system

Abstract

We provide the system. [Solution] A means for users to select from multiple templates according to their purpose, A means for the terminal to receive input from the user and send it to the server, A means of initializing and training an AI model based on the data received by the server, A means by which the server evaluates the trained model and provides the results to the terminal, A means for users to adjust the model based on evaluation results, A system that includes this.

Description

Technical Field

[0004] , , , ,

[0005] , , , , ,

[0003] , , , ,

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] Conventional AI customization platforms require technical expertise and have the problem that it is difficult for users to easily build an AI system tailored to their own purposes. As a result, there is a problem that individuals and companies face technical barriers and soaring costs when creating AI tools that meet their own needs.

Means for Solving the Problems

[0005] The present invention provides a system that solves the aforementioned problems by comprising means for the user to select from multiple templates according to their purpose, means for a terminal to receive input from the user and send it to a server, means for the server to initialize and train an AI model based on the received data, means for the server to evaluate the trained model and provide the results to the terminal, means for the user to adjust the model based on the results, and means for the terminal to provide the user with an intuitive interface. This makes it possible to build an efficient and customizable AI tool without requiring specialized knowledge.

[0006] "User" refers to an individual or organization that uses the system to build or customize AI models.

[0007] A "template" refers to a set of predefined settings that users can select according to their purpose, and which form the basis of an AI model.

[0008] A "terminal" refers to a computer or device that a user uses to interface with a system.

[0009] A "server" refers to a central computer system that receives user input and initializes, trains, and evaluates AI models.

[0010] An "AI model" refers to an artificial intelligence-based algorithm or program that is trained according to the user's needs.

[0011] "Training" refers to the process of improving the performance of an AI model by having it learn using specific data.

[0012] "Evaluation" refers to the process of measuring the performance of a trained AI model using test data and confirming its accuracy and responsiveness.

[0013] An "interface" refers to a screen or operating environment that allows users to intuitively operate a system. [Brief explanation of the drawing]

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

Embodiments for Carrying Out the Invention

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

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

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

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

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

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

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

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

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

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

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0031] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

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

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

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

[0035] This invention is a platform system that allows users to easily customize AI models. Users begin by selecting an appropriate template according to their purpose. Once the user selects a template, the terminal generates an input form based on that selection, allowing the user to input specific requirements and parameters.

[0036] After the user enters the necessary information, the terminal sends that information to the server. The server analyzes the received data and initializes an AI model based on the selected template. Subsequently, the server trains the AI ​​model using the data provided by the user to improve the model's performance.

[0037] Once training is complete, the server evaluates the AI ​​model's performance using test data and sends the evaluation results to the terminal. The terminal displays the evaluation results to the user, providing visual feedback. Based on these results, the user can adjust the model as needed.

[0038] For example, if a user wants to create a chatbot for customer support, they select a chatbot template and input response patterns and a specific customer information dataset. The server then uses this information to train a model and generate an optimal chatbot model. This model is eventually deployed to streamline the user's customer support operations.

[0039] This system allows users to efficiently customize and utilize AI models tailored to their specific needs, even without technical expertise.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The user logs into the platform and specifies a template to select an AI model that suits their purpose. The device immediately recognizes the user's selection and prepares for the next step.

[0043] Step 2:

[0044] The device generates a customizable input form based on the selected template. This form includes fields where the user can input the parameters and data required for the AI ​​model.

[0045] Step 3:

[0046] The user enters the required information into the input form and completes the setup. For example, if the user is a customer support chatbot, they would enter response patterns and customer datasets.

[0047] Step 4:

[0048] The terminal confirms the user's input and sends it to the server. This initiates the AI ​​model initialization process on the server side.

[0049] Step 5:

[0050] The server initializes the AI ​​model based on the information it receives. The model is built using the selected template and the provided data.

[0051] Step 6:

[0052] The server begins training the AI ​​model. It uses user data to improve the model's performance and apply the optimal algorithm.

[0053] Step 7:

[0054] After training is complete, the server evaluates the AI ​​model using test data. It then compiles the evaluation results and calculates performance metrics.

[0055] Step 8:

[0056] The server sends the evaluation results to the terminal. The terminal displays the evaluation results to the user and also provides graphical feedback.

[0057] Step 9:

[0058] The user reviews the evaluation results and adjusts the model as needed. This step aims to improve the model's accuracy and responsiveness.

[0059] Step 10:

[0060] After the user completes the model adjustments, the final model is confirmed. The server saves this final model and makes it available for use in the production environment.

[0061] (Example 1)

[0062] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0063] Traditional AI model customization and training require advanced technical knowledge, making them difficult for the average user to access and utilize. Furthermore, optimizing AI models to meet industry-specific needs is challenging, highlighting the need for more flexible and intuitive customization.

[0064] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0065] In this invention, the server includes means for initializing a generated AI model based on received information and performing calculations based on the data; means for evaluating the data-processed model and transmitting the evaluation information to a terminal; and means for adjusting the generated AI model using a format for a specific domain. This allows users to customize the AI ​​model without requiring specialized knowledge and optimize the model to meet the specific needs of their industry.

[0066] A "user" refers to an entity that uses the system to customize or utilize AI models.

[0067] "Selection method" refers to a method or mechanism for users to choose from multiple templates according to their purpose.

[0068] A "terminal" refers to a device that receives user input and transmits that information to devices connected to a network.

[0069] "Network-connected devices" refer to electronic devices used to process received information and perform initialization and computational processing on AI models.

[0070] A "generative AI model" refers to the structure of artificial intelligence that is customized according to the user's purpose and trained for specific tasks.

[0071] "Data-based computation" refers to the computational process of training and optimizing AI models using received data.

[0072] "Evaluation information" refers to the results of measuring the performance and accuracy of an AI model after data processing.

[0073] A "specifically designed format" refers to a format that includes customized templates and settings suited to a particular industry or field.

[0074] In implementing this invention, the user first selects an appropriate template on the platform according to their purpose. The selection means allows the user to choose options based on their industry and application, either visually or through a user interface. For example, if the goal is to automate customer support, the user can select a chatbot template.

[0075] The terminal generates an interface based on the selected template for the user to input specific requirements and parameters. This interface is designed to be intuitive and easy to use, allowing for the input of response patterns and specific datasets.

[0076] Once the user has finished inputting data, the terminal sends that data to the server. The server has the functionality to run a generated AI model based on the template selected by the user and the input data. The hardware used here typically includes server devices with powerful processing capabilities.

[0077] The server initializes the generated AI model based on the received information. During this process, the basic structure of the AI ​​model corresponding to the template is established. The server then trains the AI ​​model using the provided data. For the specific data calculations, machine learning algorithms are used to analyze large datasets and build the optimal model.

[0078] After training is complete, the server evaluates the model's performance and sends the results to the terminal. The terminal then presents this evaluation information to the user. The user can use this visual feedback to consider modifying the model and make adjustments as needed.

[0079] As a concrete example, a user could input a prompt such as, "Please generate a chatbot that can smoothly answer questions about the specifications of a new product," and the AI ​​model could be tested and improved based on this information. This system would allow users to efficiently customize and use AI models tailored to their specific needs, even without specialized knowledge.

[0080] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0081] Step 1:

[0082] Users select a template that suits their purpose on the platform. The input for selection is based on the user's objectives and industry-specific needs. As output, the selected template information is saved on the user's device. This process allows users to establish the foundation for an AI model tailored to their needs.

[0083] Step 2:

[0084] The device generates a form for the user to input the necessary information based on the template selected by the user. Specifically, it displays input fields in the UI and prompts the user to enter response patterns, dataset names, and other necessary parameters. The user's requirements are obtained as input, and this information is organized and temporarily stored on the device as output.

[0085] Step 3:

[0086] The terminal aggregates user input and prepares that data for transmission over the network. The input here is the data entered by the user into a form, and the output is a packet sent to the server. Specifically, this process involves converting the input data into an appropriate format (e.g., JSON or XML) and transmitting it according to the network protocol.

[0087] Step 4:

[0088] The server analyzes the data received from the terminal and initializes the generated AI model based on the selected template. The input is the transmitted data packets, and the output is the initialized AI model generated within the server. The specific operation includes the process of decoding the received data and constructing the model structure corresponding to the template.

[0089] Step 5:

[0090] The server trains an AI model using user-provided data. The input consists of an initialized model and a user-provided dataset, and the output is the trained model. Specifically, this involves executing machine learning algorithms and optimizing the model's parameters.

[0091] Step 6:

[0092] The server evaluates the trained AI model and measures its performance. The input is the trained model and test data, and the output is evaluation metrics. Specifically, the server inputs test data into the model and calculates metrics such as accuracy and response speed.

[0093] Step 7:

[0094] The server sends the evaluation results to the terminal. The input is performance evaluation metrics, and the output is evaluation data that can be displayed on the terminal. The specific operation includes converting the evaluation results into an appropriate format and sending them to the terminal.

[0095] Step 8:

[0096] The terminal displays evaluation results to the user in a visually accessible format. Input is evaluation data sent from the server, and output is displayed in user-friendly graph and chart formats. Specific actions include providing visual feedback using UI components.

[0097] Step 9:

[0098] The user reviews the evaluation results and modifies the model as needed. Input is the information displayed from the terminal, and output allows for new parameter settings and data additions. Specifically, adjustments such as changing parameters based on feedback and adding new data are performed.

[0099] (Application Example 1)

[0100] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0101] Traditional learning model customization and recommendation systems require technical expertise, making them difficult for the average user to utilize. Furthermore, providing optimal recommendations tailored to individual user preferences and needs quickly requires significant effort and time. To address these issues, there is a need for a more intuitive and efficient way to deliver recommendations.

[0102] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0103] In this invention, the server includes means for initializing and training a learning model based on received information, means for evaluating the trained model and providing the results to an information terminal, and means for presenting visual recommendations to the user through the information terminal. This makes it possible for users without technical expertise to easily and quickly receive recommendations tailored to their individual preferences and needs.

[0104] A "user" is an individual or group that uses the system, and is the entity that selects the information format and inputs the information.

[0105] An "information format" refers to a set of templates that users can select according to their purpose, and is a structure used for the initial setup of a system.

[0106] A "terminal" is a communication device or equipment used to receive information from a user and transmit it to a computing device.

[0107] A "computational device" is a device that acts as a server, initializing and training a learning model based on the information it receives.

[0108] A "learning model" is an artificial intelligence algorithm that is trained based on information received from users, analyzes data, and outputs the optimal result.

[0109] "Visual recommendations" refer to suggestions or options that are visually presented to the user through an information terminal.

[0110] "Evaluation results" refer to the measurement of how well a trained learning model performs on test data.

[0111] To realize this invention, a server is used as the computing device, and the user inputs information via a terminal. The server has software installed for training and initializing the learning model, and a platform such as Python or PyTorch is used to perform this role.

[0112] Users input information through an intuitive interface on their device. A mobile application is implemented on the device, built using a development framework such as React Native. This application allows users to collect data on their purchase history and interests and transmit it to a computer.

[0113] After the server analyzes the received information, it initializes a learning model based on a pre-selected information format. During this process, PyTorch is used to generate an optimal recommendation model based on the user's data. The model is evaluated using test data stored in MongoDB, and the results are provided to the user via the terminal, offering visual feedback.

[0114] For example, by inputting information about products a user has previously purchased and their search history, the server can provide more appropriate product selections for running shoes and corresponding accessories. This allows users to quickly obtain optimal recommendations tailored to their individual preferences.

[0115] An example of a specific prompt for a generative AI model is: "Create an AI model that recommends suitable products for a user who frequently purchases running shoes and is looking for the latest running wear." This enables recommendations that match the user's needs.

[0116] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0117] Step 1:

[0118] The terminal generates a user interface based on the information format selected by the user. Through this interface, the user inputs data related to purchase history and interests. The input data is parsed by the terminal into an appropriate format and prepared as a data object, such as in JSON format. This is the initial input data.

[0119] Step 2:

[0120] The terminal sends the data object entered by the user to the server. The server analyzes the received data and initializes the learning model according to a pre-selected information format. Here, the server takes in the received input data, extracts the necessary features using a natural language processing library for analysis, and determines the optimal initialization parameters. At this point, the model is ready for training.

[0121] Step 3:

[0122] The server trains a learning model based on data provided by the user. Specifically, the server extracts the necessary input parameters from the data and adjusts the model's weights using the PyTorch library. As training progresses, the model becomes capable of making recommendations that reflect the user's preferences. Here, the input is the training data, and the output is the trained model.

[0123] Step 4:

[0124] The server evaluates the performance of the trained model. The evaluation uses test data stored in MongoDB to verify how accurately the model makes recommendations that match user preferences. The evaluation results are generated as numerical data, which then serves as the input for the next step.

[0125] Step 5:

[0126] The server sends the evaluation results to the terminal, which then displays them to the user as visual feedback. The user reviews the presented results and decides whether further adjustments are needed based on their satisfaction level. Here, the input is the evaluation results, and the output is the visual feedback.

[0127] Step 6:

[0128] If a user decides to adjust the model as needed, new information and modifications are input from the terminal. Based on this information, the server retrains and adjusts the model to optimize it. This results in more accurate recommendations.

[0129] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0130] This invention is an AI model customization platform system incorporating an emotion engine that recognizes user emotions. The user first launches the platform to create an AI model tailored to their specific needs. The terminal provides an intuitive interface, allowing the user to select a template appropriate to their purpose on the spot.

[0131] Furthermore, the emotion engine analyzes the user's emotions in real time. This analysis influences the suggested templates and customization options for the user. The emotion engine includes algorithms that read emotions from the user's facial recognition data and text input.

[0132] Once the user has selected a template and customization options, the device sends that information along with the emotion engine's analysis results to the server. The server then initializes the AI ​​model based on the received data and trains it based on the user's needs and emotional state. During this process, the server can also utilize industry-specific templates.

[0133] After training, the server evaluates the AI ​​model's performance and sends the results to the terminal. The terminal then provides this feedback to the user and dynamically adjusts the user interface using an emotion engine to provide the most comfortable operating environment for the user.

[0134] For example, if a user is trying to create a customer service chatbot in a high-stress situation, the emotion engine will respond to their emotions by suggesting a relaxed-toned interface and template, helping them develop the model efficiently while mitigating stress.

[0135] By combining this with an emotion engine, users can customize AI models to be more personalized, which significantly improves the user experience.

[0136] The following describes the processing flow.

[0137] Step 1:

[0138] The user logs into the platform and specifies a template to select an AI model that suits their purpose. The terminal provides the user with an intuitive interface to support their selection.

[0139] Step 2:

[0140] The device analyzes the user's emotions using a built-in emotion engine. This emotion data is obtained from the user's facial recognition input and text analysis.

[0141] Step 3:

[0142] The device suggests the most suitable template for the user based on the analysis results from the emotion engine and applies flexible customization options. By viewing these suggestions, users can configure the model more effectively.

[0143] Step 4:

[0144] The user selects a suggested template or customization option and enters specific settings and data. The terminal aggregates this information and sends it to the server.

[0145] Step 5:

[0146] The server initializes the AI ​​model based on the received data and the user's sentiment. The server combines industry-specific templates to optimize the model according to the user's purpose.

[0147] Step 6:

[0148] The server begins training the AI ​​model. This process also utilizes information obtained from the emotion engine to build a more personalized model.

[0149] Step 7:

[0150] Once the server completes training, it evaluates the AI ​​model's performance using test data. The server then compiles the evaluation results and sends the data to the terminal.

[0151] Step 8:

[0152] The device presents the evaluation results received from the server to the user. During this process, the device continuously monitors the emotion engine data and adjusts the UI to optimize the user-generated AI experience.

[0153] Step 9:

[0154] Users can modify the AI ​​model based on the evaluation results. The device sends the modifications to the server, and any necessary retraining is performed.

[0155] Step 10:

[0156] If the user is satisfied with the final model, the server saves it and makes it available for use in the production environment. The emotion engine's support continues throughout the model's use, helping to improve the user experience.

[0157] (Example 2)

[0158] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0159] Conventional AI model customization systems have the problem of not considering the user's emotional state, resulting in an unoptimized user experience. In particular, the user interface may not respond to the user's mental state, leading to cumbersome operation, which becomes a burden on the user.

[0160] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0161] In this invention, the server includes means for analyzing the user's emotions and proposing a template based on the analysis results, means for initializing and training an AI model considering the emotion data, and means for evaluating the trained model and providing the results to the user. This makes it possible to propose the optimal template according to the user's emotions, and the operation becomes intuitive and less burdensome.

[0162] A "template" is a pre-configured design or template that users can select when customizing an AI model.

[0163] "Means of analyzing emotions" refers to processes or technologies for obtaining information from a user's face or text and recognizing their emotional state.

[0164] "Initialization" refers to the process by which an AI model builds a foundation for training based on specific settings and data received from the user.

[0165] "Training" is the process by which an AI model learns using a defined dataset and optimizes its performance.

[0166] "Evaluation" refers to the verification process conducted to measure the performance of a trained AI model and to confirm its effectiveness and accuracy.

[0167] "User interface tuning" refers to the process of modifying the appearance and behavior of an interface to make it easier to use, based on user emotions and feedback.

[0168] The present invention provides a platform for analyzing a user's emotions and customizing an AI model based on those emotions. The user first activates the system using a terminal, which provides an intuitive interface and facilitates template selection. Typical hardware includes personal computers and smartphones, while the software consists of emotion analysis algorithms and template management programs.

[0169] User sentiment analysis is performed using data from the device's camera, microphone, and keyboard input. This sentiment data is processed in real time and influences template selection. This is achieved by using machine learning algorithms to determine the user's emotional state.

[0170] Based on the sentiment analysis, the terminal suggests a template deemed optimal for the user. After the user selects a template and customizes it as needed, this information is sent from the terminal to the server. The server then initializes the AI ​​model based on the received data and performs model training that takes emotional states into account. In this process, GPUs are often used for high-speed processing.

[0171] After training, the server evaluates the AI ​​model's performance and returns the results to the terminal. Based on the sentiment analysis and evaluation results, the terminal adjusts the user interface to provide an optimal operating environment.

[0172] For example, when a user develops a chatbot for customer service, if sentiment analysis detects that the user is stressed, a relaxing template will be suggested. In this way, the user can build the model comfortably.

[0173] As an example of a prompt, users can test the AI ​​model's capabilities by entering text such as, "Please generate a friendly response for customer service."

[0174] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0175] Step 1:

[0176] The user launches the terminal. The terminal displays an intuitive user interface. It provides and displays a list of templates the user can select as input. The list of templates is displayed on the user interface as output.

[0177] Step 2:

[0178] The device analyzes the user's emotions. It uses data obtained from the device's camera and keyboard input as input. This data is analyzed using a machine learning algorithm to identify the user's emotional state. The output is information about the user's emotional state.

[0179] Step 3:

[0180] The device proposes the optimal template based on the results of the emotion analysis. The input is the emotional state information obtained in step 2. Based on this, an appropriate template is proposed, and that information is output to the user interface.

[0181] Step 4:

[0182] The user selects a template and customizes it as needed. The system accepts user selections and customization details as input. The output is the user's selected template and customization information.

[0183] Step 5:

[0184] The terminal sends the selected template and customization information to the server. As input, the user-confirmed template information is encrypted and sent to the server. The output is the data sent to the server.

[0185] Step 6:

[0186] The server initializes the AI ​​model based on the data it receives. The input consists of templates and customization information sent from the terminal. Based on this data, the server configures the AI ​​model and creates the foundation for training. The output is the initialized AI model.

[0187] Step 7:

[0188] The server trains the AI ​​model. It uses an initialized AI model and sentiment data as input. Based on this, the server trains the model and performs calculations to improve its performance. The output is the trained AI model.

[0189] Step 8:

[0190] The server evaluates the performance of the AI ​​model and sends the results to the terminal. The input is a pre-trained AI model. The server analyzes the model based on evaluation criteria and generates evaluation results. The output is a report of the evaluation results.

[0191] Step 9:

[0192] The terminal adjusts the user interface based on the evaluation results. The input consists of evaluation results and sentiment analysis information from the server. Based on this, the terminal provides the user with the most suitable interface, which is then presented to the user as output.

[0193] Step 10:

[0194] The user uses the generated AI model and inputs prompts to perform actual operations. The input is the user's prompt, such as "Please generate a friendly response for customer service." The output is the response generated by the AI ​​model.

[0195] (Application Example 2)

[0196] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0197] There is a need for technology that displays instantly optimized advertisements based on user emotions. However, conventional advertising systems do not take into account the user's emotions in the moment, limiting their ability to improve user experience and advertising effectiveness. Furthermore, there is a lack of mechanisms to analyze user emotions in real time and dynamically select and display advertisements accordingly.

[0198] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0199] In this invention, the server includes means for receiving user information and transmitting it to a communication device, means for initializing and training a generation AI model based on the data, means for evaluating the trained model and providing the results to a terminal, and means for a display device to analyze the user's facial expressions and select and present advertisements based on the results. This enables the effective presentation of advertisements that respond to the user's emotions.

[0200] A "user" refers to an entity that operates the system and selects templates and advertisements according to its purpose.

[0201] A "terminal" is a device that receives user input and exchanges information with communication devices.

[0202] A "communication device" is a device that initializes and trains a generated AI model based on received data, evaluates the model, and provides the results to the terminal.

[0203] A "generative AI model" is a form of artificial intelligence that is initialized and trained based on user data.

[0204] "Advertising" refers to information and promotional content that is selected and displayed based on the user's emotions.

[0205] A "display device" is a device that analyzes a user's facial expressions and displays advertisements based on the results.

[0206] "Facial expression analysis" is a process for determining emotions from a user's facial expressions.

[0207] The system for carrying out this invention includes a terminal, a communication device (server), and a display device. The user operates the terminal and selects a template according to their purpose. The terminal receives the user's input information and transmits it to the communication device. The communication device initializes and trains a generated AI model based on the received data. The training aims to create a model that is suitable for the user's purpose and emotional state, using industry-specific templates.

[0208] The user's device is equipped with a camera and facial recognition software (e.g., OpenCV or Google® Cloud Vision API), which allows for real-time analysis of the user's emotions. The analyzed emotion data is transmitted to a communication device and used to train and evaluate generative AI models.

[0209] The server evaluates the trained model and provides the results to the device. The device analyzes the user's facial expressions, selects advertisements based on the results, and presents them on the display device.

[0210] As a concrete example, consider a user wearing smart glasses in a park. In this situation, the user's device recognizes a relaxed facial expression, and the communication device, based on that, displays advertisements for relaxation-related products on the display device. This makes it possible to instantly provide information tailored to the user and capture their interest.

[0211] An example of a prompt to input into a generative AI model is, "Create an AI model to display ads that match a positive emotion to a user relaxing in a park." Through this prompt, it becomes possible to build a machine learning model that generates ads that best suit the user's emotions.

[0212] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0213] Step 1:

[0214] The user operates the terminal and selects a template according to their purpose. The input here is the user's selection, and the output is information about the selected template. The terminal temporarily stores the user's selection in memory, preparing it for subsequent processing.

[0215] Step 2:

[0216] The device captures images of the user's facial expressions through its camera and analyzes the emotion data using facial recognition software (e.g., OpenCV). The input is the captured facial image data, and the output is the analyzed user emotion data. The device executes an image analysis algorithm to quantify the user's subtle facial changes as emotion labels.

[0217] Step 3:

[0218] The terminal transmits selected template information and sentiment data to the communication device. The input is a pair of template information and sentiment data, and the output is a transmission completion signal to the communication device. The terminal packages the data and transmits it using a secure protocol.

[0219] Step 4:

[0220] The server (communication device) initializes and trains a generated AI model based on the data it receives. The input is template information and sentiment data, and the output is the trained AI model. The server uses a machine learning framework (e.g., TENSORFLOW®) to perform a training process suitable for the template.

[0221] Step 5:

[0222] The server evaluates the trained AI model and sends the results to the terminal. The input is the trained AI model, and the output is the evaluation result of the model. The server quantifies the model's performance and provides appropriate evaluation information to the terminal.

[0223] Step 6:

[0224] The device selects the most relevant advertisement based on the evaluation results and user facial expression analysis data, and presents it on the display device. The input is the evaluation results and emotion data, and the output is the selected advertisement content. The device searches the advertisement database for the most relevant content and displays it instantly.

[0225] Step 7:

[0226] Users view advertisements and utilize the information as needed. The input is the presented advertisement, and the output is the user's response. Users refer to the content of the advertisement and may explore further information if they are interested.

[0227] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0228] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0229] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0230] [Second Embodiment]

[0231] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0232] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0233] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0234] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0235] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0236] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0237] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0238] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0239] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0240] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0241] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0242] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0243] This invention is a platform system that allows users to easily customize AI models. Users begin by selecting an appropriate template according to their purpose. Once the user selects a template, the terminal generates an input form based on that selection, allowing the user to input specific requirements and parameters.

[0244] After the user enters the necessary information, the terminal sends that information to the server. The server analyzes the received data and initializes an AI model based on the selected template. Subsequently, the server trains the AI ​​model using the data provided by the user to improve the model's performance.

[0245] Once training is complete, the server evaluates the AI ​​model's performance using test data and sends the evaluation results to the terminal. The terminal displays the evaluation results to the user, providing visual feedback. Based on these results, the user can adjust the model as needed.

[0246] For example, if a user wants to create a chatbot for customer support, they select a chatbot template and input response patterns and a specific customer information dataset. The server then uses this information to train a model and generate an optimal chatbot model. This model is eventually deployed to streamline the user's customer support operations.

[0247] This system allows users to efficiently customize and utilize AI models tailored to their specific needs, even without technical expertise.

[0248] The following describes the processing flow.

[0249] Step 1:

[0250] The user logs into the platform and specifies a template to select an AI model that suits their purpose. The device immediately recognizes the user's selection and prepares for the next step.

[0251] Step 2:

[0252] The device generates a customizable input form based on the selected template. This form includes fields where the user can input the parameters and data required for the AI ​​model.

[0253] Step 3:

[0254] The user enters the required information into the input form and completes the setup. For example, if the user is a customer support chatbot, they would enter response patterns and customer datasets.

[0255] Step 4:

[0256] The terminal confirms the user's input and sends it to the server. This initiates the AI ​​model initialization process on the server side.

[0257] Step 5:

[0258] The server initializes the AI ​​model based on the information it receives. The model is built using the selected template and the provided data.

[0259] Step 6:

[0260] The server begins training the AI ​​model. It uses user data to improve the model's performance and apply the optimal algorithm.

[0261] Step 7:

[0262] After training is complete, the server evaluates the AI ​​model using test data. It then compiles the evaluation results and calculates performance metrics.

[0263] Step 8:

[0264] The server sends the evaluation results to the terminal. The terminal displays the evaluation results to the user and also provides graphical feedback.

[0265] Step 9:

[0266] The user reviews the evaluation results and adjusts the model as needed. This step aims to improve the model's accuracy and responsiveness.

[0267] Step 10:

[0268] After the user completes the model adjustments, the final model is confirmed. The server saves this final model and makes it available for use in the production environment.

[0269] (Example 1)

[0270] Next, we will describe Example 1. 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."

[0271] Traditional AI model customization and training require advanced technical knowledge, making them difficult for the average user to access and utilize. Furthermore, optimizing AI models to meet industry-specific needs is challenging, highlighting the need for more flexible and intuitive customization.

[0272] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0273] In this invention, the server includes means for initializing a generated AI model based on received information and performing calculations based on the data; means for evaluating the data-processed model and transmitting the evaluation information to a terminal; and means for adjusting the generated AI model using a format for a specific domain. This allows users to customize the AI ​​model without requiring specialized knowledge and optimize the model to meet the specific needs of their industry.

[0274] A "user" refers to an entity that uses the system to customize or utilize AI models.

[0275] "Selection method" refers to a method or mechanism for users to choose from multiple templates according to their purpose.

[0276] A "terminal" refers to a device that receives user input and transmits that information to devices connected to a network.

[0277] "Network-connected devices" refer to electronic devices used to process received information and perform initialization and computational processing on AI models.

[0278] A "generative AI model" refers to the structure of artificial intelligence that is customized according to the user's purpose and trained for specific tasks.

[0279] "Data-based computation" refers to the computational process of training and optimizing AI models using received data.

[0280] "Evaluation information" refers to the results of measuring the performance and accuracy of an AI model after data processing.

[0281] A "specifically designed format" refers to a format that includes customized templates and settings suited to a particular industry or field.

[0282] In implementing this invention, the user first selects an appropriate template on the platform according to their purpose. The selection means allows the user to choose options based on their industry and application, either visually or through a user interface. For example, if the goal is to automate customer support, the user can select a chatbot template.

[0283] The terminal generates an interface based on the selected template for the user to input specific requirements and parameters. This interface is designed to be intuitive and easy to use, allowing for the input of response patterns and specific datasets.

[0284] When the input from the user is completed, the terminal sends the data to the server. The server is equipped with a function to execute the AI model generated based on the template selected by the user and the input data. The hardware used here generally includes a server device with powerful processing capabilities.

[0285] The server initializes the generated AI model based on the received information. In this process, the basic structure of the AI model corresponding to the template is set. The server further trains the AI model using the provided data. For specific data operations, machine learning algorithms for analyzing a large amount of data sets and constructing an optimal model are used.

[0286] After the training is completed, the server evaluates the performance of the model and sends the result to the terminal. The terminal presents this evaluation information to the user. The user can consider modifying the model based on this visual feedback and make adjustments if necessary.

[0287] As a specific example, a scenario can be considered where the user inputs a prompt sentence such as "Please generate a chatbot that can smoothly answer questions about the specifications of new products" and tries out and improves the AI model based on this information. With this system, even without specialized knowledge, the user can efficiently customize and utilize an AI model according to the purpose.

[0288] The flow of the specific process in Example 1 will be described using FIG. 11.

[0289] Step 1:

[0290] The user selects a template suitable for the purpose on the platform. The input when selecting is based on the user's purpose and industry-specific needs. As output, the selected template information is saved on the user's terminal. By this operation, the user establishes the basis of an AI model that meets their needs.

[0291] Step 2:

[0292] The device generates a form for the user to input the necessary information based on the template selected by the user. Specifically, it displays input fields in the UI and prompts the user to enter response patterns, dataset names, and other necessary parameters. The user's requirements are obtained as input, and this information is organized and temporarily stored on the device as output.

[0293] Step 3:

[0294] The terminal aggregates user input and prepares that data for transmission over the network. The input here is the data entered by the user into a form, and the output is a packet sent to the server. Specifically, this process involves converting the input data into an appropriate format (e.g., JSON or XML) and transmitting it according to the network protocol.

[0295] Step 4:

[0296] The server analyzes the data received from the terminal and initializes the generated AI model based on the selected template. The input is the transmitted data packets, and the output is the initialized AI model generated within the server. The specific operation includes the process of decoding the received data and constructing the model structure corresponding to the template.

[0297] Step 5:

[0298] The server trains an AI model using user-provided data. The input consists of an initialized model and a user-provided dataset, and the output is the trained model. Specifically, this involves executing machine learning algorithms and optimizing the model's parameters.

[0299] Step 6:

[0300] The server evaluates the trained AI model and measures its performance. The inputs are the trained model and test data, and the evaluation metrics are generated as the output. Specifically, the operation of inputting the test data into the model and calculating indicators such as accuracy and response speed is performed.

[0301] Step 7:

[0302] The server sends the evaluation results to the terminal. The input is the metrics of the performance evaluation, and the evaluation data that can be displayed on the terminal is the output. The specific operation includes converting the evaluation results into an appropriate format and sending them to the terminal.

[0303] Step 8:

[0304] The terminal displays the evaluation results in a form that is visible to the user. The input is the evaluation data sent from the server, and the output is the display in a graph or chart format that is easy for the user to understand. The specific operation includes the process of providing visual feedback using UI components.

[0305] Step 9:

[0306] The user checks the evaluation results and modifies the model as needed. The input is the display information from the terminal, and the output enables new parameter settings and data addition. Specifically, adjustment operations such as changing parameters based on feedback and adding new data are performed.

[0307] (Application Example 1)

[0308] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0309] Traditional learning model customization and recommendation systems require technical expertise, making them difficult for the average user to utilize. Furthermore, providing optimal recommendations tailored to individual user preferences and needs quickly requires significant effort and time. To address these issues, there is a need for a more intuitive and efficient way to deliver recommendations.

[0310] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0311] In this invention, the server includes means for initializing and training a learning model based on received information, means for evaluating the trained model and providing the results to an information terminal, and means for presenting visual recommendations to the user through the information terminal. This makes it possible for users without technical expertise to easily and quickly receive recommendations tailored to their individual preferences and needs.

[0312] A "user" is an individual or group that uses the system, and is the entity that selects the information format and inputs the information.

[0313] An "information format" refers to a set of templates that users can select according to their purpose, and is a structure used for the initial setup of a system.

[0314] A "terminal" is a communication device or equipment used to receive information from a user and transmit it to a computing device.

[0315] A "computational device" is a device that acts as a server, initializing and training a learning model based on the information it receives.

[0316] A "learning model" is an artificial intelligence algorithm that is trained based on information received from users, analyzes data, and outputs the optimal result.

[0317] "Visual recommendations" refer to suggestions or options that are visually presented to the user through an information terminal.

[0318] "Evaluation results" refer to the measurement of how well a trained learning model performs on test data.

[0319] To realize this invention, a server is used as the computing device, and the user inputs information via a terminal. The server has software installed for training and initializing the learning model, and a platform such as Python or PyTorch is used to perform this role.

[0320] Users input information through an intuitive interface on their device. A mobile application is implemented on the device, built using a development framework such as React Native. This application allows users to collect data on their purchase history and interests and transmit it to a computer.

[0321] After the server analyzes the received information, it initializes a learning model based on a pre-selected information format. During this process, PyTorch is used to generate an optimal recommendation model based on the user's data. The model is evaluated using test data stored in MongoDB, and the results are provided to the user via the terminal, offering visual feedback.

[0322] For example, by inputting information about products a user has previously purchased and their search history, the server can provide more appropriate product selections for running shoes and corresponding accessories. This allows users to quickly obtain optimal recommendations tailored to their individual preferences.

[0323] An example of a specific prompt for a generative AI model is: "Create an AI model that recommends suitable products for a user who frequently purchases running shoes and is looking for the latest running wear." This enables recommendations that match the user's needs.

[0324] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0325] Step 1:

[0326] The terminal generates a user interface based on the information format selected by the user. Through this interface, the user inputs data related to purchase history and interests. The input data is parsed by the terminal into an appropriate format and prepared as a data object, such as in JSON format. This is the initial input data.

[0327] Step 2:

[0328] The terminal sends the data object entered by the user to the server. The server analyzes the received data and initializes the learning model according to a pre-selected information format. Here, the server takes in the received input data, extracts the necessary features using a natural language processing library for analysis, and determines the optimal initialization parameters. At this point, the model is ready for training.

[0329] Step 3:

[0330] The server trains a learning model based on data provided by the user. Specifically, the server extracts the necessary input parameters from the data and adjusts the model's weights using the PyTorch library. As training progresses, the model becomes capable of making recommendations that reflect the user's preferences. Here, the input is the training data, and the output is the trained model.

[0331] Step 4:

[0332] The server evaluates the performance of the trained model. The evaluation uses test data stored in MongoDB to verify how accurately the model makes recommendations that match user preferences. The evaluation results are generated as numerical data, which then serves as the input for the next step.

[0333] Step 5:

[0334] The server sends the evaluation results to the terminal, which then displays them to the user as visual feedback. The user reviews the presented results and decides whether further adjustments are needed based on their satisfaction level. Here, the input is the evaluation results, and the output is the visual feedback.

[0335] Step 6:

[0336] If a user decides to adjust the model as needed, new information and modifications are input from the terminal. Based on this information, the server retrains and adjusts the model to optimize it. This results in more accurate recommendations.

[0337] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0338] This invention is an AI model customization platform system incorporating an emotion engine that recognizes user emotions. The user first launches the platform to create an AI model tailored to their specific needs. The terminal provides an intuitive interface, allowing the user to select a template appropriate to their purpose on the spot.

[0339] Furthermore, the emotion engine analyzes the user's emotions in real time. This analysis influences the suggested templates and customization options for the user. The emotion engine includes algorithms that read emotions from the user's facial recognition data and text input.

[0340] Once the user has selected a template and customization options, the device sends that information along with the emotion engine's analysis results to the server. The server then initializes the AI ​​model based on the received data and trains it based on the user's needs and emotional state. During this process, the server can also utilize industry-specific templates.

[0341] After training, the server evaluates the AI ​​model's performance and sends the results to the terminal. The terminal then provides this feedback to the user and dynamically adjusts the user interface using an emotion engine to provide the most comfortable operating environment for the user.

[0342] For example, if a user is trying to create a customer service chatbot in a high-stress situation, the emotion engine will respond to their emotions by suggesting a relaxed-toned interface and template, helping them develop the model efficiently while mitigating stress.

[0343] By combining this with an emotion engine, users can customize AI models to be more personalized, which significantly improves the user experience.

[0344] The following describes the processing flow.

[0345] Step 1:

[0346] The user logs into the platform and specifies a template to select an AI model that suits their purpose. The terminal provides the user with an intuitive interface to support their selection.

[0347] Step 2:

[0348] The device analyzes the user's emotions using a built-in emotion engine. This emotion data is obtained from the user's facial recognition input and text analysis.

[0349] Step 3:

[0350] The device suggests the most suitable template for the user based on the analysis results from the emotion engine and applies flexible customization options. By viewing these suggestions, users can configure the model more effectively.

[0351] Step 4:

[0352] The user selects a suggested template or customization option and enters specific settings and data. The terminal aggregates this information and sends it to the server.

[0353] Step 5:

[0354] The server initializes the AI ​​model based on the received data and the user's sentiment. The server combines industry-specific templates to optimize the model according to the user's purpose.

[0355] Step 6:

[0356] The server begins training the AI ​​model. This process also utilizes information obtained from the emotion engine to build a more personalized model.

[0357] Step 7:

[0358] Once the server completes training, it evaluates the AI ​​model's performance using test data. The server then compiles the evaluation results and sends the data to the terminal.

[0359] Step 8:

[0360] The device presents the evaluation results received from the server to the user. During this process, the device continuously monitors the emotion engine data and adjusts the UI to optimize the user-generated AI experience.

[0361] Step 9:

[0362] Users can modify the AI ​​model based on the evaluation results. The device sends the modifications to the server, and any necessary retraining is performed.

[0363] Step 10:

[0364] If the user is satisfied with the final model, the server saves it and makes it available for use in the production environment. The emotion engine's support continues throughout the model's use, helping to improve the user experience.

[0365] (Example 2)

[0366] Next, we will describe Example 2. 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".

[0367] Conventional AI model customization systems have the problem of not considering the user's emotional state, resulting in an unoptimized user experience. In particular, the user interface may not respond to the user's mental state, leading to cumbersome operation, which becomes a burden on the user.

[0368] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0369] In this invention, the server includes means for analyzing the user's emotions and proposing a template based on the analysis results, means for initializing and training an AI model considering the emotion data, and means for evaluating the trained model and providing the results to the user. This makes it possible to propose the optimal template according to the user's emotions, and the operation becomes intuitive and less burdensome.

[0370] A "template" is a pre-configured design or template that users can select when customizing an AI model.

[0371] "Means of analyzing emotions" refers to processes or technologies for obtaining information from a user's face or text and recognizing their emotional state.

[0372] "Initialization" refers to the process by which an AI model builds a foundation for training based on specific settings and data received from the user.

[0373] "Training" is the process by which an AI model learns using a defined dataset and optimizes its performance.

[0374] "Evaluation" refers to the verification process conducted to measure the performance of a trained AI model and to confirm its effectiveness and accuracy.

[0375] "User interface tuning" refers to the process of modifying the appearance and behavior of an interface to make it easier to use, based on user emotions and feedback.

[0376] The present invention provides a platform for analyzing a user's emotions and customizing an AI model based on those emotions. The user first activates the system using a terminal, which provides an intuitive interface and facilitates template selection. Typical hardware includes personal computers and smartphones, while the software consists of emotion analysis algorithms and template management programs.

[0377] User sentiment analysis is performed using data from the device's camera, microphone, and keyboard input. This sentiment data is processed in real time and influences template selection. This is achieved by using machine learning algorithms to determine the user's emotional state.

[0378] Based on the sentiment analysis, the terminal suggests a template deemed optimal for the user. After the user selects a template and customizes it as needed, this information is sent from the terminal to the server. The server then initializes the AI ​​model based on the received data and performs model training that takes emotional states into account. In this process, GPUs are often used for high-speed processing.

[0379] After training, the server evaluates the AI ​​model's performance and returns the results to the terminal. Based on the sentiment analysis and evaluation results, the terminal adjusts the user interface to provide an optimal operating environment.

[0380] For example, when a user develops a chatbot for customer service, if sentiment analysis detects that the user is stressed, a relaxing template will be suggested. In this way, the user can build the model comfortably.

[0381] As an example of a prompt, users can test the AI ​​model's capabilities by entering text such as, "Please generate a friendly response for customer service."

[0382] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0383] Step 1:

[0384] The user launches the terminal. The terminal displays an intuitive user interface. It provides and displays a list of templates the user can select as input. The list of templates is displayed on the user interface as output.

[0385] Step 2:

[0386] The device analyzes the user's emotions. It uses data obtained from the device's camera and keyboard input as input. This data is analyzed using a machine learning algorithm to identify the user's emotional state. The output is information about the user's emotional state.

[0387] Step 3:

[0388] The device proposes the optimal template based on the results of the emotion analysis. The input is the emotional state information obtained in step 2. Based on this, an appropriate template is proposed, and that information is output to the user interface.

[0389] Step 4:

[0390] The user selects a template and customizes it as needed. The system accepts user selections and customization details as input. The output is the user's selected template and customization information.

[0391] Step 5:

[0392] The terminal sends the selected template and customization information to the server. As input, the user-confirmed template information is encrypted and sent to the server. The output is the data sent to the server.

[0393] Step 6:

[0394] The server initializes the AI ​​model based on the data it receives. The input consists of templates and customization information sent from the terminal. Based on this data, the server configures the AI ​​model and creates the foundation for training. The output is the initialized AI model.

[0395] Step 7:

[0396] The server trains the AI ​​model. It uses an initialized AI model and sentiment data as input. Based on this, the server trains the model and performs calculations to improve its performance. The output is the trained AI model.

[0397] Step 8:

[0398] The server evaluates the performance of the AI ​​model and sends the results to the terminal. The input is a pre-trained AI model. The server analyzes the model based on evaluation criteria and generates evaluation results. The output is a report of the evaluation results.

[0399] Step 9:

[0400] The terminal adjusts the user interface based on the evaluation results. The input consists of evaluation results and sentiment analysis information from the server. Based on this, the terminal provides the user with the most suitable interface, which is then presented to the user as output.

[0401] Step 10:

[0402] The user uses the generated AI model and inputs prompts to perform actual operations. The input is the user's prompt, such as "Please generate a friendly response for customer service." The output is the response generated by the AI ​​model.

[0403] (Application Example 2)

[0404] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0405] There is a need for technology that displays instantly optimized advertisements based on user emotions. However, conventional advertising systems do not take into account the user's emotions in the moment, limiting their ability to improve user experience and advertising effectiveness. Furthermore, there is a lack of mechanisms to analyze user emotions in real time and dynamically select and display advertisements accordingly.

[0406] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0407] In this invention, the server includes means for receiving user information and transmitting it to a communication device, means for initializing and training a generation AI model based on the data, means for evaluating the trained model and providing the results to a terminal, and means for a display device to analyze the user's facial expressions and select and present advertisements based on the results. This enables the effective presentation of advertisements that respond to the user's emotions.

[0408] A "user" refers to an entity that operates the system and selects templates and advertisements according to its purpose.

[0409] A "terminal" is a device that receives user input and exchanges information with communication devices.

[0410] A "communication device" is a device that initializes and trains a generated AI model based on received data, evaluates the model, and provides the results to the terminal.

[0411] A "generative AI model" is a form of artificial intelligence that is initialized and trained based on user data.

[0412] "Advertising" refers to information and promotional content that is selected and displayed based on the user's emotions.

[0413] A "display device" is a device that analyzes a user's facial expressions and displays advertisements based on the results.

[0414] "Facial expression analysis" is a process for determining emotions from a user's facial expressions.

[0415] The system for carrying out this invention includes a terminal, a communication device (server), and a display device. The user operates the terminal and selects a template according to their purpose. The terminal receives the user's input information and transmits it to the communication device. The communication device initializes and trains a generated AI model based on the received data. The training aims to create a model that is suitable for the user's purpose and emotional state, using industry-specific templates.

[0416] The user's device is equipped with a camera and facial recognition software (e.g., OpenCV or Google Cloud Vision API), which allows for real-time analysis of the user's emotions. The analyzed emotion data is transmitted to a communication device and used to train and evaluate generative AI models.

[0417] The server evaluates the trained model and provides the results to the device. The device analyzes the user's facial expressions, selects advertisements based on the results, and presents them on the display device.

[0418] As a concrete example, consider a user wearing smart glasses in a park. In this situation, the user's device recognizes a relaxed facial expression, and the communication device, based on that, displays advertisements for relaxation-related products on the display device. This makes it possible to instantly provide information tailored to the user and capture their interest.

[0419] An example of a prompt to input into a generative AI model is, "Create an AI model to display ads that match a positive emotion to a user relaxing in a park." Through this prompt, it becomes possible to build a machine learning model that generates ads that best suit the user's emotions.

[0420] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0421] Step 1:

[0422] The user operates the terminal and selects a template according to their purpose. The input here is the user's selection, and the output is information about the selected template. The terminal temporarily stores the user's selection in memory, preparing it for subsequent processing.

[0423] Step 2:

[0424] The device captures images of the user's facial expressions through its camera and analyzes the emotion data using facial recognition software (e.g., OpenCV). The input is the captured facial image data, and the output is the analyzed user emotion data. The device executes an image analysis algorithm to quantify the user's subtle facial changes as emotion labels.

[0425] Step 3:

[0426] The terminal transmits selected template information and sentiment data to the communication device. The input is a pair of template information and sentiment data, and the output is a transmission completion signal to the communication device. The terminal packages the data and transmits it using a secure protocol.

[0427] Step 4:

[0428] The server (communication device) initializes and trains a generated AI model based on the data it receives. The input is template information and sentiment data, and the output is the trained AI model. The server uses a machine learning framework (e.g., TensorFlow) to perform a training process appropriate to the template.

[0429] Step 5:

[0430] The server evaluates the trained AI model and sends the results to the terminal. The input is the trained AI model, and the output is the evaluation result of the model. The server quantifies the model's performance and provides appropriate evaluation information to the terminal.

[0431] Step 6:

[0432] The device selects the most relevant advertisement based on the evaluation results and user facial expression analysis data, and presents it on the display device. The input is the evaluation results and emotion data, and the output is the selected advertisement content. The device searches the advertisement database for the most relevant content and displays it instantly.

[0433] Step 7:

[0434] Users view advertisements and utilize the information as needed. The input is the presented advertisement, and the output is the user's response. Users refer to the content of the advertisement and may explore further information if they are interested.

[0435] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0436] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0437] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0438] [Third Embodiment]

[0439] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0440] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0441] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0442] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0443] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0444] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0445] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0446] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0447] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0448] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0449] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0450] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0451] This invention is a platform system that allows users to easily customize AI models. Users begin by selecting an appropriate template according to their purpose. Once the user selects a template, the terminal generates an input form based on that selection, allowing the user to input specific requirements and parameters.

[0452] After the user enters the necessary information, the terminal sends that information to the server. The server analyzes the received data and initializes an AI model based on the selected template. Subsequently, the server trains the AI ​​model using the data provided by the user to improve the model's performance.

[0453] Once training is complete, the server evaluates the AI ​​model's performance using test data and sends the evaluation results to the terminal. The terminal displays the evaluation results to the user, providing visual feedback. Based on these results, the user can adjust the model as needed.

[0454] For example, if a user wants to create a chatbot for customer support, they select a chatbot template and input response patterns and a specific customer information dataset. The server then uses this information to train a model and generate an optimal chatbot model. This model is eventually deployed to streamline the user's customer support operations.

[0455] This system allows users to efficiently customize and utilize AI models tailored to their specific needs, even without technical expertise.

[0456] The following describes the processing flow.

[0457] Step 1:

[0458] The user logs into the platform and specifies a template to select an AI model that suits their purpose. The device immediately recognizes the user's selection and prepares for the next step.

[0459] Step 2:

[0460] The device generates a customizable input form based on the selected template. This form includes fields where the user can input the parameters and data required for the AI ​​model.

[0461] Step 3:

[0462] The user enters the required information into the input form and completes the setup. For example, if the user is a customer support chatbot, they would enter response patterns and customer datasets.

[0463] Step 4:

[0464] The terminal confirms the user's input and sends it to the server. This initiates the AI ​​model initialization process on the server side.

[0465] Step 5:

[0466] The server initializes the AI ​​model based on the information it receives. The model is built using the selected template and the provided data.

[0467] Step 6:

[0468] The server begins training the AI ​​model. It uses user data to improve the model's performance and apply the optimal algorithm.

[0469] Step 7:

[0470] After training is complete, the server evaluates the AI ​​model using test data. It then compiles the evaluation results and calculates performance metrics.

[0471] Step 8:

[0472] The server sends the evaluation results to the terminal. The terminal displays the evaluation results to the user and also provides graphical feedback.

[0473] Step 9:

[0474] The user reviews the evaluation results and adjusts the model as needed. This step aims to improve the model's accuracy and responsiveness.

[0475] Step 10:

[0476] After the user completes the model adjustments, the final model is confirmed. The server saves this final model and makes it available for use in the production environment.

[0477] (Example 1)

[0478] Next, we will describe Example 1. 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."

[0479] Traditional AI model customization and training require advanced technical knowledge, making them difficult for the average user to access and utilize. Furthermore, optimizing AI models to meet industry-specific needs is challenging, highlighting the need for more flexible and intuitive customization.

[0480] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0481] In this invention, the server includes means for initializing a generated AI model based on received information and performing calculations based on the data; means for evaluating the data-processed model and transmitting the evaluation information to a terminal; and means for adjusting the generated AI model using a format for a specific domain. This allows users to customize the AI ​​model without requiring specialized knowledge and optimize the model to meet the specific needs of their industry.

[0482] A "user" refers to an entity that uses the system to customize or utilize AI models.

[0483] "Selection method" refers to a method or mechanism for users to choose from multiple templates according to their purpose.

[0484] A "terminal" refers to a device that receives user input and transmits that information to devices connected to a network.

[0485] "Network-connected devices" refer to electronic devices used to process received information and perform initialization and computational processing on AI models.

[0486] A "generative AI model" refers to the structure of artificial intelligence that is customized according to the user's purpose and trained for specific tasks.

[0487] "Data-based computation" refers to the computational process of training and optimizing AI models using received data.

[0488] "Evaluation information" refers to the results of measuring the performance and accuracy of an AI model after data processing.

[0489] A "specifically designed format" refers to a format that includes customized templates and settings suited to a particular industry or field.

[0490] In implementing this invention, the user first selects an appropriate template on the platform according to their purpose. The selection means allows the user to choose options based on their industry and application, either visually or through a user interface. For example, if the goal is to automate customer support, the user can select a chatbot template.

[0491] The terminal generates an interface based on the selected template for the user to input specific requirements and parameters. This interface is designed to be intuitive and easy to use, allowing for the input of response patterns and specific datasets.

[0492] Once the user has finished inputting data, the terminal sends that data to the server. The server has the functionality to run a generated AI model based on the template selected by the user and the input data. The hardware used here typically includes server devices with powerful processing capabilities.

[0493] The server initializes the generated AI model based on the received information. During this process, the basic structure of the AI ​​model corresponding to the template is established. The server then trains the AI ​​model using the provided data. For the specific data calculations, machine learning algorithms are used to analyze large datasets and build the optimal model.

[0494] After training is complete, the server evaluates the model's performance and sends the results to the terminal. The terminal then presents this evaluation information to the user. The user can use this visual feedback to consider modifying the model and make adjustments as needed.

[0495] As a concrete example, a user could input a prompt such as, "Please generate a chatbot that can smoothly answer questions about the specifications of a new product," and the AI ​​model could be tested and improved based on this information. This system would allow users to efficiently customize and use AI models tailored to their specific needs, even without specialized knowledge.

[0496] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0497] Step 1:

[0498] Users select a template that suits their purpose on the platform. The input for selection is based on the user's objectives and industry-specific needs. As output, the selected template information is saved on the user's device. This process allows users to establish the foundation for an AI model tailored to their needs.

[0499] Step 2:

[0500] The device generates a form for the user to input the necessary information based on the template selected by the user. Specifically, it displays input fields in the UI and prompts the user to enter response patterns, dataset names, and other necessary parameters. The user's requirements are obtained as input, and this information is organized and temporarily stored on the device as output.

[0501] Step 3:

[0502] The terminal aggregates user input and prepares that data for transmission over the network. The input here is the data entered by the user into a form, and the output is a packet sent to the server. Specifically, this process involves converting the input data into an appropriate format (e.g., JSON or XML) and transmitting it according to the network protocol.

[0503] Step 4:

[0504] The server analyzes the data received from the terminal and initializes the generated AI model based on the selected template. The input is the transmitted data packets, and the output is the initialized AI model generated within the server. The specific operation includes the process of decoding the received data and constructing the model structure corresponding to the template.

[0505] Step 5:

[0506] The server trains an AI model using user-provided data. The input consists of an initialized model and a user-provided dataset, and the output is the trained model. Specifically, this involves executing machine learning algorithms and optimizing the model's parameters.

[0507] Step 6:

[0508] The server evaluates the trained AI model and measures its performance. The input is the trained model and test data, and the output is evaluation metrics. Specifically, the server inputs test data into the model and calculates metrics such as accuracy and response speed.

[0509] Step 7:

[0510] The server sends the evaluation results to the terminal. The input is performance evaluation metrics, and the output is evaluation data that can be displayed on the terminal. The specific operation includes converting the evaluation results into an appropriate format and sending them to the terminal.

[0511] Step 8:

[0512] The terminal displays evaluation results to the user in a visually accessible format. Input is evaluation data sent from the server, and output is displayed in user-friendly graph and chart formats. Specific actions include providing visual feedback using UI components.

[0513] Step 9:

[0514] The user reviews the evaluation results and modifies the model as needed. Input is the information displayed from the terminal, and output allows for new parameter settings and data additions. Specifically, adjustments such as changing parameters based on feedback and adding new data are performed.

[0515] (Application Example 1)

[0516] Next, we will explain Application Example 1. In the following explanation, 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."

[0517] Traditional learning model customization and recommendation systems require technical expertise, making them difficult for the average user to utilize. Furthermore, providing optimal recommendations tailored to individual user preferences and needs quickly requires significant effort and time. To address these issues, there is a need for a more intuitive and efficient way to deliver recommendations.

[0518] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0519] In this invention, the server includes means for initializing and training a learning model based on received information, means for evaluating the trained model and providing the results to an information terminal, and means for presenting visual recommendations to the user through the information terminal. This makes it possible for users without technical expertise to easily and quickly receive recommendations tailored to their individual preferences and needs.

[0520] A "user" is an individual or group that uses the system, and is the entity that selects the information format and inputs the information.

[0521] An "information format" refers to a set of templates that users can select according to their purpose, and is a structure used for the initial setup of a system.

[0522] A "terminal" is a communication device or equipment used to receive information from a user and transmit it to a computing device.

[0523] A "computational device" is a device that acts as a server, initializing and training a learning model based on the information it receives.

[0524] A "learning model" is an artificial intelligence algorithm that is trained based on information received from users, analyzes data, and outputs the optimal result.

[0525] "Visual recommendations" refer to suggestions or options that are visually presented to the user through an information terminal.

[0526] "Evaluation results" refer to the measurement of how well a trained learning model performs on test data.

[0527] To realize this invention, a server is used as the computing device, and the user inputs information via a terminal. The server has software installed for training and initializing the learning model, and a platform such as Python or PyTorch is used to perform this role.

[0528] Users input information through an intuitive interface on their device. A mobile application is implemented on the device, built using a development framework such as React Native. This application allows users to collect data on their purchase history and interests and transmit it to a computer.

[0529] After the server analyzes the received information, it initializes a learning model based on a pre-selected information format. During this process, PyTorch is used to generate an optimal recommendation model based on the user's data. The model is evaluated using test data stored in MongoDB, and the results are provided to the user via the terminal, offering visual feedback.

[0530] For example, by inputting information about products a user has previously purchased and their search history, the server can provide more appropriate product selections for running shoes and corresponding accessories. This allows users to quickly obtain optimal recommendations tailored to their individual preferences.

[0531] An example of a specific prompt for a generative AI model is: "Create an AI model that recommends suitable products for a user who frequently purchases running shoes and is looking for the latest running wear." This enables recommendations that match the user's needs.

[0532] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0533] Step 1:

[0534] The terminal generates a user interface based on the information format selected by the user. Through this interface, the user inputs data related to purchase history and interests. The input data is parsed by the terminal into an appropriate format and prepared as a data object, such as in JSON format. This is the initial input data.

[0535] Step 2:

[0536] The terminal sends the data object entered by the user to the server. The server analyzes the received data and initializes the learning model according to a pre-selected information format. Here, the server takes in the received input data, extracts the necessary features using a natural language processing library for analysis, and determines the optimal initialization parameters. At this point, the model is ready for training.

[0537] Step 3:

[0538] The server trains a learning model based on data provided by the user. Specifically, the server extracts the necessary input parameters from the data and adjusts the model's weights using the PyTorch library. As training progresses, the model becomes capable of making recommendations that reflect the user's preferences. Here, the input is the training data, and the output is the trained model.

[0539] Step 4:

[0540] The server evaluates the performance of the trained model. The evaluation uses test data stored in MongoDB to verify how accurately the model makes recommendations that match user preferences. The evaluation results are generated as numerical data, which then serves as the input for the next step.

[0541] Step 5:

[0542] The server sends the evaluation results to the terminal, which then displays them to the user as visual feedback. The user reviews the presented results and decides whether further adjustments are needed based on their satisfaction level. Here, the input is the evaluation results, and the output is the visual feedback.

[0543] Step 6:

[0544] If a user decides to adjust the model as needed, new information and modifications are input from the terminal. Based on this information, the server retrains and adjusts the model to optimize it. This results in more accurate recommendations.

[0545] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0546] This invention is an AI model customization platform system incorporating an emotion engine that recognizes user emotions. The user first launches the platform to create an AI model tailored to their specific needs. The terminal provides an intuitive interface, allowing the user to select a template appropriate to their purpose on the spot.

[0547] Furthermore, the emotion engine analyzes the user's emotions in real time. This analysis influences the suggested templates and customization options for the user. The emotion engine includes algorithms that read emotions from the user's facial recognition data and text input.

[0548] Once the user has selected a template and customization options, the device sends that information along with the emotion engine's analysis results to the server. The server then initializes the AI ​​model based on the received data and trains it based on the user's needs and emotional state. During this process, the server can also utilize industry-specific templates.

[0549] After training, the server evaluates the AI ​​model's performance and sends the results to the terminal. The terminal then provides this feedback to the user and dynamically adjusts the user interface using an emotion engine to provide the most comfortable operating environment for the user.

[0550] For example, if a user is trying to create a customer service chatbot in a high-stress situation, the emotion engine will respond to their emotions by suggesting a relaxed-toned interface and template, helping them develop the model efficiently while mitigating stress.

[0551] By combining this with an emotion engine, users can customize AI models to be more personalized, which significantly improves the user experience.

[0552] The following describes the processing flow.

[0553] Step 1:

[0554] The user logs into the platform and specifies a template to select an AI model that suits their purpose. The terminal provides the user with an intuitive interface to support their selection.

[0555] Step 2:

[0556] The device analyzes the user's emotions using a built-in emotion engine. This emotion data is obtained from the user's facial recognition input and text analysis.

[0557] Step 3:

[0558] The device suggests the most suitable template for the user based on the analysis results from the emotion engine and applies flexible customization options. By viewing these suggestions, users can configure the model more effectively.

[0559] Step 4:

[0560] The user selects a suggested template or customization option and enters specific settings and data. The terminal aggregates this information and sends it to the server.

[0561] Step 5:

[0562] The server initializes the AI ​​model based on the received data and the user's sentiment. The server combines industry-specific templates to optimize the model according to the user's purpose.

[0563] Step 6:

[0564] The server begins training the AI ​​model. This process also utilizes information obtained from the emotion engine to build a more personalized model.

[0565] Step 7:

[0566] Once the server completes training, it evaluates the AI ​​model's performance using test data. The server then compiles the evaluation results and sends the data to the terminal.

[0567] Step 8:

[0568] The device presents the evaluation results received from the server to the user. During this process, the device continuously monitors the emotion engine data and adjusts the UI to optimize the user-generated AI experience.

[0569] Step 9:

[0570] Users can modify the AI ​​model based on the evaluation results. The device sends the modifications to the server, and any necessary retraining is performed.

[0571] Step 10:

[0572] If the user is satisfied with the final model, the server saves it and makes it available for use in the production environment. The emotion engine's support continues throughout the model's use, helping to improve the user experience.

[0573] (Example 2)

[0574] Next, we will describe Example 2. 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."

[0575] Conventional AI model customization systems have the problem of not considering the user's emotional state, resulting in an unoptimized user experience. In particular, the user interface may not respond to the user's mental state, leading to cumbersome operation, which becomes a burden on the user.

[0576] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0577] In this invention, the server includes means for analyzing the user's emotions and proposing a template based on the analysis results, means for initializing and training an AI model considering the emotion data, and means for evaluating the trained model and providing the results to the user. This makes it possible to propose the optimal template according to the user's emotions, and the operation becomes intuitive and less burdensome.

[0578] A "template" is a pre-configured design or template that users can select when customizing an AI model.

[0579] "Means of analyzing emotions" refers to processes or technologies for obtaining information from a user's face or text and recognizing their emotional state.

[0580] "Initialization" refers to the process by which an AI model builds a foundation for training based on specific settings and data received from the user.

[0581] "Training" is the process by which an AI model learns using a defined dataset and optimizes its performance.

[0582] "Evaluation" refers to the verification process conducted to measure the performance of a trained AI model and to confirm its effectiveness and accuracy.

[0583] "User interface tuning" refers to the process of modifying the appearance and behavior of an interface to make it easier to use, based on user emotions and feedback.

[0584] The present invention provides a platform for analyzing a user's emotions and customizing an AI model based on those emotions. The user first activates the system using a terminal, which provides an intuitive interface and facilitates template selection. Typical hardware includes personal computers and smartphones, while the software consists of emotion analysis algorithms and template management programs.

[0585] User sentiment analysis is performed using data from the device's camera, microphone, and keyboard input. This sentiment data is processed in real time and influences template selection. This is achieved by using machine learning algorithms to determine the user's emotional state.

[0586] Based on the sentiment analysis, the terminal suggests a template deemed optimal for the user. After the user selects a template and customizes it as needed, this information is sent from the terminal to the server. The server then initializes the AI ​​model based on the received data and performs model training that takes emotional states into account. In this process, GPUs are often used for high-speed processing.

[0587] After training, the server evaluates the AI ​​model's performance and returns the results to the terminal. Based on the sentiment analysis and evaluation results, the terminal adjusts the user interface to provide an optimal operating environment.

[0588] For example, when a user develops a chatbot for customer service, if sentiment analysis detects that the user is stressed, a relaxing template will be suggested. In this way, the user can build the model comfortably.

[0589] As an example of a prompt, users can test the AI ​​model's capabilities by entering text such as, "Please generate a friendly response for customer service."

[0590] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0591] Step 1:

[0592] The user launches the terminal. The terminal displays an intuitive user interface. It provides and displays a list of templates the user can select as input. The list of templates is displayed on the user interface as output.

[0593] Step 2:

[0594] The device analyzes the user's emotions. It uses data obtained from the device's camera and keyboard input as input. This data is analyzed using a machine learning algorithm to identify the user's emotional state. The output is information about the user's emotional state.

[0595] Step 3:

[0596] The device proposes the optimal template based on the results of the emotion analysis. The input is the emotional state information obtained in step 2. Based on this, an appropriate template is proposed, and that information is output to the user interface.

[0597] Step 4:

[0598] The user selects a template and customizes it as needed. The system accepts user selections and customization details as input. The output is the user's selected template and customization information.

[0599] Step 5:

[0600] The terminal sends the selected template and customization information to the server. As input, the user-confirmed template information is encrypted and sent to the server. The output is the data sent to the server.

[0601] Step 6:

[0602] The server initializes the AI ​​model based on the data it receives. The input consists of templates and customization information sent from the terminal. Based on this data, the server configures the AI ​​model and creates the foundation for training. The output is the initialized AI model.

[0603] Step 7:

[0604] The server trains the AI ​​model. It uses an initialized AI model and sentiment data as input. Based on this, the server trains the model and performs calculations to improve its performance. The output is the trained AI model.

[0605] Step 8:

[0606] The server evaluates the performance of the AI ​​model and sends the results to the terminal. The input is a pre-trained AI model. The server analyzes the model based on evaluation criteria and generates evaluation results. The output is a report of the evaluation results.

[0607] Step 9:

[0608] The terminal adjusts the user interface based on the evaluation results. The input consists of evaluation results and sentiment analysis information from the server. Based on this, the terminal provides the user with the most suitable interface, which is then presented to the user as output.

[0609] Step 10:

[0610] The user uses the generated AI model and inputs prompts to perform actual operations. The input is the user's prompt, such as "Please generate a friendly response for customer service." The output is the response generated by the AI ​​model.

[0611] (Application Example 2)

[0612] Next, we will explain application example 2. In the following explanation, 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."

[0613] There is a need for technology that displays instantly optimized advertisements based on user emotions. However, conventional advertising systems do not take into account the user's emotions in the moment, limiting their ability to improve user experience and advertising effectiveness. Furthermore, there is a lack of mechanisms to analyze user emotions in real time and dynamically select and display advertisements accordingly.

[0614] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0615] In this invention, the server includes means for receiving user information and transmitting it to a communication device, means for initializing and training a generation AI model based on the data, means for evaluating the trained model and providing the results to a terminal, and means for a display device to analyze the user's facial expressions and select and present advertisements based on the results. This enables the effective presentation of advertisements that respond to the user's emotions.

[0616] A "user" refers to an entity that operates the system and selects templates and advertisements according to its purpose.

[0617] A "terminal" is a device that receives user input and exchanges information with communication devices.

[0618] A "communication device" is a device that initializes and trains a generated AI model based on received data, evaluates the model, and provides the results to the terminal.

[0619] A "generative AI model" is a form of artificial intelligence that is initialized and trained based on user data.

[0620] "Advertising" refers to information and promotional content that is selected and displayed based on the user's emotions.

[0621] A "display device" is a device that analyzes a user's facial expressions and displays advertisements based on the results.

[0622] "Facial expression analysis" is a process for determining emotions from a user's facial expressions.

[0623] The system for carrying out this invention includes a terminal, a communication device (server), and a display device. The user operates the terminal and selects a template according to their purpose. The terminal receives the user's input information and transmits it to the communication device. The communication device initializes and trains a generated AI model based on the received data. The training aims to create a model that is suitable for the user's purpose and emotional state, using industry-specific templates.

[0624] The user's device is equipped with a camera and facial recognition software (e.g., OpenCV or Google Cloud Vision API), which allows for real-time analysis of the user's emotions. The analyzed emotion data is transmitted to a communication device and used to train and evaluate generative AI models.

[0625] The server evaluates the trained model and provides the results to the device. The device analyzes the user's facial expressions, selects advertisements based on the results, and presents them on the display device.

[0626] As a concrete example, consider a user wearing smart glasses in a park. In this situation, the user's device recognizes a relaxed facial expression, and the communication device, based on that, displays advertisements for relaxation-related products on the display device. This makes it possible to instantly provide information tailored to the user and capture their interest.

[0627] An example of a prompt to input into a generative AI model is, "Create an AI model to display ads that match a positive emotion to a user relaxing in a park." Through this prompt, it becomes possible to build a machine learning model that generates ads that best suit the user's emotions.

[0628] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0629] Step 1:

[0630] The user operates the terminal and selects a template according to their purpose. The input here is the user's selection, and the output is information about the selected template. The terminal temporarily stores the user's selection in memory, preparing it for subsequent processing.

[0631] Step 2:

[0632] The device captures images of the user's facial expressions through its camera and analyzes the emotion data using facial recognition software (e.g., OpenCV). The input is the captured facial image data, and the output is the analyzed user emotion data. The device executes an image analysis algorithm to quantify the user's subtle facial changes as emotion labels.

[0633] Step 3:

[0634] The terminal transmits selected template information and sentiment data to the communication device. The input is a pair of template information and sentiment data, and the output is a transmission completion signal to the communication device. The terminal packages the data and transmits it using a secure protocol.

[0635] Step 4:

[0636] The server (communication device) initializes and trains a generated AI model based on the data it receives. The input is template information and sentiment data, and the output is the trained AI model. The server uses a machine learning framework (e.g., TensorFlow) to perform a training process appropriate to the template.

[0637] Step 5:

[0638] The server evaluates the trained AI model and sends the results to the terminal. The input is the trained AI model, and the output is the evaluation result of the model. The server quantifies the model's performance and provides appropriate evaluation information to the terminal.

[0639] Step 6:

[0640] The device selects the most relevant advertisement based on the evaluation results and user facial expression analysis data, and presents it on the display device. The input is the evaluation results and emotion data, and the output is the selected advertisement content. The device searches the advertisement database for the most relevant content and displays it instantly.

[0641] Step 7:

[0642] Users view advertisements and utilize the information as needed. The input is the presented advertisement, and the output is the user's response. Users refer to the content of the advertisement and may explore further information if they are interested.

[0643] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0644] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0645] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0646] [Fourth Embodiment]

[0647] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0648] As shown in Figure 7, the 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.

[0649] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0650] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0651] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0652] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0653] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0654] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0655] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0656] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0657] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0658] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0659] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0660] This invention is a platform system that allows users to easily customize AI models. Users begin by selecting an appropriate template according to their purpose. Once the user selects a template, the terminal generates an input form based on that selection, allowing the user to input specific requirements and parameters.

[0661] After the user enters the necessary information, the terminal sends that information to the server. The server analyzes the received data and initializes an AI model based on the selected template. Subsequently, the server trains the AI ​​model using the data provided by the user to improve the model's performance.

[0662] Once training is complete, the server evaluates the AI ​​model's performance using test data and sends the evaluation results to the terminal. The terminal displays the evaluation results to the user, providing visual feedback. Based on these results, the user can adjust the model as needed.

[0663] For example, if a user wants to create a chatbot for customer support, they select a chatbot template and input response patterns and a specific customer information dataset. The server then uses this information to train a model and generate an optimal chatbot model. This model is eventually deployed to streamline the user's customer support operations.

[0664] This system allows users to efficiently customize and utilize AI models tailored to their specific needs, even without technical expertise.

[0665] The following describes the processing flow.

[0666] Step 1:

[0667] The user logs into the platform and specifies a template to select an AI model that suits their purpose. The device immediately recognizes the user's selection and prepares for the next step.

[0668] Step 2:

[0669] The device generates a customizable input form based on the selected template. This form includes fields where the user can input the parameters and data required for the AI ​​model.

[0670] Step 3:

[0671] The user enters the required information into the input form and completes the setup. For example, if the user is a customer support chatbot, they would enter response patterns and customer datasets.

[0672] Step 4:

[0673] The terminal confirms the user's input and sends it to the server. This initiates the AI ​​model initialization process on the server side.

[0674] Step 5:

[0675] The server initializes the AI ​​model based on the information it receives. The model is built using the selected template and the provided data.

[0676] Step 6:

[0677] The server begins training the AI ​​model. It uses user data to improve the model's performance and apply the optimal algorithm.

[0678] Step 7:

[0679] After training is complete, the server evaluates the AI ​​model using test data. It then compiles the evaluation results and calculates performance metrics.

[0680] Step 8:

[0681] The server sends the evaluation results to the terminal. The terminal displays the evaluation results to the user and also provides graphical feedback.

[0682] Step 9:

[0683] The user reviews the evaluation results and adjusts the model as needed. This step aims to improve the model's accuracy and responsiveness.

[0684] Step 10:

[0685] After the user completes the model adjustments, the final model is confirmed. The server saves this final model and makes it available for use in the production environment.

[0686] (Example 1)

[0687] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0688] Traditional AI model customization and training require advanced technical knowledge, making them difficult for the average user to access and utilize. Furthermore, optimizing AI models to meet industry-specific needs is challenging, highlighting the need for more flexible and intuitive customization.

[0689] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0690] In this invention, the server includes means for initializing a generated AI model based on received information and performing calculations based on the data; means for evaluating the data-processed model and transmitting the evaluation information to a terminal; and means for adjusting the generated AI model using a format for a specific domain. This allows users to customize the AI ​​model without requiring specialized knowledge and optimize the model to meet the specific needs of their industry.

[0691] A "user" refers to an entity that uses the system to customize or utilize AI models.

[0692] "Selection method" refers to a method or mechanism for users to choose from multiple templates according to their purpose.

[0693] A "terminal" refers to a device that receives user input and transmits that information to devices connected to a network.

[0694] "Network-connected devices" refer to electronic devices used to process received information and perform initialization and computational processing on AI models.

[0695] A "generative AI model" refers to the structure of artificial intelligence that is customized according to the user's purpose and trained for specific tasks.

[0696] "Data-based computation" refers to the computational process of training and optimizing AI models using received data.

[0697] "Evaluation information" refers to the results of measuring the performance and accuracy of an AI model after data processing.

[0698] A "specifically designed format" refers to a format that includes customized templates and settings suited to a particular industry or field.

[0699] In implementing this invention, the user first selects an appropriate template on the platform according to their purpose. The selection means allows the user to choose options based on their industry and application, either visually or through a user interface. For example, if the goal is to automate customer support, the user can select a chatbot template.

[0700] The terminal generates an interface based on the selected template for the user to input specific requirements and parameters. This interface is designed to be intuitive and easy to use, allowing for the input of response patterns and specific datasets.

[0701] Once the user has finished inputting data, the terminal sends that data to the server. The server has the functionality to run a generated AI model based on the template selected by the user and the input data. The hardware used here typically includes server devices with powerful processing capabilities.

[0702] The server initializes the generated AI model based on the received information. During this process, the basic structure of the AI ​​model corresponding to the template is established. The server then trains the AI ​​model using the provided data. For the specific data calculations, machine learning algorithms are used to analyze large datasets and build the optimal model.

[0703] After training is complete, the server evaluates the model's performance and sends the results to the terminal. The terminal then presents this evaluation information to the user. The user can use this visual feedback to consider modifying the model and make adjustments as needed.

[0704] As a concrete example, a user could input a prompt such as, "Please generate a chatbot that can smoothly answer questions about the specifications of a new product," and the AI ​​model could be tested and improved based on this information. This system would allow users to efficiently customize and use AI models tailored to their specific needs, even without specialized knowledge.

[0705] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0706] Step 1:

[0707] Users select a template that suits their purpose on the platform. The input for selection is based on the user's objectives and industry-specific needs. As output, the selected template information is saved on the user's device. This process allows users to establish the foundation for an AI model tailored to their needs.

[0708] Step 2:

[0709] The device generates a form for the user to input the necessary information based on the template selected by the user. Specifically, it displays input fields in the UI and prompts the user to enter response patterns, dataset names, and other necessary parameters. The user's requirements are obtained as input, and this information is organized and temporarily stored on the device as output.

[0710] Step 3:

[0711] The terminal aggregates user input and prepares that data for transmission over the network. The input here is the data entered by the user into a form, and the output is a packet sent to the server. Specifically, this process involves converting the input data into an appropriate format (e.g., JSON or XML) and transmitting it according to the network protocol.

[0712] Step 4:

[0713] The server analyzes the data received from the terminal and initializes the generated AI model based on the selected template. The input is the transmitted data packets, and the output is the initialized AI model generated within the server. The specific operation includes the process of decoding the received data and constructing the model structure corresponding to the template.

[0714] Step 5:

[0715] The server trains an AI model using user-provided data. The input consists of an initialized model and a user-provided dataset, and the output is the trained model. Specifically, this involves executing machine learning algorithms and optimizing the model's parameters.

[0716] Step 6:

[0717] The server evaluates the trained AI model and measures its performance. The input is the trained model and test data, and the output is evaluation metrics. Specifically, the server inputs test data into the model and calculates metrics such as accuracy and response speed.

[0718] Step 7:

[0719] The server sends the evaluation results to the terminal. The input is performance evaluation metrics, and the output is evaluation data that can be displayed on the terminal. The specific operation includes converting the evaluation results into an appropriate format and sending them to the terminal.

[0720] Step 8:

[0721] The terminal displays evaluation results to the user in a visually accessible format. Input is evaluation data sent from the server, and output is displayed in user-friendly graph and chart formats. Specific actions include providing visual feedback using UI components.

[0722] Step 9:

[0723] The user reviews the evaluation results and modifies the model as needed. Input is the information displayed from the terminal, and output allows for new parameter settings and data additions. Specifically, adjustments such as changing parameters based on feedback and adding new data are performed.

[0724] (Application Example 1)

[0725] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0726] Traditional learning model customization and recommendation systems require technical expertise, making them difficult for the average user to utilize. Furthermore, providing optimal recommendations tailored to individual user preferences and needs quickly requires significant effort and time. To address these issues, there is a need for a more intuitive and efficient way to deliver recommendations.

[0727] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0728] In this invention, the server includes means for initializing and training a learning model based on received information, means for evaluating the trained model and providing the results to an information terminal, and means for presenting visual recommendations to the user through the information terminal. This makes it possible for users without technical expertise to easily and quickly receive recommendations tailored to their individual preferences and needs.

[0729] A "user" is an individual or group that uses the system, and is the entity that selects the information format and inputs the information.

[0730] An "information format" refers to a set of templates that users can select according to their purpose, and is a structure used for the initial setup of a system.

[0731] A "terminal" is a communication device or equipment used to receive information from a user and transmit it to a computing device.

[0732] A "computational device" is a device that acts as a server, initializing and training a learning model based on the information it receives.

[0733] A "learning model" is an artificial intelligence algorithm that is trained based on information received from users, analyzes data, and outputs the optimal result.

[0734] "Visual recommendations" refer to suggestions or options that are visually presented to the user through an information terminal.

[0735] "Evaluation results" refer to the measurement of how well a trained learning model performs on test data.

[0736] To realize this invention, a server is used as the computing device, and the user inputs information via a terminal. The server has software installed for training and initializing the learning model, and a platform such as Python or PyTorch is used to perform this role.

[0737] Users input information through an intuitive interface on their device. A mobile application is implemented on the device, built using a development framework such as React Native. This application allows users to collect data on their purchase history and interests and transmit it to a computer.

[0738] After the server analyzes the received information, it initializes a learning model based on a pre-selected information format. During this process, PyTorch is used to generate an optimal recommendation model based on the user's data. The model is evaluated using test data stored in MongoDB, and the results are provided to the user via the terminal, offering visual feedback.

[0739] For example, by inputting information about products a user has previously purchased and their search history, the server can provide more appropriate product selections for running shoes and corresponding accessories. This allows users to quickly obtain optimal recommendations tailored to their individual preferences.

[0740] An example of a specific prompt for a generative AI model is: "Create an AI model that recommends suitable products for a user who frequently purchases running shoes and is looking for the latest running wear." This enables recommendations that match the user's needs.

[0741] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0742] Step 1:

[0743] The terminal generates a user interface based on the information format selected by the user. Through this interface, the user inputs data related to purchase history and interests. The input data is parsed by the terminal into an appropriate format and prepared as a data object, such as in JSON format. This is the initial input data.

[0744] Step 2:

[0745] The terminal sends the data object entered by the user to the server. The server analyzes the received data and initializes the learning model according to a pre-selected information format. Here, the server takes in the received input data, extracts the necessary features using a natural language processing library for analysis, and determines the optimal initialization parameters. At this point, the model is ready for training.

[0746] Step 3:

[0747] The server trains a learning model based on data provided by the user. Specifically, the server extracts the necessary input parameters from the data and adjusts the model's weights using the PyTorch library. As training progresses, the model becomes capable of making recommendations that reflect the user's preferences. Here, the input is the training data, and the output is the trained model.

[0748] Step 4:

[0749] The server evaluates the performance of the trained model. The evaluation uses test data stored in MongoDB to verify how accurately the model makes recommendations that match user preferences. The evaluation results are generated as numerical data, which then serves as the input for the next step.

[0750] Step 5:

[0751] The server sends the evaluation results to the terminal, which then displays them to the user as visual feedback. The user reviews the presented results and decides whether further adjustments are needed based on their satisfaction level. Here, the input is the evaluation results, and the output is the visual feedback.

[0752] Step 6:

[0753] If a user decides to adjust the model as needed, new information and modifications are input from the terminal. Based on this information, the server retrains and adjusts the model to optimize it. This results in more accurate recommendations.

[0754] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0755] This invention is an AI model customization platform system incorporating an emotion engine that recognizes user emotions. The user first launches the platform to create an AI model tailored to their specific needs. The terminal provides an intuitive interface, allowing the user to select a template appropriate to their purpose on the spot.

[0756] Furthermore, the emotion engine analyzes the user's emotions in real time. This analysis influences the suggested templates and customization options for the user. The emotion engine includes algorithms that read emotions from the user's facial recognition data and text input.

[0757] Once the user has selected a template and customization options, the device sends that information along with the emotion engine's analysis results to the server. The server then initializes the AI ​​model based on the received data and trains it based on the user's needs and emotional state. During this process, the server can also utilize industry-specific templates.

[0758] After training, the server evaluates the AI ​​model's performance and sends the results to the terminal. The terminal then provides this feedback to the user and dynamically adjusts the user interface using an emotion engine to provide the most comfortable operating environment for the user.

[0759] For example, if a user is trying to create a customer service chatbot in a high-stress situation, the emotion engine will respond to their emotions by suggesting a relaxed-toned interface and template, helping them develop the model efficiently while mitigating stress.

[0760] By combining this with an emotion engine, users can customize AI models to be more personalized, which significantly improves the user experience.

[0761] The following describes the processing flow.

[0762] Step 1:

[0763] The user logs into the platform and specifies a template to select an AI model that suits their purpose. The terminal provides the user with an intuitive interface to support their selection.

[0764] Step 2:

[0765] The device analyzes the user's emotions using a built-in emotion engine. This emotion data is obtained from the user's facial recognition input and text analysis.

[0766] Step 3:

[0767] The device suggests the most suitable template for the user based on the analysis results from the emotion engine and applies flexible customization options. By viewing these suggestions, users can configure the model more effectively.

[0768] Step 4:

[0769] The user selects a suggested template or customization option and enters specific settings and data. The terminal aggregates this information and sends it to the server.

[0770] Step 5:

[0771] The server initializes the AI ​​model based on the received data and the user's sentiment. The server combines industry-specific templates to optimize the model according to the user's purpose.

[0772] Step 6:

[0773] The server begins training the AI ​​model. This process also utilizes information obtained from the emotion engine to build a more personalized model.

[0774] Step 7:

[0775] Once the server completes training, it evaluates the AI ​​model's performance using test data. The server then compiles the evaluation results and sends the data to the terminal.

[0776] Step 8:

[0777] The device presents the evaluation results received from the server to the user. During this process, the device continuously monitors the emotion engine data and adjusts the UI to optimize the user-generated AI experience.

[0778] Step 9:

[0779] Users can modify the AI ​​model based on the evaluation results. The device sends the modifications to the server, and any necessary retraining is performed.

[0780] Step 10:

[0781] If the user is satisfied with the final model, the server saves it and makes it available for use in the production environment. The emotion engine's support continues throughout the model's use, helping to improve the user experience.

[0782] (Example 2)

[0783] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0784] Conventional AI model customization systems have the problem of not considering the user's emotional state, resulting in an unoptimized user experience. In particular, the user interface may not respond to the user's mental state, leading to cumbersome operation, which becomes a burden on the user.

[0785] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0786] In this invention, the server includes means for analyzing the user's emotions and proposing a template based on the analysis results, means for initializing and training an AI model considering the emotion data, and means for evaluating the trained model and providing the results to the user. This makes it possible to propose the optimal template according to the user's emotions, and the operation becomes intuitive and less burdensome.

[0787] A "template" is a pre-configured design or template that users can select when customizing an AI model.

[0788] "Means of analyzing emotions" refers to processes or technologies for obtaining information from a user's face or text and recognizing their emotional state.

[0789] "Initialization" refers to the process by which an AI model builds a foundation for training based on specific settings and data received from the user.

[0790] "Training" is the process by which an AI model learns using a defined dataset and optimizes its performance.

[0791] "Evaluation" refers to the verification process conducted to measure the performance of a trained AI model and to confirm its effectiveness and accuracy.

[0792] "User interface tuning" refers to the process of modifying the appearance and behavior of an interface to make it easier to use, based on user emotions and feedback.

[0793] The present invention provides a platform for analyzing a user's emotions and customizing an AI model based on those emotions. The user first activates the system using a terminal, which provides an intuitive interface and facilitates template selection. Typical hardware includes personal computers and smartphones, while the software consists of emotion analysis algorithms and template management programs.

[0794] User sentiment analysis is performed using data from the device's camera, microphone, and keyboard input. This sentiment data is processed in real time and influences template selection. This is achieved by using machine learning algorithms to determine the user's emotional state.

[0795] Based on the sentiment analysis, the terminal suggests a template deemed optimal for the user. After the user selects a template and customizes it as needed, this information is sent from the terminal to the server. The server then initializes the AI ​​model based on the received data and performs model training that takes emotional states into account. In this process, GPUs are often used for high-speed processing.

[0796] After training, the server evaluates the AI ​​model's performance and returns the results to the terminal. Based on the sentiment analysis and evaluation results, the terminal adjusts the user interface to provide an optimal operating environment.

[0797] For example, when a user develops a chatbot for customer service, if sentiment analysis detects that the user is stressed, a relaxing template will be suggested. In this way, the user can build the model comfortably.

[0798] As an example of a prompt, users can test the AI ​​model's capabilities by entering text such as, "Please generate a friendly response for customer service."

[0799] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0800] Step 1:

[0801] The user launches the terminal. The terminal displays an intuitive user interface. It provides and displays a list of templates the user can select as input. The list of templates is displayed on the user interface as output.

[0802] Step 2:

[0803] The device analyzes the user's emotions. It uses data obtained from the device's camera and keyboard input as input. This data is analyzed using a machine learning algorithm to identify the user's emotional state. The output is information about the user's emotional state.

[0804] Step 3:

[0805] The device proposes the optimal template based on the results of the emotion analysis. The input is the emotional state information obtained in step 2. Based on this, an appropriate template is proposed, and that information is output to the user interface.

[0806] Step 4:

[0807] The user selects a template and customizes it as needed. The system accepts user selections and customization details as input. The output is the user's selected template and customization information.

[0808] Step 5:

[0809] The terminal sends the selected template and customization information to the server. As input, the user-confirmed template information is encrypted and sent to the server. The output is the data sent to the server.

[0810] Step 6:

[0811] The server initializes the AI ​​model based on the data it receives. The input consists of templates and customization information sent from the terminal. Based on this data, the server configures the AI ​​model and creates the foundation for training. The output is the initialized AI model.

[0812] Step 7:

[0813] The server trains the AI ​​model. It uses an initialized AI model and sentiment data as input. Based on this, the server trains the model and performs calculations to improve its performance. The output is the trained AI model.

[0814] Step 8:

[0815] The server evaluates the performance of the AI ​​model and sends the results to the terminal. The input is a pre-trained AI model. The server analyzes the model based on evaluation criteria and generates evaluation results. The output is a report of the evaluation results.

[0816] Step 9:

[0817] The terminal adjusts the user interface based on the evaluation results. The input consists of evaluation results and sentiment analysis information from the server. Based on this, the terminal provides the user with the most suitable interface, which is then presented to the user as output.

[0818] Step 10:

[0819] The user uses the generated AI model and inputs prompts to perform actual operations. The input is the user's prompt, such as "Please generate a friendly response for customer service." The output is the response generated by the AI ​​model.

[0820] (Application Example 2)

[0821] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0822] There is a need for technology that displays instantly optimized advertisements based on user emotions. However, conventional advertising systems do not take into account the user's emotions in the moment, limiting their ability to improve user experience and advertising effectiveness. Furthermore, there is a lack of mechanisms to analyze user emotions in real time and dynamically select and display advertisements accordingly.

[0823] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0824] In this invention, the server includes means for receiving user information and transmitting it to a communication device, means for initializing and training a generation AI model based on the data, means for evaluating the trained model and providing the results to a terminal, and means for a display device to analyze the user's facial expressions and select and present advertisements based on the results. This enables the effective presentation of advertisements that respond to the user's emotions.

[0825] A "user" refers to an entity that operates the system and selects templates and advertisements according to its purpose.

[0826] A "terminal" is a device that receives user input and exchanges information with communication devices.

[0827] A "communication device" is a device that initializes and trains a generated AI model based on received data, evaluates the model, and provides the results to the terminal.

[0828] A "generative AI model" is a form of artificial intelligence that is initialized and trained based on user data.

[0829] "Advertising" refers to information and promotional content that is selected and displayed based on the user's emotions.

[0830] A "display device" is a device that analyzes a user's facial expressions and displays advertisements based on the results.

[0831] "Facial expression analysis" is a process for determining emotions from a user's facial expressions.

[0832] The system for carrying out this invention includes a terminal, a communication device (server), and a display device. The user operates the terminal and selects a template according to their purpose. The terminal receives the user's input information and transmits it to the communication device. The communication device initializes and trains a generated AI model based on the received data. The training aims to create a model that is suitable for the user's purpose and emotional state, using industry-specific templates.

[0833] The user's device is equipped with a camera and facial recognition software (e.g., OpenCV or Google Cloud Vision API), which allows for real-time analysis of the user's emotions. The analyzed emotion data is transmitted to a communication device and used to train and evaluate generative AI models.

[0834] The server evaluates the trained model and provides the results to the device. The device analyzes the user's facial expressions, selects advertisements based on the results, and presents them on the display device.

[0835] As a concrete example, consider a user wearing smart glasses in a park. In this situation, the user's device recognizes a relaxed facial expression, and the communication device, based on that, displays advertisements for relaxation-related products on the display device. This makes it possible to instantly provide information tailored to the user and capture their interest.

[0836] An example of a prompt to input into a generative AI model is, "Create an AI model to display ads that match a positive emotion to a user relaxing in a park." Through this prompt, it becomes possible to build a machine learning model that generates ads that best suit the user's emotions.

[0837] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0838] Step 1:

[0839] The user operates the terminal and selects a template according to their purpose. The input here is the user's selection, and the output is information about the selected template. The terminal temporarily stores the user's selection in memory, preparing it for subsequent processing.

[0840] Step 2:

[0841] The device captures images of the user's facial expressions through its camera and analyzes the emotion data using facial recognition software (e.g., OpenCV). The input is the captured facial image data, and the output is the analyzed user emotion data. The device executes an image analysis algorithm to quantify the user's subtle facial changes as emotion labels.

[0842] Step 3:

[0843] The terminal transmits selected template information and sentiment data to the communication device. The input is a pair of template information and sentiment data, and the output is a transmission completion signal to the communication device. The terminal packages the data and transmits it using a secure protocol.

[0844] Step 4:

[0845] The server (communication device) initializes and trains a generated AI model based on the data it receives. The input is template information and sentiment data, and the output is the trained AI model. The server uses a machine learning framework (e.g., TensorFlow) to perform a training process appropriate to the template.

[0846] Step 5:

[0847] The server evaluates the trained AI model and sends the results to the terminal. The input is the trained AI model, and the output is the evaluation result of the model. The server quantifies the model's performance and provides appropriate evaluation information to the terminal.

[0848] Step 6:

[0849] The device selects the most relevant advertisement based on the evaluation results and user facial expression analysis data, and presents it on the display device. The input is the evaluation results and emotion data, and the output is the selected advertisement content. The device searches the advertisement database for the most relevant content and displays it instantly.

[0850] Step 7:

[0851] Users view advertisements and utilize the information as needed. The input is the presented advertisement, and the output is the user's response. Users refer to the content of the advertisement and may explore further information if they are interested.

[0852] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0853] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0854] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0855] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0856] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0857] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0858] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0859] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0860] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0861] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0862] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0863] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0864] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0865] 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.

[0866] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0867] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0868] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0869] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0870] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0871] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0872] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0873] The following is further disclosed regarding the embodiments described above.

[0874] (Claim 1)

[0875] A means for users to select from multiple templates according to their purpose,

[0876] A means for the terminal to receive input from the user and send it to the server,

[0877] A means of initializing and training an AI model based on the data received by the server,

[0878] A means by which the server evaluates the trained model and provides the results to the terminal,

[0879] A means for users to adjust the model based on evaluation results,

[0880] A system that includes this.

[0881] (Claim 2)

[0882] The system according to claim 1, wherein the terminal provides means for providing an intuitive interface to the user.

[0883] (Claim 3)

[0884] The system according to claim 1, comprising a server with means for customizing an AI model using industry-specific templates.

[0885] "Example 1"

[0886] (Claim 1)

[0887] A method using multiple templates that the user can select from according to their purpose,

[0888] A means by which a terminal receives input from a user and transmits it to a device connected to the network,

[0889] A means for initializing a generated AI model and performing calculations based on data received by a network-connected device,

[0890] A means by which a network-connected device evaluates a data-processed model and transmits the evaluation information to a terminal,

[0891] A means for users to modify the model based on evaluation information,

[0892] A system that includes this.

[0893] (Claim 2)

[0894] The system according to claim 1, wherein the terminal has means for providing a visual interface to the user.

[0895] (Claim 3)

[0896] The system according to claim 1, comprising a means for a network-connected device to adjust a generated AI model using a format for a specific domain.

[0897] "Application Example 1"

[0898] (Claim 1)

[0899] A means for users to select from multiple information formats according to their purpose,

[0900] A means for a terminal to receive information from a user and transmit it to a computing device,

[0901] A means for initializing and training a learning model based on information received by a computing device,

[0902] A means by which a computing device evaluates a trained model and provides the results to an information terminal,

[0903] A means by which an information terminal presents visual recommendations to the user,

[0904] A means for users to improve the model based on evaluation results,

[0905] A system that includes this.

[0906] (Claim 2)

[0907] The system according to claim 1, wherein the information terminal is provided with means for providing an intuitive screen to the user.

[0908] (Claim 3)

[0909] The system according to claim 1, wherein the computing device has means for constructing a learning model using a business-specific format.

[0910] "Example 2 of combining an emotion engine"

[0911] (Claim 1)

[0912] A means for users to select from multiple templates according to their purpose,

[0913] A means by which the device analyzes the user's emotions and suggests templates based on the analysis results,

[0914] A means for the terminal to receive input from the user and send it to the server,

[0915] A method for initializing and training an AI model based on data received by the server, taking emotional data into consideration,

[0916] A means by which the server evaluates the trained model and provides the results to the terminal,

[0917] A means for the device to dynamically adjust the user interface while referring to sentiment analysis,

[0918] A means for users to adjust the model based on evaluation results,

[0919] A system that includes this.

[0920] (Claim 2)

[0921] The system according to claim 1, wherein the terminal provides means for providing an intuitive interface to the user.

[0922] (Claim 3)

[0923] The system according to claim 1, comprising a server with means for customizing an AI model using industry-specific templates.

[0924] "Application example 2 of combining emotional engines"

[0925] (Claim 1)

[0926] A means for users to choose from multiple designs according to their purpose,

[0927] A means for a terminal to receive user information and transmit it to a communication device,

[0928] A means for initializing and training a generated AI model based on data received by a communication device,

[0929] A means by which a communication device evaluates a trained model and provides the results to a terminal,

[0930] A means by which a display device analyzes the user's facial expressions and selects and presents advertisements based on the results,

[0931] A means for users to adjust the model based on evaluation results,

[0932] A system that includes this.

[0933] (Claim 2)

[0934] The system according to claim 1, wherein the terminal provides means for providing an intuitive interaction to the user.

[0935] (Claim 3)

[0936] The system according to claim 1, wherein the communication device has means for customizing the generated AI model using an industry-specific design. [Explanation of Symbols]

[0937] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for users to select from multiple templates according to their purpose, A means for the terminal to receive input from the user and send it to the server, A means of initializing and training an AI model based on the data received by the server, A means by which the server evaluates the trained model and provides the results to the terminal, A means for users to adjust the model based on evaluation results, A system that includes this.

2. The system according to claim 1, wherein the terminal provides means for providing an intuitive interface to the user.

3. The system according to claim 1, comprising a server with means for customizing an AI model using industry-specific templates.

Images