:

[1308] The server converts the saved gameplay data into an analyzable format. For example, it extracts specific frames from video data and adds necessary metadata (timestamps, event logs, etc.). It also converts the operation log data into a unified format.

[1309] Step 4:

[1310] The server passes the converted data to the AI ​​model, and at the same time issues an analysis request.

[1311] Step 5:

[1312] The AI ​​model receives the transmitted play data and analyzes the user's movement patterns. For example, it compares the play data of professional gamers to evaluate the user's movements (shooting timing, movement patterns, etc.). The AI ​​model also compares the user's play data with the professional gamer's standards to perform a discrepancy analysis.

[1313] Step 6:

[1314] The AI ​​model generates analysis results and identifies the user's issues and areas for improvement. For example, specific problems such as "firing timing is 0.2 seconds late" or "cover movement is slow in certain areas" are summarized in text format along with how to improve them.

[1315] Step 7:

[1316] Based on the analysis results received from the AI ​​model, the server generates feedback reports for the user, including text reports, graphical dashboards, and lists of specific areas for improvement, as well as graphs and heat maps for visual coaching.

[1317] Step 8:

[1318] The server sends the generated feedback report to the user's device, and the analysis results are reflected on the user's personal dashboard.

[1319] Step 9:

[1320] The device receives the feedback report sent from the server and displays it in an interface that the user can view. The user can refer to this to identify problems with their gameplay and use the suggested improvements to prepare for their next gameplay.

[1321] Step 10:

[1322] Users use the feedback to implement specific improvements in their next gameplay, and then upload their gameplay data again to receive continuous feedback using the server and AI model to improve their skills.

[1323] Example 1

[1324] 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."

[1325] Conventional gameplay data analysis systems have struggled to efficiently and effectively analyze user-provided play data and identify specific issues and areas for improvement to improve the user's skills. Furthermore, there has been a lack of a way to present the analysis results in a format that users can easily understand and apply. This has resulted in users being unable to effectively utilize their play data, which has prevented them from improving their skills.

[1326] 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.

[1327] In this invention, the server includes means for receiving play data provided by a user, means for converting the received play data into an analyzable format, means for comparing and analyzing the converted data with play data of previously learned professional gamers, means for extracting issues and areas for improvement for the user based on the analysis results, means for presenting the extracted issues and areas for improvement to the user, means for the user to upload the play data to the server, means for saving the play data in a storage directory, means for extracting specific frames from the play data, means for converting operation log data into a timestamp-added format, means for receiving the analysis results from the server and processing them into a format that is easy for the user to understand, and means for providing an interface for visually displaying feedback to the user. This makes it possible to effectively analyze the user's play data, allowing the user to easily understand specific issues and areas for improvement and put them into action.

[1328] "Play data" refers to information such as operation logs and video files that are generated by the user while playing the game.

[1329] A "server" is a device that receives play data provided by users, stores it, converts it into an analyzable format, sends it to an AI model, and receives the analysis results.

[1330] A "terminal" is a computer device that a user operates to create play data, upload it to a server, and receive and check the analysis results.

[1331] An "AI model" is an artificial intelligence program that learns the play data of professional gamers in advance, analyzes the user's play data, and extracts issues and areas for improvement.

[1332] "Professional gamer play data" refers to information such as operation logs and video files generated by professional gamers while playing games.

[1333] A "parseable format" is a specific data format that an AI model requires to parse play data.

[1334] "Operation log data" is data that records operations and actions performed by a user while playing a game.

[1335] The "time stamped format" is a data format in which time information is added to the operation log.

[1336] "Analysis results" are information on issues and areas for improvement derived after the AI ​​model analyzes the user's play data.

[1337] "Feedback" is information used to present analysis results and areas for improvement to the user.

[1338] The "interface" is the part of the software that allows the user to send and receive data to and from the server and view feedback.

[1339] This system allows users to provide their own gameplay data, which is then analyzed by an AI model, which then presents specific issues and areas for improvement. This system consists of a user's device, a server, and an AI model.

[1340] System Configuration

[1341] 1. User's device

[1342] The user's terminal is a device for playing games and creating game data. The user records their gameplay and saves the play data on the terminal. The saved play data is uploaded to the server via the terminal. The terminal also receives feedback from the server and provides an interface that the user can check.

[1343] 2. Server

[1344] The server receives gameplay data uploaded by users and saves it in a designated directory. The received data is converted into an analyzable format, and the converted data is sent to the AI ​​model. The server then processes the analysis results from the AI ​​model into a format that is easy for users to understand. Examples include text reports, graphical dashboards, and lists of specific improvements.

[1345] 3. AI Model

[1346] The AI ​​model learns from professional gamer play data in advance and analyzes the user's play data. The AI ​​model compares the user's actions and tactics with the professional gamer data to identify issues and areas for improvement. For example, these include "shooting timing is 0.2 seconds late" or "moving to cover in a specific area is inappropriate."

[1347] Example of a system

[1348] Taking an FPS game as an example, a user uploads a video of their FPS gameplay from their device to a server. The server receives the video data, extracts specific frames, and converts them into an analyzable format. The AI ​​model analyzes the play data and identifies that the user's shooting timing is slower than that of professional gamers or that their cover movement is inappropriate. Based on these analysis results, the server generates a feedback report containing specific improvements, such as "shoot 0.2 seconds earlier" or "move to cover more quickly in certain areas," and sends it to the device. The user can then review the feedback on their device and put it into practice the next time they play the game.

[1349] Prompt Sentence Examples

[1350] You can request an analysis from the AI ​​model by entering a prompt like the one below.

[1351] "Please analyze my latest FPS gameplay video and let me know what specific improvements I can make."

[1352] "Based on this play data, please tell me what I need to improve on compared to professional gamers."

[1353] The present invention allows users to effectively analyze their own gameplay data and understand specific issues and areas for improvement, thereby providing specific guidance for users to improve their gaming skills.

[1354] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1355] Step 1: Creating and uploading user play data

[1356] Users record their own gameplay and save the play data on their device. Then, they upload the recorded play data to the server through the device interface. The input is the user's gameplay data (e.g., "gameplay.mp4"), and the output is the play data uploaded to the server. Specifically, users press the "Upload" button, select a file, and send it to the server.

[1357] Step 2: Receiving and saving your play data

[1358] The server receives the play data sent by the user and saves it in a temporary buffer. It then moves and saves the received play data to a specified save directory. The input is the play data sent by the user, and the output is the play data stored in the save directory. Specifically, the play data is saved in the " / uploads" directory and is finally moved to the " / processed_data" directory.

[1359] Step 3: Convert your game data

[1360] The server converts the saved play data into an analyzable format. Specifically, it extracts specific frames from the video data and converts them into image files, and converts the operation log data into a format with a timestamp. The input is the play data saved on the server, and the output is the data converted into an analyzable format. Specifically, it extracts one image every 30 frames and saves it as "frame_0001.png" or similar.

[1361] Step 4: Request data analysis

[1362] The server sends the converted play data to the AI ​​model and requests it to analyze it. A specific API is used for sending the data. The input is the converted play data, and the output is the analysis results from the AI ​​model. Specifically, a POST request is sent to "http: / / aimodelserver / analyze" and the converted data is attached and sent.

[1363] Step 5: Receiving and processing the analysis results

[1364] The server receives the analysis results from the AI ​​model and processes them into a format that is easy for users to understand. The input is the analysis results obtained from the AI ​​model, and the output is feedback that can be viewed by the user. Specific operations include generating text reports, graphical dashboards, and lists of specific areas for improvement. For example, information such as "insufficient cover movement" can be expressed as "rapid cover movement should be performed in specific areas."

[1365] Step 6: Submit and view feedback

[1366] The server sends the generated feedback report to the user's device. The device then visually displays the received feedback to the user. The input is the processed feedback, and the output is the feedback information viewed by the user. Specifically, the feedback report is saved as "feedback_username_timestamp.pdf" and displayed to the user. For example, graphs and text explanations can be displayed using a PDF viewer.

[1367] The above are the specific processing steps of the program for this system.

[1368] (Application example 1)

[1369] 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."

[1370] Conventional factory robot operation management systems have had difficulty providing specific feedback to optimize robot operation efficiency and productivity, which has resulted in insufficient improvement in production efficiency and robot operating efficiency within the factory, making it difficult to achieve an optimized production process.

[1371] 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.

[1372] In this invention, the server includes means for receiving operation data provided by a user, means for converting the received operation data into an analyzable format, means for comparing and analyzing the converted data with pre-trained professional operation data, means for collecting operation data from a factory robot and analyzing it in real time to improve specific work efficiency, means for extracting user issues and areas for improvement based on the analysis results, and means for presenting the extracted issues and areas for improvement to the user. This makes it possible to analyze the operation efficiency of a factory robot in real time and provide specific areas for improvement to the user.

[1373] "User-provided operational data" refers to data about specific operations and behaviors collected from devices or systems operated by users.

[1374] "Converting into an analyzable format" refers to converting the collected raw data into a data format that can be interpreted and analyzed by AI or machine learning models.

[1375] "Comparative analysis" refers to comparing newly collected data with data from professionals who have already studied it, and evaluating and analyzing it using the same standards.

[1376] "Extracting issues and areas for improvement" refers to identifying, from the analysis results, problems with user behavior and operations and specific areas for improvement to improve efficiency.

[1377] "Presenting to the user" means providing the analysis results to the user in an easy-to-understand format so that the user can easily understand and use the results.

[1378] "Real-time analysis" refers to processing collected data immediately and generating analysis results without delay.

[1379] A "factory robot" refers to an automated machine installed to automate manufacturing operations and tasks.

[1380] The present invention provides a system that analyzes the operation data of a factory robot and presents problems and areas for improvement in real time. Specific embodiments of the system will be described below.

[1381] System Configuration

[1382] The system consists of a user's device, a server, and an AI model.

[1383] 1. On the user's device:

[1384] Tablet terminal: Used in the factory to collect robot operation data and send it to a server.

[1385] Data collection software using the MQTT protocol is used to collect data.

[1386] Additionally, an interface is provided that visually displays feedback from the server.

[1387] 2. Server:

[1388] Data reception and storage: Receives and stores operational data sent from the user terminal.

[1389] Data conversion: Converts received data into a parsable format (JSON format).

[1390] Software used: Dedicated server software is used for data collection and conversion.

[1391] Execution of AI models: Run AI models using deep learning frameworks such as TensorFlow and perform analysis.

[1392] Feedback generation: Based on the analysis results, a detailed feedback report is generated and sent to the user's device.

[1393] 3. AI model:

[1394] Data analysis: Based on the converted data, compare it with professional operational data to identify bottlenecks and issues.

[1395] Extraction of issues and improvements: Identify problems and improvements in the user's behavior and send them back to the server.

[1396] System Operation

[1397] The server receives the operational data provided by the user and converts it into an analyzable format. The converted data is sent to the AI ​​model and compared with professional data. Based on the analysis results, the user's issues and areas for improvement are extracted and the results are presented to the user. Specifically, it works as follows:

[1398] Hardware and Software

[1399] 1. Hardware:

[1400] Factory robots: Used as a source of operational data.

[1401] Tablet device: For data collection and feedback display.

[1402] 2. Software:

[1403] Data collection software: Software for collecting operational data from factory robots in real time and sending it to a server.

[1404] Server software: receives, stores, converts, and analyzes data.

[1405] AI model: Utilizes TensorFlow framework to analyze behavioral data and compare it with professional data.

[1406] Specific examples

[1407] For example, if a factory robot's operations are delayed, collecting operational data and analyzing it in real time will reveal that certain operations are slower than others. As a result of the analysis, feedback such as "The robot is slow when moving a specific part. The operation speed should be reduced by 0.5 seconds" is provided.

[1408] Prompt Sentence Examples

[1409] Here are some example prompts to input to the generative AI model:

[1410] Based on the operation data of a factory robot, please propose specific improvements to improve efficiency. The following is an example of operation data: {"Operation Data": [{"Operation 1": 1.2 seconds, "Operation 2": 0.8 seconds, ...}]}

[1411] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1412] Step 1:

[1413] Collecting user behavior data

[1414] Input: Factory robot operation data

[1415] The server receives real-time robot operation data from the user's device (tablet) via the MQTT protocol. This data is sent as raw data.

[1416] Output: raw data collected

[1417] Step 2:

[1418] Saving operation data

[1419] Input: Raw data collected

[1420] The server saves the received operational data in the specified directory in the format used for secondary storage of raw data.

[1421] Output: Saved operation data file

[1422] Step 3:

[1423] Data transformation

[1424] Input: Saved motion data file

[1425] The server converts the raw data into a JSON format that can be analyzed. For example, it extracts necessary metrics (such as operation time, distance traveled, and number of operations) from the raw data and converts them into log data with timestamps.

[1426] Output: Parsable data in JSON format

[1427] Step 4:

[1428] Sending data to the AI ​​model

[1429] Input: Parsable data in JSON format

[1430] The server then sends the converted data to the AI ​​model, typically using HTTP or gRPC as the transmission protocol.

[1431] Output: Send request to AI model

[1432] Step 5:

[1433] Analysis using AI models

[1434] Input: Parsable data sent by the server

[1435] The AI ​​model compares the received data with that of the professional, evaluating, for example, movement timing, efficiency, and movement patterns, and identifies discrepancies.

[1436] Output: Analysis results including issues and improvements

[1437] Step 6:

[1438] Generate feedback

[1439] Input: Analysis results including issues and improvements

[1440] The server generates a detailed feedback report based on the analysis results, which includes text instructions, graphs, and charts.

[1441] Output: Feedback report

[1442] Step 7:

[1443] Providing feedback to the user

[1444] Input: Feedback Report

[1445] The terminal visually displays the feedback reports received from the server, laid out on an interface that is easy for the user to understand.

[1446] Output: Feedback displayed on the user interface

[1447] 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.

[1448] The present invention relates to a system that uses an AI model to analyze play data provided by a user and presents the user with issues and areas for improvement. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide feedback that combines the analysis results with the user's emotional state. Specific embodiments of the system are described below.

[1449] System Configuration

[1450] This system consists of a user's device, a server, an AI model, and an emotion engine.

[1451] 1. On the user's device:

[1452] The user plays the game and creates play data.

[1453] Its role is to upload play data to the server and receive and check feedback.

[1454] The camera and microphone are used to capture the user's facial expressions and voice and send them to the emotion engine.

[1455] 2. Server:

[1456] Receives and stores play data and converts it into an analyzable format.

[1457] The converted data is passed to the AI ​​model and the analysis results are received.

[1458] Receives user emotion data and passes it to the emotion engine.

[1459] The analysis results are integrated with emotional data to generate a feedback report for the user.

[1460] 3. AI model:

[1461] The system learns the play data of professional gamers in advance and analyzes the user's play data.

[1462] Evaluate user actions and tactics to identify issues and areas for improvement.

[1463] 4. Emotion Engine:

[1464] It analyzes the user's facial expressions and voice while playing to recognize their emotional state (e.g., joy, anger, surprise, etc.).

[1465] The recognized emotion data is sent to the server.

[1466] System action

[1467] The system has a series of steps from uploading the user's play data to providing feedback. The specific operation of each component is as follows:

[1468] Server Operation

[1469] Receiving play data:

[1470] The server receives play data uploaded by the user and stores it in a storage directory. It also receives emotion data based on the user's facial expressions and voice data.

[1471] Transforming data:

[1472] The server converts the saved gameplay data into an analyzable format. For example, it extracts specific frames from video data and adds necessary metadata (timestamps, event logs, etc.). It also converts the operation log data into a unified format.

[1473] Sending data:

[1474] The converted play data is sent to the AI ​​model, and the emotion data is sent to the emotion engine, at the same time issuing an analysis request.

[1475] Receiving and processing analysis results:

[1476] The server receives the analysis results from the AI ​​model and the emotion data from the emotion engine, and combines them to generate feedback for the user, such as a text report, a graphical dashboard, or a list of areas for improvement.

[1477] How AI models work

[1478] Analysis of gameplay data:

[1479] The AI ​​model analyzes the user's movement patterns based on the play data sent from the server, compares it with the play data of professional gamers, and evaluates the user's movements (e.g., shooting timing, movement patterns).

[1480] Identifying issues and areas for improvement:

[1481] Based on the analysis results, the system extracts issues and specific areas for improvement in the user's gameplay, such as "the timing of the shot is 0.2 seconds late" or "moving to cover in a specific area is inappropriate."

[1482] Emotion Engine Operation

[1483] Emotional Data Analysis:

[1484] The emotion engine analyzes the user's facial expressions and voice data sent from the server to recognize the user's emotional state. For example, it quantifies the degree of "joy," "anger," or "surprise" expressed during gameplay.

[1485] Emotional Feedback:

[1486] After recognizing the emotional state, the data is sent to the server, which then integrates it with the analysis results and provides feedback according to the user's emotions.

[1487] Device behavior

[1488] Uploading gameplay and emotion data:

[1489] Users upload their play data and emotional data (facial expressions and voice) from their devices to the server, which then begins analysis on the server side.

[1490] Receiving and viewing feedback:

[1491] The terminal receives the feedback report sent from the server and presents it to the user. The feedback is displayed visually and is provided in a form that is easy for the user to understand and act on.

[1492] Specific examples

[1493] Example 1: Analysis of play data and emotion data in FPS games

[1494] User: Uploads video of their own FPS gameplay, along with facial expressions and audio data from their device to the server.

[1495] Server: Receives video data and converts it into an analyzable format. It also receives facial expression and voice data and sends them to the emotion engine.

[1496] AI model: Analyzes gameplay data and discovers that the user's shooting timing is slower than that of professional gamers, and identifies inappropriate cover movements.

[1497] Emotion engine: Based on facial expressions and voices during gameplay, it recognizes when the user is feeling stressed in a particular situation.

[1498] Server: Integrates the analysis results received from the AI ​​model and emotion engine, generates a feedback report containing specific improvement suggestions such as "You should shoot 0.2 seconds earlier," as well as emotion-based advice such as "You should try breathing exercises to reduce stress in specific areas," and sends it to the device.

[1499] User: Checks the feedback on their device and puts it into practice the next time they play the game. They then upload their play data and emotional data again, and receive continuous feedback using the server and AI model to improve their skills and mental state.

[1500] The processing flow will be explained below.

[1501] Step 1:

[1502] After finishing a game, the user saves the gameplay data (such as replay videos and operation logs) and facial expressions and voice data recorded during gameplay on the device, and then uploads this data to the server using a dedicated application or web interface.

[1503] Step 2:

[1504] The server receives play data uploaded by the user and saves it in a specified directory. It also receives the user's facial expression and voice data and prepares them for transmission to the emotion engine.

[1505] Step 3:

[1506] The server converts the saved gameplay data into an analyzable format. For example, it extracts specific frames from video data and adds necessary metadata (timestamps, event logs, etc.). It also converts the operation log data into a unified format.

[1507] Step 4:

[1508] The server sends the converted play data to the AI ​​model. At the same time, it sends the user's facial expressions and voice data to the emotion engine, and issues an analysis request.

[1509] Step 5:

[1510] The AI ​​model receives the transmitted play data and analyzes the user's movement patterns. It compares this with the play data of professional gamers, evaluates the user's movements (shooting timing, movement patterns, etc.), and analyzes the differences.

[1511] Step 6:

[1512] The emotion engine analyzes the facial and voice data sent, recognizes the user's emotional state (happiness, anger, surprise, etc.), and converts it into numerical data.

[1513] Step 7:

[1514] Based on the analysis results, the AI ​​model identifies the user's issues and areas for improvement, such as "the timing of the shot is 0.2 seconds late" or "the cover movement in a specific area is inappropriate."

[1515] Step 8:

[1516] The emotion engine sends the recognized emotion data to the server, which evaluates the user's stress level and concentration level in a particular situation based on the emotional state.

[1517] Step 9:

[1518] The server receives the analysis results from the AI ​​model and the emotional data from the emotion engine, and integrates them. For example, it associates the user's challenges in specific actions during gameplay with their emotional state at that time.

[1519] Step 10:

[1520] The server generates a feedback report for the user based on the integrated data, including suggestions for improvement such as "You should shoot 0.2 seconds earlier" and emotion-based advice such as "Try breathing exercises to reduce stress in certain areas."

[1521] Step 11:

[1522] The server generates and sends the feedback report to the user's device, which may include text reports, graphs, heat maps, etc.

[1523] Step 12:

[1524] The device receives the feedback report sent from the server and displays it in an interface that can be viewed by the user. The user can then review the presented issues and improvements and implement them in their next gameplay.

[1525] Step 13:

[1526] Users can use the feedback to implement specific improvements in their next gameplay, upload their play data and emotional data again, and use the server and AI model to receive continuous feedback and improve their skills and mental state.

[1527] Example 2

[1528] 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."

[1529] Conventional play data analysis systems focus on analyzing a user's playing performance and do not consider their emotional state, resulting in insufficient feedback to the user. As a result, it is difficult for users to comprehensively understand both their emotional state and technical issues during play, making it difficult to improve efficiently. This invention aims to integrate and analyze play data and user emotional data to more accurately and comprehensively present users' issues and areas for improvement.

[1530] 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.

[1531] In this invention, the server includes means for receiving data provided by the user, means for converting the received data into an analyzable format, means for comparing and analyzing the converted data with data from experts previously trained, means for extracting the user's issues and areas for improvement based on the analysis results, means for presenting the extracted issues and areas for improvement to the user, means for recognizing the user's emotional state and analyzing the data, and means for integrating the analyzed emotional data with the results of the comparative analysis and providing feedback to the user. This allows the user to comprehensively understand their technical issues and emotional reactions and efficiently improve their performance.

[1532] "Data provided by the user" refers to video data and operation log data that the user records of their own playing status and emotional state.

[1533] "Means for receiving" refers to the software and hardware configuration that allows the server to receive data from the user via the Internet.

[1534] "Means of converting into an analyzable format" refers to the process of converting data received from users into a format that can be analyzed by an AI model, such as by extracting specific frames from videos or standardizing the format of operation logs.

[1535] "Means for comparative analysis" refers to algorithms and AI models that compare the converted data with pre-trained professional data to identify users' playing patterns and technical issues.

[1536] "Means for extracting issues and areas for improvement" refers to the process for automatically identifying technical issues and specific ways to improve users' play data from the analysis results of the AI ​​model.

[1537] "Means of presenting to the user" refers to a user interface and report generation function that displays the extracted issues and areas for improvement in a format that is easy for the user to understand.

[1538] "Means for recognizing emotional state" refers to an algorithm and analysis engine for analyzing and quantifying the emotional state based on the user's facial expressions and voice data while playing.

[1539] "Means for providing feedback" refers to software and hardware configurations for generating text reports and graphical dashboards that integrate technical issues and emotional states to provide easy-to-understand feedback to users.

[1540] MODE FOR CARRYING OUT THE INVENTION

[1541] This invention relates to a system that analyzes play data and emotional data provided by users, extracts and presents the user's issues and areas for improvement. This system is composed of a user terminal, a server, an AI model, and an emotional engine.

[1542] System Configuration

[1543] 1. On the user's device:

[1544] A user plays a game and creates play data (video data and operation log data).

[1545] Its role is to upload play data and emotional data (facial expressions and voice data) to the server and receive and confirm feedback. Files are selected and uploaded via a dedicated application or web interface.

[1546] At this time, the user's facial expressions and voice are captured using a camera and microphone and sent to the server as emotional data.

[1547] 2. Server:

[1548] The server receives gameplay data uploaded by users and saves it in a specified directory. The saved data is then converted into an analyzable format. For example, specific frames are extracted from video data, necessary metadata is added, and operation log data is converted into a unified format.

[1549] The converted play data is sent to the AI ​​model, which issues an analysis request. Emotion data is also sent to the emotion engine, which issues an emotion analysis request.

[1550] It receives the analysis results from the AI ​​model and the emotion engine, integrates them, and generates a feedback report for the user, which is provided in a format that is easy for the user to understand.

[1551] 3. AI model:

[1552] Based on the play data sent from the server, the user's movement patterns are analyzed by comparing them with the play data of professionals, using an AI model that has been trained in advance using the play data of professionals.

[1553] Based on the analysis results, technical issues and specific areas for improvement can be identified. For example, specific suggestions such as "the timing of shooting is delayed" or "moving to cover in a specific area is inappropriate" can be made.

[1554] 4. Emotion Engine:

[1555] The system analyzes the user's facial expressions and voice data sent from the server to recognize the user's emotional state. For example, it quantifies emotional states such as "joy," "anger," and "surprise" while playing.

[1556] The recognized emotion data is sent to the server, which then integrates it with the analysis results and provides feedback that takes the user's emotion data into account.

[1557] Specific examples

[1558] Example 1: Analysis of play data and emotion data in FPS games

[1559] User: After playing an FPS game, upload the gameplay video and facial expressions and voice data (emotion data) recorded during the gameplay to the server using a dedicated app. Click the upload button in the app, select the file, and then use the "Upload" button.

[1560] Server: Receives video data and converts it into an analyzable format. It adds metadata (timestamps, event logs) and converts operation log data into a unified format. It also sends facial expression and voice data to the emotion engine.

[1561] AI model: Analyzes gameplay data and detects when a user's shooting timing is delayed compared to a professional. It also identifies inappropriate cover movement. For example, it detects when a user's shooting timing is delayed by 0.2 seconds.

[1562] Emotion engine: Based on facial expressions and voices during gameplay, it recognizes when a user is feeling stressed in a particular situation. For example, it recognizes that "stress levels are high in a particular area."

[1563] Server: Integrates the analysis results from the AI ​​model and emotion engine to generate a feedback report with specific improvements such as "the timing of the shot should be advanced by 0.2 seconds" as well as emotion-based advice such as "try breathing exercises to reduce stress in specific areas."

[1564] User: Checks the feedback on their device and puts it into practice the next time they play the game. They then upload their play data and emotional data again, and receive continuous feedback using the server and AI model to improve their skills and mental state.

[1565] Examples of prompt statements

[1566] "Based on gameplay data and emotional data from FPS games, analyze users' issues and areas for improvement and provide specific feedback. For example, if a user's shooting timing is slow, provide specific ways to improve, and include advice on how to relax for users who are feeling stressed."

[1567] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1568] Step 1: Upload your gameplay data

[1569] Users upload gameplay videos and emotional data (facial expressions and voice) from their own devices to the server. Specifically, they use a dedicated application or web interface to select the gameplay data file and emotional data and click the "Upload" button.

[1570] Input: Gameplay video, operation log data, facial expression and voice data.

[1571] Output: The data uploaded to the server.

[1572] Step 2: Saving gameplay data and emotion data

[1573] The server receives play data and emotion data uploaded by users and temporarily stores them in a specified directory. It manages the data by dividing it into folders based on the user's identification information.

[1574] Input: Uploaded data.

[1575] Output: Data saved in the save directory.

[1576] Step 3: Convert your game data

[1577] The server converts the saved gameplay data into an analyzable format. Specifically, it extracts specific frames from the video data, adds necessary metadata (timestamps, event logs), and converts the operation log data into a unified format.

[1578] Input: Saved play data.

[1579] Output: Transformed, parseable data.

[1580] Step 4: Issue an analysis request and send data

[1581] The server sends the converted play data to the AI ​​model and issues an analysis request. At the same time, it also sends the emotion data to the emotion engine and issues an emotion analysis request. Specifically, it sends the data to the AI ​​model and emotion engine via an API request.

[1582] Input: Converted play data, emotion data.

[1583] Output: Data sent to the AI ​​model and emotion engine.

[1584] Step 5: Analyzing play data with an AI model

[1585] The AI ​​model receives play data sent from the server and compares it with professional play data to analyze the user's movement patterns, specifically evaluating shooting timing and movement patterns to identify the user's technical issues.

[1586] Input: Play data sent to the AI ​​model.

[1587] Output: Analysis results including technical issues and improvements.

[1588] Step 6: Analyze the sentiment data

[1589] The emotion engine analyzes the user's facial expressions and voice data sent from the server to recognize the user's emotional state, quantifying the degree of the emotional state and identifying the emotional response in a specific situation.

[1590] Input: Facial and speech data sent to the emotion engine.

[1591] Output: Quantified data indicating emotional state.

[1592] Step 7: Integrating analysis results with emotion data

[1593] The server receives the analysis results from the AI ​​model and the emotional data from the emotion engine, and then integrates them to generate a feedback report for the user. Specifically, it creates feedback that encompasses both technical and emotional issues.

[1594] Input: Analysis results, emotion data.

[1595] Output: Consolidated feedback report.

[1596] Step 8: Generate and display feedback

[1597] The server sends the generated feedback report to the user's device, which visually displays the received feedback and provides it to the user in a format that is easy for the user to understand, such as through a text report or a graphical dashboard.

[1598] Input: Consolidated feedback report.

[1599] Output: Feedback displayed on the user's terminal.

[1600] (Application example 2)

[1601] 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."

[1602] Simply analyzing motion data is insufficient for improving user performance and solving problems. More effective feedback is needed, especially by taking into account the operator's emotional state. However, currently there is no system that can integrate and analyze motion data and emotional data and provide accurate feedback based on that. Therefore, the realization of a system that can simultaneously analyze a user's motion and emotional state and provide comprehensive feedback that takes both into account is a challenge.

[1603] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving motion data provided by the user, means for converting the received motion data into an analyzable format, means for comparing and analyzing the converted data with pre-trained reference data, means for extracting the user's issues and areas for improvement based on the analysis results, means for analyzing the user's facial expression and voice data to recognize their emotional state, and means for integrating the analysis results and the emotional data and presenting feedback to the user. This enables comprehensive and effective feedback that takes into account both the user's motion performance and emotional state.

[1604] "Operation data" refers to data relating to actions and operations provided by the user, and includes the patterns and timing of those actions, error information, and the like.

[1605] An "analyzable format" is data received that has been converted into a format suitable for analysis by machine learning models and algorithms.

[1606] "Reference data" refers to data that has been learned in advance, and includes, as specific standards, best practices from other users and data from professionals.

[1607] "Issues" refer to problems or areas that need improvement in the user's actions or operations.

[1608] "Improvements" refer to specific methods or suggestions for making user actions or operations more efficient and effective.

[1609] "Facial expression data" is data obtained from the user's facial expressions, and serves as a basis for analyzing the emotional state.

[1610] "Voice data" is data obtained from the user's vocalizations and tone of voice, and serves as the basis for analyzing the emotional state.

[1611] "Emotional state" refers to the user's emotional state, and is expressed as numerical values ​​or categories of emotions such as stress, joy, surprise, etc.

[1612] "Feedback" refers to specific improvement suggestions and advice provided to users based on the analysis results and emotional data.

[1613] The present invention is a system that integrates and analyzes motion data and emotion data, and provides feedback to the user on areas for improvement based on the results. Specifically, the system receives the user's motion data and emotion data and analyzes them on a server to improve the user's performance. The specific system configuration and operation are described below.

[1614] System Configuration

[1615] This system consists of the following elements:

[1616] 1. On the user's device:

[1617] Operational data: Collecting data on user operations and behavior. Specific examples include operation logs on a manufacturing line and machine operation logs.

[1618] Emotion data: The camera and microphone are used to capture the user's facial expressions and voice.

[1619] 2. Server:

[1620] Data reception: Receives and stores the motion data and emotion data sent from the user's device.

[1621] Data conversion: Converts received data into an analyzable format. This process involves extracting specific frames from video data and adding timestamps and event logs.

[1622] Data analysis: The converted data is analyzed using an AI model and emotion engine to identify the user's issues and areas for improvement. The AI ​​model compares the user's movements with those of professionals and evaluates their movements.

[1623] Feedback generation: Integrates analysis results and emotional data to generate feedback for users, including specific improvements and advice.

[1624] 3. AI model:

[1625] Movement data analysis: An AI model that has learned from professional movement data performs comparative analysis with the user's movement data.

[1626] Identifying issues: Identifying delays and errors in user actions and extracting areas for improvement.

[1627] 4. Emotion Engine:

[1628] Emotion analysis: Analyzes the user's facial expression and voice data to quantify their emotional state.

[1629] Emotional feedback: Based on the user's emotional state, the areas where the user is feeling stressed or tired are identified and reflected in the analysis results.

[1630] System Operation

[1631] The server receives the user's motion and emotion data, integrates it, and converts it into an analyzable format. It then analyzes the data using an AI model and emotion engine, identifying issues and areas for improvement based on the analysis results. It then integrates the analysis results with the emotion data and provides feedback to the user. The feedback includes not only specific improvements for improving motion efficiency and reducing errors, but also advice that takes into account the operator's emotional aspects, such as stress management and improving concentration.

[1632] Specific examples

[1633] For example, if the system performs analysis based on data provided by an operator working on a production line, it may generate the following feedback: "Operation delay time: 0.2 seconds. Number of operation errors: 5. Stress level: High. Suggested improvement: Increase operator breaks to increase operation speed and reduce the occurrence of errors."

[1634] Prompt Sentence Examples

[1635] An example prompt for using a generative model: "Analyze the robot operation data and the operator's emotional data, and generate specific feedback for operational efficiency and error correction."

[1636] The present invention enables comprehensive and effective feedback that takes into account both the user's motion performance and emotional state.

[1637] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1638] Step 1:

[1639] Users collect their own motion data and emotional data on their devices. Motion data includes operation logs and machine operation logs. Emotion data is captured using a camera and microphone to capture facial expressions and voice. The collected data is temporarily stored in the device (input: user motion data, facial expression data, voice data / output: temporarily stored data).

[1640] Step 2:

[1641] The device uploads the collected motion and emotion data to a server, which receives the data and stores it in dedicated storage (input: temporary data / output: server storage).

[1642] Step 3:

[1643] The server converts the received motion data into an analyzable format. For example, it extracts specific frames from video data and adds timestamps and event logs. It also converts the operation log into a unified format (input: motion data, emotion data / output: analyzable format data).

[1644] Step 4:

[1645] The server sends the converted motion data to the AI ​​model, which then compares it with the professional's motion data to analyze the user's motion and identify issues and areas for improvement (input: data in an analyzable format / output: list of issues and areas for improvement).

[1646] Step 5:

[1647] The server sends facial expression data and voice data to the emotion engine, which analyzes the user's emotional state and expresses it in numerical values ​​and categories (input: facial expression data, voice data / output: emotional state data).

[1648] Step 6:

[1649] The server integrates the motion analysis results from the AI ​​model with the emotional state data from the emotion engine. Based on this integrated data, it generates feedback for the user. The feedback includes specific improvements to improve motion efficiency and reduce errors, as well as advice that takes emotional aspects into consideration (input: list of issues and improvements, emotional state data; output: feedback report).

[1650] Step 7:

[1651] The server sends the generated feedback report to the user's device, where the user can check the report and implement specific improvement measures (input: feedback report / output: user checks and implements feedback).

[1652] These steps provide comprehensive feedback that takes into account the user's motion performance and emotional state, resulting in motion efficiency and error improvement.

[1653] 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.

[1654] 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.

[1655] 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.

[1656] 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.

[1657] 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.

[1658] 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.

[1659] 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).

[1660] 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.

[1661] 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."

[1662] 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.

[1663] 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).

[1664] 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.

[1665] 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.

[1666] 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.

[1667] 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.

[1668] 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.

[1669] 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.

[1670] 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.

[1671] 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.

[1672] 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.

[1673] 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.

[1674] The following is further disclosed regarding the above embodiment.

[1675] (Claim 1)

[1676] means for receiving play data provided by a user;

[1677] A means for converting the received play data into an analyzable format;

[1678] A means for comparing and analyzing the converted data with pre-trained play data of professional gamers;

[1679] A means of extracting user issues and areas for improvement based on the analysis results,

[1680] A means for presenting the extracted issues and areas for improvement to the user;

[1681] A system including:

[1682] (Claim 2)

[1683] 10. The system of claim 1, further comprising means for storing the user's play data after receiving it.

[1684] (Claim 3)

[1685] 10. The system of claim 1, further comprising means for providing an interface for visually displaying the analysis results.

[1686] "Example 1"

[1687] (Claim 1)

[1688] means for receiving play data provided by a user;

[1689] A means for converting the received play data into an analyzable format;

[1690] A means for comparing and analyzing the converted data with pre-trained play data of professional gamers;

[1691] A means of extracting user issues and areas for improvement based on the analysis results,

[1692] A means for presenting the extracted issues and areas for improvement to the user;

[1693] A means for users to upload play data to a server;

[1694] A means for saving play data to a save directory;

[1695] A means for extracting a specific frame from play data;

[1696] a means for converting the operation log data into a time-stamped format;

[1697] A means for receiving the analysis results from the server and processing them into a format that is easy for the user to understand;

[1698] means for providing an interface for displaying visual feedback to a user;

[1699] A system including:

[1700] (Claim 2)

[1701] 10. The system of claim 1, further comprising means for storing the user's play data after receiving it.

[1702] (Claim 3)

[1703] 10. The system of claim 1, further comprising means for providing an interface for visually displaying the analysis results.

[1704] "Application Example 1"

[1705] (Claim 1)

[1706] means for receiving user-provided operational data;

[1707] means for converting the received motion data into a parsable format;

[1708] A means for comparing and analyzing the converted data with pre-trained professional motion data;

[1709] A means of extracting user issues and areas for improvement based on the analysis results,

[1710] A means for presenting the extracted issues and areas for improvement to the user;

[1711] A means for collecting operational data from factory robots and analyzing it in real time to improve the efficiency of specific tasks;

[1712] A system including:

[1713] (Claim 2)

[1714] 10. The system of claim 1, further comprising means for storing the user's motion data after receiving it.

[1715] (Claim 3)

[1716] 10. The system of claim 1, further comprising means for providing an interface for visually displaying the analysis results.

[1717] "Example 2: Combining Emotion Engines"

[1718] (Claim 1)

[1719] means for receiving user provided data;

[1720] means for converting the received data into a parsable format;

[1721] A means for performing comparative analysis based on the converted data with data of experts previously trained;

[1722] A means of extracting user issues and areas for improvement based on the analysis results,

[1723] A means for presenting the extracted issues and areas for improvement to the user;

[1724] means for recognizing a user's emotional state and analyzing the data;

[1725] a means for integrating the analyzed emotion data and the comparative analysis results and providing feedback to the user;

[1726] A system including:

[1727] (Claim 2)

[1728] 10. The system of claim 1, further comprising means for storing the user's data after receiving it.

[1729] (Claim 3)

[1730] 10. The system of claim 1, further comprising: means for providing an interface for visually displaying the analysis results and the integrated feedback.

[1731] "Application example 2 when combining emotion engines"

[1732] (Claim 1)

[1733] means for receiving user-provided operational data;

[1734] means for converting the received motion data into a parsable format;

[1735] A means for performing comparative analysis based on the converted data with previously learned reference data;

[1736] A means of extracting user issues and areas for improvement based on the analysis results,

[1737] means for analyzing facial expression and voice data of a user to recognize the emotional state of the user;

[1738] A means for integrating the analysis results with the emotion data and presenting feedback to the user;

[1739] A system including:

[1740] (Claim 2)

[1741] 10. The system of claim 1, further comprising means for storing the user's motion data and emotion data after receiving the data.

[1742] (Claim 3)

[1743] 10. The system of claim 1, further comprising means for providing an interface for visually displaying the analysis results and the emotion data. [Explanation of symbols]

[1744] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving play data provided by a user; A means for converting the received play data into an analyzable format; A means for comparing and analyzing the converted data with pre-trained play data of professional gamers; A means of extracting user issues and areas for improvement based on the analysis results, A means for presenting the extracted issues and areas for improvement to the user; A system including:

2. 10. The system of claim 1, further comprising means for storing the user's play data after receiving it.

3. The system of claim 1 further comprising means for providing an interface for visually displaying the analysis results.

Images