System

Abstract

A system is provided.SOLUTION: A system comprising: means for generating a solution to a particular task using a generative artificial intelligence model; means for receiving data input from a user; means for executing the generative artificial intelligence model based on the received data to generate a result; and means for returning the generated result to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] While the use of generative AI models has increased in recent years, current systems that can quickly provide highly accurate solutions to specific tasks are insufficient. Furthermore, there is a need for a method to effectively process user-entered data and maximize the performance of generative AI models. Furthermore, there is a need for a means to efficiently return generated results to users. Given these circumstances, there is a need for a new method or system that utilizes generative AI models. [Means for solving the problem]

[0005] The present invention provides a system including a means for generating solutions to specific tasks using a generative AI model, a means for receiving data input from a user, a means for executing the generative AI model based on the received data to generate results, and a means for returning the generated results to the user. Specifically, the system includes a procedure for training the generative AI model using a specific dataset and a means for preprocessing the input data. This invention maximizes the performance of the generative AI model and makes it possible to quickly provide users with highly accurate solutions.

[0006] A "generative artificial intelligence model" is a system that learns parameters based on a dataset and generates solutions or predictions tailored to specific tasks for new data.

[0007] A "specific task" refers to a specific problem or issue that a user wants to solve, for which a solution is required.

[0008] A "user" is a person or organization that utilizes the system to seek a solution to a particular task.

[0009] "Means for receiving data" refers to the mechanism or method for obtaining and processing information sent by a user within the system.

[0010] "Means for generating results" refers to a process or processing system that runs a generative artificial intelligence model based on input data and generates a solution or predicted result.

[0011] "Means for sending feedback to the user" refers to the method or mechanism for notifying the user of the generated solutions and prediction results.

[0012] A "dataset" is a collection of related sets of data used to train a generative artificial intelligence model.

[0013] "Preprocessing" refers to the cleaning, formatting, and other processes that are performed on data before it is input into a generative artificial intelligence model. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0022] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0035] Three main components are required to implement the present invention: a server, a terminal, and a user.

[0036] 1. Server

[0037] The server plays a central role in training the generative AI model, receiving and processing data to generate solutions and predictions. First, the server trains the generative AI model with a specific dataset. This dataset is cleaned to remove unwanted noise. Once training is complete, the generative AI model is ready to generate solutions for a specific task.

[0038] When data is sent by the user, the server receives it, preprocesses it, and feeds it into a generative AI model, which processes the data and generates a solution to a specific task. This result is formatted and forwarded to the user.

[0039] 2. Terminal

[0040] The device provides an interface for the user to input data related to a specific task. For example, this can be a dedicated application or a form in a web browser. After the user enters the data, the device sends the input data to the server. The device is also responsible for receiving responses from the server and notifying the user.

[0041] 3. Users

[0042] The user is the one seeking a solution to a particular task. They use a device to input data, and once that data is processed, they see the results sent back from the server. The user can then provide further feedback based on the results.

[0043] Example: New product idea contest

[0044] Users can come up with ideas for new smartphone features and use the device to input details of "AI battery management features," including specific requirements such as "optimizing battery consumption."

[0045] The device sends the data to a server, which receives the data, preprocesses it, and then inputs it into a generative AI model. The generative AI model analyzes the data and generates "proposals for battery management and automatic charging schedule adjustment."

[0046] The server sends the results back to the terminal, where the user can confirm the proposal. Based on the proposal, the user can create and submit an entry form for the contest.

[0047] The present invention maximizes the effectiveness of generative AI models and can quickly provide users with highly accurate solutions, enabling contest participants to quickly generate high-quality proposals and increase their competitiveness.

[0048] The processing flow will be explained below.

[0049] Step 1:

[0050] The user opens a dedicated application or web interface on the device.

[0051] Step 2:

[0052] Users input data related to a specific task, for example, "AI-powered battery management" as an "idea for a new smartphone feature."

[0053] Step 3:

[0054] The user checks the input contents and presses the send button to send the data to the server.

[0055] Step 4:

[0056] The terminal converts the data entered by the user into JSON format.

[0057] Step 5:

[0058] The device sends an HTTP POST request to the API endpoint of the specified server.

[0059] Step 6:

[0060] The server receives an HTTP request from a client and extracts the input data from the request body.

[0061] Step 7:

[0062] The server checks the format of the received data to ensure it is valid.

[0063] Step 8:

[0064] The server performs preprocessing and prepares the data for input into the generative AI model.

[0065] Step 9:

[0066] The server loads the generative AI model and performs predictions and suggestions based on the received data.

[0067] Step 10:

[0068] The server formats the generated results and creates an API response to send back to the user.

[0069] Step 11:

[0070] The terminal receives the response from the server and notifies the user.

[0071] Step 12:

[0072] The user checks the results sent back from the server. For example, they may be offered the option of "AI-based battery management and automatic charging schedule adjustment."

[0073] Step 13:

[0074] The user creates a contest entry form based on the content of their proposal and participates in the contest.

[0075] In this way, through the specific actions taken at each step, the effectiveness of the generative AI model can be maximized and highly accurate solutions can be quickly provided to users.

[0076] Example 1

[0077] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0078] In systems using existing generative AI models, data preprocessing, solution generation, and notification of results to users are often complex and time-consuming. For this reason, there is a demand for systems that can quickly provide highly accurate solutions. Another challenge is to streamline the entire process of data entry, submission, preprocessing, and formatting, and provide a seamless experience for users.

[0079] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0080] In this invention, the server includes means for a user to input data using a terminal, means for transmitting the input data from the terminal to the server, means for preprocessing the data received by the server, means for inputting the preprocessed data into a generative AI model to generate a solution, means for formatting the generated solution, means for transmitting the formatted solution to the terminal, and means for the terminal to notify the user of the solution. This makes it possible to quickly provide highly accurate solutions and provide a seamless experience to the user.

[0081] A "terminal" is a device through which a user inputs, transmits, and receives results.

[0082] The "server" is the central processing unit that receives data, pre-processes it, runs the generative AI model, and generates and transmits solutions.

[0083] A "user" is an end user who inputs data about a particular task and requests a solution.

[0084] "Data entry" is the act of a user providing information for a particular task through a terminal.

[0085] "Data transmission" is the process in which the terminal sends the input data to the server.

[0086] "Preprocessing" refers to the process of removing noise and standardizing the format of data received by the server.

[0087] A "generative AI model" is an algorithm that analyzes input data and generates solutions to specific tasks.

[0088] "Solution generation" is the process in which a generative AI model analyzes preprocessed data and outputs the solution desired by the user.

[0089] "Solution formatting" is the process of arranging the generated solution in a format that is easy for the user to understand.

[0090] "Sending a solution" is the act of the server transferring a formatted solution to the terminal.

[0091] "Result notification" is the process by which the terminal informs the user of the solution received from the server.

[0092] Three main components are required to implement the present invention: a server, a terminal, and a user.

[0093] server

[0094] The server plays a central role in training the generative AI model, receiving data, preprocessing, and generating solutions. Specifically, the server trains the generative AI model using a specific cleaned dataset. Once this training is complete, the generative AI model is ready to generate solutions for specific tasks. The specific functions of the server are as follows:

[0095] Data reception and preprocessing:

[0096] The server receives user data sent from the device. The received data is pre-processed to remove noise and missing values. Pre-processing includes cleaning the data and standardizing the format.

[0097] Inputs and processing for generative AI models:

[0098] The preprocessed data is then fed into a generative AI model, which analyzes the data and generates a solution for the specific task, such as a deep learning model or a natural language processing model.

[0099] Solution format:

[0100] The server formats the generated solutions in a user-friendly format, for example by converting them into easy-to-read sentences in natural language.

[0101] Send solution to device:

[0102] The formatted solution is then sent from the server to the device using encryption protocols to ensure data integrity and security.

[0103] Terminal

[0104] The terminal acts as an interface for users to input data, send data, and accept results. The specific functions of the terminal are as follows:

[0105] Data Input Interface:

[0106] It provides an interface for users to enter data related to a specific task, either through a dedicated application or through a form in a web browser.

[0107] Data transmission:

[0108] The entered data is sent to the server in the appropriate format.

[0109] Result notification:

[0110] The solution received from the server is notified to the user via a popup or email.

[0111] User

[0112] The user is the party seeking a solution to a specific task. The following are the specific operations performed by the user:

[0113] Data Entry:

[0114] A user uses the device to input data about a specific task, for example, a requirement for a new battery management feature called "optimize battery consumption."

[0115] Check the result:

[0116] Check the solution notified by the device and take further action as necessary. For example, consider whether to adopt the proposed "automatic charging schedule adjustment function."

[0117] Example: New product idea contest

[0118] Users come up with ideas for new smartphone features and use their device to input details of an "AI-based battery management feature," including specific requirements such as "optimizing battery consumption." The device then sends the data to a server. The server receives the data, performs preprocessing, and then inputs it into a generative AI model. The generative AI model analyzes the data and generates a "proposal for a battery management feature plus an automatic charging schedule adjustment feature." The server then sends the results back to the device, where the user can review the proposal. The user can then create and submit an entry form for the contest based on their proposal.

[0119] Prompt Sentence Examples

[0120] "Please enter your new ideas for smartphone battery management features. For example, please state specific requirements such as 'optimizing battery consumption' or 'automatically adjusting charging schedules.'"

[0121] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0122] Step 1:

[0123] The user enters data using the device interface. Specifically, the user accesses a form in a smartphone app or web browser and enters a specific requirement, such as "optimize battery consumption." The data entered by the user is in text format and contains detailed information about the specific task. This data becomes the input for the process.

[0124] Step 2:

[0125] The terminal checks the format of the entered data and converts it to the appropriate format. For example, it checks whether the character code is consistent and whether all required fields are filled in. Data that passes the format check is sent to the server. The input here is the data entered by the user, and the output is the format-checked data.

[0126] Step 3:

[0127] The server receives data sent from the terminal. The received data is temporarily stored in a database. At this time, the server uses a checksum to confirm that the data was received correctly to ensure data integrity. The input is the format-checked data sent from the terminal, and the output is the data stored in the database.

[0128] Step 4:

[0129] The server preprocesses the data it receives. Preprocessing includes removing noise, filling in missing values, and normalizing data. For example, it removes unnecessary spaces and line breaks and standardizes the format of text data. The input is the raw data stored in the database, and the output is the preprocessed data.

[0130] Step 5:

[0131] The server inputs the preprocessed data into a generative AI model, which uses natural language processing and deep learning to analyze the data and generate a solution such as "automatic adjustment of charging schedules." The input is the preprocessed data, and the output is the generated solution.

[0132] Step 6:

[0133] The server formats the generated solution in a user-friendly format. For example, it converts the raw data output by the generative AI model into natural language sentences that are easy for humans to understand. The input is the generated solution, and the output is the formatted solution.

[0134] Step 7:

[0135] The server sends the formatted solution to the terminal, using an encryption protocol to ensure data integrity and security. The input is the formatted solution, and the output is the encrypted data.

[0136] Step 8:

[0137] The device notifies the user of the solution received from the server. Specifically, the result is notified to the user using a pop-up notification or email. The input is the encrypted data sent from the server, and the output is the solution presented to the user.

[0138] Step 9:

[0139] The user checks the solution through the device and provides subsequent feedback if necessary, which is also sent to the server in a similar process for further analysis and use as training data.

[0140] The above steps result in a system that quickly provides highly accurate solutions and provides a seamless experience for users.

[0141] (Application example 1)

[0142] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0143] In modern content distribution services, users face difficulties in selecting the most suitable video content from the vast number of available options. However, the lack of appropriate recommendations based on viewing history and interests leads to a poor user experience. To solve this problem, a system is needed that automatically recommends the most suitable content in real time using user viewing data.

[0144] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0145] In this invention, the server includes means for generating a solution to a specific task using a generative artificial intelligence model, means for receiving data input from a user, means for executing the generative artificial intelligence model based on the received data to generate a result, means for automatically generating data and displaying it through an identification device, and means for returning the generated result to the user, thereby enabling optimal video content to be recommended in real time based on the user's viewing history and interests, improving the user experience.

[0146] A "generative artificial intelligence model" is an algorithm that is trained to generate solutions to specific tasks.

[0147] A "user" is an entity that provides data to the system and receives the results.

[0148] "Data receiving means" is a function for taking data input by the user into the system.

[0149] "Data pre-processing means" is a function that executes a process to convert received data into a format that is easy to analyze.

[0150] An "identification device" is a device for displaying information to a user, such as smart glasses.

[0151] "Means for automatically generating data" is a function that creates new data or content based on input data.

[0152] The "result generation means" is a function that inputs preprocessed data into a generative artificial intelligence model to generate an optimal solution.

[0153] The "result return means" is a communication and display function for providing the generated results to the user.

[0154] The system of the present invention consists of three main components: a server, a terminal, and a user. The server plays a central role in training the generative artificial intelligence model, receiving and processing data to generate solutions and recommendation results.

[0155] Server Operation

[0156] The server trains a generative artificial intelligence model using a specific dataset. The training dataset is cleaned and noise removed. Once training is complete, the generative AI model is ready to generate solutions for specific tasks. When data is submitted by the user, the server receives the data, preprocesses it, and inputs it into the generative AI model. The generative AI model processes the data and generates a solution for the specific task. The results are formatted and forwarded to the user.

[0157] Device behavior

[0158] The device provides an interface for the user to input data related to a specific task. For example, this can be a dedicated application or a form in a web browser. After the user inputs the data, the device sends the input data to a server. The device is also responsible for receiving responses from the server and notifying the user. The device also has the ability to display the results through an identification device such as smart glasses.

[0159] User Roles

[0160] A user is an entity seeking a solution to a particular task. They use a device to input data, which is processed and then the server sends back results. The user can then provide further feedback based on the results.

[0161] Example

[0162] For example, in the case of a personalized video recommendation application for smart glasses, users can use their smart glasses to select video content to watch. Data such as viewing history, interests, and viewing time are sent to a server via the device, and the server analyzes this data to recommend the most suitable content in real time. This allows users to seamlessly enjoy the latest video content that matches their interests.

[0163] Prompt Sentence Examples

[0164] User ID: user123

[0165] Viewing history: Movies, documentaries, news

[0166] Interests: Science fiction, history, modern technology

[0167] Current time: 2023-10-03T18:00:00Z"

[0168] Based on this, a generative AI model recommends the most suitable content to the user.

[0169] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0170] Step 1:

[0171] The user inputs viewing data through the smart glasses.

[0172] Input: User ID, viewing history, interests, current time.

[0173] How it works: Users use the smart glasses interface to input data such as their viewing history, interests, and the current time, which is then collected by the device.

[0174] Output: Collected data is sent to the terminal.

[0175] Step 2:

[0176] The terminal transmits user data to the server.

[0177] Input: User data collected from smart glasses.

[0178] How it works: The device sends collected user data (user ID, viewing history, interests, current time) to the server. This communication uses standard protocols such as HTTP requests.

[0179] Output: User data arrives at the server.

[0180] Step 3:

[0181] Preprocessing data received by the server.

[0182] Input: User data sent from the device.

[0183] How it works: The server cleanses the data it receives, removes noise, and converts it into a format that's easier to analyze, including imputing missing values ​​and normalizing the data.

[0184] Output: Preprocessed data is generated.

[0185] Step 4:

[0186] The server inputs the preprocessed data into the generated artificial intelligence model.

[0187] Input: Preprocessed data.

[0188] How it works: The server inputs the preprocessed data into the generative AI model to perform the analysis task. The generative AI model generates a solution to recommend the best video content based on the data.

[0189] Output: Best video content recommendation results.

[0190] Step 5:

[0191] The server returns the generated recommendation results to the device.

[0192] Input: Best video content recommendation results.

[0193] How it works: The server formats the generated recommendations and sends them back to the device, again using standard protocols such as HTTP requests.

[0194] Output: The recommended results arrive on your terminal.

[0195] Step 6:

[0196] The device notifies the user of the recommended results.

[0197] Input: The recommended results returned by the server.

[0198] How it works: The device notifies the user of the received recommendations and displays them on the smart glasses display, allowing the user to watch the most suitable video content in real time.

[0199] Output: The recommended results are displayed on the smart glasses display.

[0200] Step 7:

[0201] The user watches the recommended video content.

[0202] Input: Recommendation results displayed on smart glasses.

[0203] How it works: The user selects and watches recommended video content displayed on the smart glasses display. After viewing, the data is input back into the device for use in future recommendations.

[0204] Output: New viewing data is generated and used for the next recommendation.

[0205] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0206] To implement this invention, three main components are required: a server, a terminal, and a user. Furthermore, by combining an emotion engine that recognizes the user's emotions, the quality of the provided solution can be improved.

[0207] 1. Server

[0208] The server plays a central role in training the generative AI model, receiving and processing data sent by users to generate solutions and predictions. First, the generative AI model is trained using a specific dataset. The training data is cleaned to remove unnecessary noise. After training is complete, the generative AI model is ready to generate solutions for specific tasks.

[0209] When data is sent by the user, the server receives the data. The received data is preprocessed and input into the generative AI model. At this time, the emotion engine also analyzes the user's input data to detect the user's emotional state. The generative AI model processes the data and emotion information and generates a solution for the specific task. The result is formatted and sent back to the user.

[0210] 2. Terminal

[0211] The device provides an interface for the user to enter data related to a specific task. For example, this can be a dedicated application or a form in a web browser. After the user enters the data, the device sends the input data to the server. The device is also responsible for receiving responses from the server and notifying the user.

[0212] 3. Users

[0213] The user is the one seeking a solution to a particular task. They use a device to input data, which is then processed and the server sends back results, which the user can then use to provide further feedback.

[0214] Example: New product idea contest

[0215] Users can come up with ideas for new smartphone features and use their devices to input details of "AI-powered battery management features," including specific requirements such as "optimizing battery consumption." During this input, the emotion engine analyzes the user's input data and interactions to detect their emotional state.

[0216] The device sends the data and the detected emotion information to a server. The server receives the data, performs preprocessing, and then inputs it into a generative AI model. The generative AI model analyzes the data and emotion information and generates "proposals for battery management functions and automatic charging schedule adjustment functions."

[0217] The results are sent back from the server to the device, where the user can confirm the proposal. Since the user is in a state where they are likely to be convinced of the proposal, it is expected that the results of the emotion engine will also be reflected. Based on the proposal, the user can create and submit an entry form for the contest.

[0218] This maximizes the effectiveness of generative AI models and emotion engines, enabling us to quickly provide users with highly accurate and emotion-sensitive solutions.

[0219] The processing flow will be explained below.

[0220] Step 1:

[0221] The user opens a dedicated application or web interface on the device.

[0222] Step 2:

[0223] Users input data related to a specific task, for example, "AI-powered battery management" as an "idea for a new smartphone feature."

[0224] Step 3:

[0225] The user checks the input contents and presses the send button to send the data to the server.

[0226] Step 4:

[0227] The terminal converts the data entered by the user into JSON format.

[0228] Step 5:

[0229] The device sends an HTTP POST request to the API endpoint of the specified server.

[0230] Step 6:

[0231] The server receives an HTTP request from a client and extracts the input data from the request body.

[0232] Step 7:

[0233] The server checks the format of the received data to ensure it is valid.

[0234] Step 8:

[0235] The server performs pre-processing and inputs the data into the emotion engine.

[0236] Step 9:

[0237] The emotion engine analyzes input data and user interactions to detect the user's emotional state.

[0238] Step 10:

[0239] The server prepares the emotional state detected by the emotion engine to be sent to the generative AI model.

[0240] Step 11:

[0241] The server loads the generative AI model and performs predictions and suggestions based on the received data and emotional information.

[0242] Step 12:

[0243] The server formats the generated results and creates an API response to send back to the user.

[0244] Step 13:

[0245] The terminal receives the response from the server and notifies the user.

[0246] Step 14:

[0247] The user checks the results sent back from the server, and receives, for example, a suggestion for "AI-based battery management and automatic charging schedule adjustment."

[0248] Step 15:

[0249] The user creates a contest entry form based on the content of their proposal and participates in the contest.

[0250] Through these specific steps, the effectiveness of the generative AI model and emotion engine can be maximized, enabling users to quickly provide highly accurate and emotion-sensitive solutions.

[0251] Example 2

[0252] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0253] While systems that use generative artificial intelligence models to generate solutions for specific tasks already exist, they often fail to take into account the user's emotional state. As a result, the generated solutions may not match the user's emotions or the situation. Therefore, there is a need for a system that provides solutions that take the user's emotions into account.

[0254] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0255] In this invention, the server includes a means for analyzing the user's emotions, a means for inputting the analyzed emotion information into the generative artificial intelligence model, and a means for returning the generated results to the user, thereby enabling the generation of solutions that take the user's emotions into consideration.

[0256] A "generative artificial intelligence model" is an artificial intelligence algorithm that generates solutions or predictive outcomes based on specific input data.

[0257] A "specific task" is a specific task or problem for which a user enters data to seek a solution.

[0258] A "solution" is a recommended action, answer, or suggestion generated based on input data.

[0259] "Data" refers to information that the system processes, such as information entered by the user, numbers, text messages, etc.

[0260] An "emotion engine" is a technology or software that analyzes a user's emotional state from input data and quantifies it.

[0261] "Means for receiving" refers to the method or process by which the server obtains the data sent by the user.

[0262] "Preprocessing" refers to a series of processes that clean the data to be input into the raw artificial intelligence model, remove noise, and convert the format.

[0263] "Means for analyzing" refers to the process of detecting the user's emotions using an emotion engine and extracting that information.

[0264] "Return mechanism" refers to the method or protocol by which the server transmits the generated solution to the user.

[0265] To implement this invention, three main components are required: a server, a terminal, and a user. Furthermore, by combining an emotion engine that recognizes the user's emotions, the quality of the provided solution can be improved.

[0266] The server plays a central role in training the generative AI model, receiving and processing data sent by users to generate solutions and predictions. First, the server trains the generative AI model using a specific dataset. For this training, it is recommended to use a machine learning framework such as PyTorch or TENSORFLOW (registered trademark). The training data is cleaned to remove unnecessary noise. After training is complete, the generative AI model is ready to generate solutions for specific tasks.

[0267] When data is sent by the user, the server receives it. The received data is preprocessed using a data processing library such as Numpy or Pandas. At this time, an emotion engine (such as the Emotion API) analyzes the user's input data and detects the user's emotional state. The preprocessed data and emotional information are input into a generative AI model. This generative AI model generates a solution based on the data and emotional information. The results are formatted in JSON format or similar and sent back to the user.

[0268] The device provides an interface for the user to enter data related to a specific task. For example, this can be a dedicated application or a form in a web browser. This can be a web application built with React or Angular, or a native app for Android or iOS. After the user enters the data, the device sends the input data to the server. This is usually done via an HTTP POST request. The device is also responsible for receiving the response from the server and notifying the user.

[0269] Users interact with their devices to find solutions to specific tasks. For example, they might have an idea for a new app feature and use their device to enter details. The data is processed and the server returns the results to the user, who can then provide feedback if they are satisfied with the results.

[0270] As a concrete example, consider the case where a user participates in a new product idea contest. The user uses the device to input ideas for new smartphone features. For example, the user might input a specific requirement such as "optimizing battery consumption" as details for an "AI-based battery management function." The emotion engine analyzes the user's input data and interactions to detect their emotional state. The device then sends this data and the detected emotional information to the server.

[0271] The server receives the data, preprocesses it using Numpy and Pandas, and then inputs it into the generative AI model. The generative AI model analyzes the data and emotional information and generates a "proposal for an automatic charging schedule adjustment function in addition to a battery management function." The server then sends the results back to the device, where the user can confirm the proposal. Since the user is in a state where they are likely to be convinced by the proposal, it is expected that the results of the emotional engine will also be reflected.

[0272] Examples of prompts include:

[0273] "What are your ideas for AI-powered battery management?"

[0274] "Please give me some suggestions for battery optimization features."

[0275] "Generate battery management ideas, including automatic adjustment of charging schedules."

[0276] This maximizes the effectiveness of generative AI models and emotion engines, enabling us to quickly provide users with highly accurate and emotion-sensitive solutions.

[0277] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0278] Step 1:

[0279] The user inputs a prompt via a terminal. For example, the user inputs specific data or a question, such as "AI-based battery management function suggestions," into a smartphone application or web browser interface. This input data becomes the input for the system.

[0280] Step 2:

[0281] The device sends the input data along with the emotion engine to the server. The device (web application or smartphone app) collects the data entered by the user and analyzes the user's emotions using the Emotion API. The analyzed emotion information and the input data are sent to the server via an HTTP POST request.

[0282] Step 3:

[0283] The server receives the data and performs preprocessing. The server cleans the received data using data processing libraries such as Numpy and Pandas to remove unnecessary noise. This processing transforms the data into a format suitable for generative AI models. The input is the raw data sent by the user, and the output is the preprocessed, clean data.

[0284] Step 4:

[0285] The server analyzes the emotional information and inputs it into the generative AI model. The received emotional information is also analyzed to identify the user's emotional state. This completes the dataset to be input into the generative AI model. The input is the emotional data sent from the emotion engine, and the output is the emotional data converted into a format that can be input into the generative AI model.

[0286] Step 5:

[0287] The server runs the generative AI model and generates a solution. The server inputs the preprocessed data and emotional information into the generative AI model (for example, a model trained with PyTorch or TensorFlow). The model generates a solution based on this data. For example, a solution such as "proposing an automatic charging schedule adjustment function in addition to a battery management function" is generated. The input is the formatted data and emotional information, and the output is the generated solution.

[0288] Step 6:

[0289] The server formats the generated solution and sends it back to the device. The generated result is converted into a format that is easy for the user to understand (for example, JSON format) and sent back to the device as an HTTP response. The input is the solution output by the generative AI model, and the output is the formatted solution.

[0290] Step 7:

[0291] The terminal notifies the user of the solution and displays it. The terminal receives a response from the server and displays the solution on the user interface. The user can check the displayed solution and send feedback that reflects their feelings. The input is the solution returned from the server, and the output is the solution displayed to the user.

[0292] This process flow allows users to quickly obtain solutions that are highly accurate and considerate of emotions.

[0293] (Application example 2)

[0294] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0295] Systems using conventional generative AI models have difficulty generating solutions that take user emotions into account, resulting in lower user satisfaction. Furthermore, while there is a need to analyze a user's emotional state in real time and provide appropriate suggestions based on that analysis, current technology makes it difficult to achieve this.

[0296] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for generating a solution for a specific task using a generative AI model, means for receiving data input from a user, means for executing the generative AI model based on the received data and generating a result, means including an emotion engine for analyzing the user's emotional state, and means for returning the generated result and emotion information to the user. This makes it possible to provide high-quality solutions that take the user's emotions into consideration, which is expected to not only improve user satisfaction but also enable the provision of appropriate suggestions based on real-time analysis.

[0297] A "generative artificial intelligence model" refers to an artificial intelligence technology that generates solutions or predicted results for specific tasks based on data input by a user.

[0298] "User" refers to an entity that utilizes the system and inputs data to seek a solution to a particular task.

[0299] "Data receiving means" refers to a mechanism for the server to receive input data sent by the user.

[0300] "Emotion engine" refers to a system element for analyzing a user's emotional state and providing that emotional information.

[0301] "Preprocessing means" refers to a mechanism that performs preprocessing such as noise removal and format conversion on received data before inputting it into the generative artificial intelligence model.

[0302] "Result generation means" refers to a mechanism that runs a generative artificial intelligence model based on preprocessed data to generate solutions or predicted results.

[0303] "Return means" refers to a mechanism for returning generated solutions and prediction results to the user.

[0304] "Server" refers to the central computer system that receives input data, processes it, runs generative AI models, and generates and returns results.

[0305] "System" refers to a device or configuration that includes a set of means for providing a solution to a user's specific task using a generative artificial intelligence model.

[0306] To implement this invention, three main components are required: a server, a terminal, and a user. In addition, by combining an emotion engine that recognizes the user's emotions, the quality of the provided solution can be improved.

[0307] First, the server plays a central role in training the generative AI model, receiving and processing data sent by users to generate solutions and predictions. Specifically, the server trains the generative AI model using training data. This training data is cleaned to remove unnecessary noise. Once training is complete, the generative AI model is ready to generate solutions for specific tasks. When data is sent by users, the server receives it, preprocesses it, and inputs it into the generative AI model. At this time, the emotion engine also analyzes the user's input data to detect the user's emotional state. The generative AI model processes the data and emotional information to generate a solution for the specific task. The result is formatted and sent back to the user.

[0308] The device provides an interface for the user to input data related to a specific task. For example, this can be a dedicated application or a form on a web browser. After the user enters the data, the device sends the input data to the server. The device is also responsible for receiving responses from the server and notifying the user. For example, when using smart glasses, the device can analyze the customer's emotions in real time through the built-in camera and display and provide appropriate suggestions to the store clerk.

[0309] The user is the one seeking a solution to a specific task. They input data using a device, and once the data is processed, the server sends back the results. The user can also provide further feedback based on the results. For example, a sales associate in a physical store could wear smart glasses and receive personalized solutions in real time, while understanding the customer's emotional state through the glasses.

[0310] In this way, the server generates solutions using the generative AI model and then uses the emotion engine to reflect the user's emotional state while returning the solutions to the user, thereby providing higher quality solutions. As a result, user satisfaction is improved and appropriate suggestions can be provided in real time.

[0311] As a concrete example, a user entering a new product idea contest can come up with an idea for a new smartphone feature and input details of an "AI-based battery management function" using their device. During this input, the emotion engine analyzes the user's input data and interactions to detect their emotional state. The device then sends the data and the detected emotion information to a server, which receives the data and inputs it into a generative AI model after preprocessing. The generative AI model analyzes the data and emotion information and generates a "proposal for a battery management function plus an automatic charging schedule adjustment function." The result is sent back from the server to the device, where the user confirms the proposal. Since the user is in a state where they are likely to be convinced by the proposal, it is expected that the emotion engine's results will also be reflected in the proposal. Based on the proposal, an entry form can be created and submitted to the contest.

[0312] Examples of prompt sentences include the following:

[0313] "A new customer walks into the store. It appears the customer is looking for a specific product, but what is the best way to respond? Use the emotion engine and generative AI model to provide the next suggestion. The customer appears confused, so provide suggestions to help the store associate respond appropriately."

[0314] In this way, by combining a generative AI model with an emotion engine, it is possible to respond appropriately to customer needs and emotions, thereby improving customer satisfaction.

[0315] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0316] Step 1:

[0317] A user inputs data using a terminal (smart glasses). For example, when a customer is browsing products in a store, a camera installed in the smart glasses captures the customer's facial expressions and movements.

[0318] Input: Video data including customer facial expressions and movements

[0319] Output: Captured video data

[0320] Step 2:

[0321] The device sends the captured video data to the emotion engine, which analyzes the user's (customer's) emotional state. The emotion engine analyzes facial expressions and movements from the video data to detect the customer's emotional state.

[0322] Input: Captured video data

[0323] Output: Emotional state (e.g., happy, confused, interested, etc.)

[0324] Step 3:

[0325] The device sends the video data along with the detected emotional state to a server, which preprocesses the received data, removes noise, and converts it into a format suitable for generative AI models.

[0326] Input: Video data, emotional state

[0327] Output: Preprocessed data (e.g. cleaned data, formatted data)

[0328] Step 4:

[0329] The server inputs the preprocessed data into a generative AI model to generate solutions for specific tasks. The generative AI model analyzes the input data and emotional information to generate appropriate countermeasures and suggestions.

[0330] Input: Preprocessed data, emotional state

[0331] Output: Solutions or suggestions (e.g., specific product descriptions, service proposals, etc.)

[0332] Step 5:

[0333] The server formats the generated solutions and suggestions and generates data to send back to the user, including emotional information, in a format that is useful to the user.

[0334] Input: Generated solutions and suggestions

[0335] Output: Formatted data (e.g., suggestion message)

[0336] Step 6:

[0337] The terminal displays the formatted data received from the server and notifies the store clerk of suggestions, and specific countermeasures are displayed in real time on the smart glasses display.

[0338] Input: Formatted data

[0339] Output: Suggestions displayed on the smart glasses display

[0340] Step 7:

[0341] The user (store clerk) can respond optimally to the customer based on the suggestions displayed on the smart glasses, for example, explaining the product to a confused customer or providing additional information to an interested customer.

[0342] Input: Suggestions from smart glasses

[0343] Output: Appropriate response to the customer

[0344] This step is expected to improve customer satisfaction. By utilizing an emotion engine and generative AI model in the process of generating solutions for specific tasks, advanced support based on the user's emotions can be realized.

[0345] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0346] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0347] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0348] [Second embodiment]

[0349] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0350] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0351] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0352] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0353] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0354] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0355] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0356] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0357] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0358] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0359] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0360] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0361] Three main components are required to implement the present invention: a server, a terminal, and a user.

[0362] 1. Server

[0363] The server plays a central role in training the generative AI model, receiving and processing data to generate solutions and predictions. First, the server trains the generative AI model with a specific dataset. This dataset is cleaned to remove unwanted noise. Once training is complete, the generative AI model is ready to generate solutions for a specific task.

[0364] When data is sent by the user, the server receives it, preprocesses it, and feeds it into a generative AI model, which processes the data and generates a solution to a specific task. This result is formatted and forwarded to the user.

[0365] 2. Terminal

[0366] The device provides an interface for the user to input data related to a specific task. For example, this can be a dedicated application or a form in a web browser. After the user enters the data, the device sends the input data to the server. The device is also responsible for receiving responses from the server and notifying the user.

[0367] 3. Users

[0368] The user is the one seeking a solution to a particular task. They use a device to input data, and once that data is processed, they see the results sent back from the server. The user can then provide further feedback based on the results.

[0369] Example: New product idea contest

[0370] Users can come up with ideas for new smartphone features and use the device to input details of "AI battery management features," including specific requirements such as "optimizing battery consumption."

[0371] The device sends the data to a server, which receives the data, preprocesses it, and then inputs it into a generative AI model. The generative AI model analyzes the data and generates "proposals for battery management and automatic charging schedule adjustment."

[0372] The server sends the results back to the terminal, where the user can confirm the proposal. Based on the proposal, the user can create and submit an entry form for the contest.

[0373] The present invention maximizes the effectiveness of generative AI models and can quickly provide users with highly accurate solutions, enabling contest participants to quickly generate high-quality proposals and increase their competitiveness.

[0374] The processing flow will be explained below.

[0375] Step 1:

[0376] The user opens a dedicated application or web interface on the device.

[0377] Step 2:

[0378] Users input data related to a specific task, for example, "AI-powered battery management" as an "idea for a new smartphone feature."

[0379] Step 3:

[0380] The user checks the input contents and presses the send button to send the data to the server.

[0381] Step 4:

[0382] The terminal converts the data entered by the user into JSON format.

[0383] Step 5:

[0384] The device sends an HTTP POST request to the API endpoint of the specified server.

[0385] Step 6:

[0386] The server receives an HTTP request from a client and extracts the input data from the request body.

[0387] Step 7:

[0388] The server checks the format of the received data to ensure it is valid.

[0389] Step 8:

[0390] The server performs preprocessing and prepares the data for input into the generative AI model.

[0391] Step 9:

[0392] The server loads the generative AI model and performs predictions and suggestions based on the received data.

[0393] Step 10:

[0394] The server formats the generated results and creates an API response to send back to the user.

[0395] Step 11:

[0396] The terminal receives the response from the server and notifies the user.

[0397] Step 12:

[0398] The user checks the results sent back from the server. For example, they may be offered the option of "AI-based battery management and automatic charging schedule adjustment."

[0399] Step 13:

[0400] The user creates a contest entry form based on the content of their proposal and participates in the contest.

[0401] In this way, through the specific actions taken at each step, the effectiveness of the generative AI model can be maximized and highly accurate solutions can be quickly provided to users.

[0402] Example 1

[0403] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0404] In systems using existing generative AI models, data preprocessing, solution generation, and notification of results to users are often complex and time-consuming. For this reason, there is a demand for systems that can quickly provide highly accurate solutions. Another challenge is to streamline the entire process of data entry, submission, preprocessing, and formatting, and provide a seamless experience for users.

[0405] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0406] In this invention, the server includes means for a user to input data using a terminal, means for transmitting the input data from the terminal to the server, means for preprocessing the data received by the server, means for inputting the preprocessed data into a generative AI model to generate a solution, means for formatting the generated solution, means for transmitting the formatted solution to the terminal, and means for the terminal to notify the user of the solution. This makes it possible to quickly provide highly accurate solutions and provide a seamless experience to the user.

[0407] A "terminal" is a device through which a user inputs, transmits, and receives results.

[0408] The "server" is the central processing unit that receives data, pre-processes it, runs the generative AI model, and generates and transmits solutions.

[0409] A "user" is an end user who inputs data about a particular task and requests a solution.

[0410] "Data entry" is the act of a user providing information for a particular task through a terminal.

[0411] "Data transmission" is the process in which the terminal sends the input data to the server.

[0412] "Preprocessing" refers to the process of removing noise and standardizing the format of data received by the server.

[0413] A "generative AI model" is an algorithm that analyzes input data and generates solutions to specific tasks.

[0414] "Solution generation" is the process in which a generative AI model analyzes preprocessed data and outputs the solution desired by the user.

[0415] "Solution formatting" is the process of arranging the generated solution in a format that is easy for the user to understand.

[0416] "Sending a solution" is the act of the server transferring a formatted solution to the terminal.

[0417] "Result notification" is the process by which the terminal informs the user of the solution received from the server.

[0418] Three main components are required to implement the present invention: a server, a terminal, and a user.

[0419] server

[0420] The server plays a central role in training the generative AI model, receiving data, preprocessing, and generating solutions. Specifically, the server trains the generative AI model using a specific cleaned dataset. Once this training is complete, the generative AI model is ready to generate solutions for specific tasks. The specific functions of the server are as follows:

[0421] Data reception and preprocessing:

[0422] The server receives user data sent from the device. The received data is pre-processed to remove noise and missing values. Pre-processing includes cleaning the data and standardizing the format.

[0423] Inputs and processing for generative AI models:

[0424] The preprocessed data is then fed into a generative AI model, which analyzes the data and generates a solution for the specific task, such as a deep learning model or a natural language processing model.

[0425] Solution format:

[0426] The server formats the generated solutions in a user-friendly format, for example by converting them into easy-to-read sentences in natural language.

[0427] Send solution to device:

[0428] The formatted solution is then sent from the server to the device using encryption protocols to ensure data integrity and security.

[0429] Terminal

[0430] The terminal acts as an interface for users to input data, send data, and accept results. The specific functions of the terminal are as follows:

[0431] Data Input Interface:

[0432] It provides an interface for users to enter data related to a specific task, either through a dedicated application or through a form in a web browser.

[0433] Data transmission:

[0434] The entered data is sent to the server in the appropriate format.

[0435] Result notification:

[0436] The solution received from the server is notified to the user via a popup or email.

[0437] User

[0438] The user is the party seeking a solution to a specific task. The following are the specific operations performed by the user:

[0439] Data Entry:

[0440] A user uses the device to input data about a specific task, for example, a requirement for a new battery management feature called "optimize battery consumption."

[0441] Check the result:

[0442] Check the solution notified by the device and take further action as necessary. For example, consider whether to adopt the proposed "automatic charging schedule adjustment function."

[0443] Example: New product idea contest

[0444] Users come up with ideas for new smartphone features and use their device to input details of an "AI-based battery management feature," including specific requirements such as "optimizing battery consumption." The device then sends the data to a server. The server receives the data, performs preprocessing, and then inputs it into a generative AI model. The generative AI model analyzes the data and generates a "proposal for a battery management feature plus an automatic charging schedule adjustment feature." The server then sends the results back to the device, where the user can review the proposal. The user can then create and submit an entry form for the contest based on their proposal.

[0445] Prompt Sentence Examples

[0446] "Please enter your new ideas for smartphone battery management features. For example, please state specific requirements such as 'optimizing battery consumption' or 'automatically adjusting charging schedules.'"

[0447] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0448] Step 1:

[0449] The user enters data using the device interface. Specifically, the user accesses a form in a smartphone app or web browser and enters a specific requirement, such as "optimize battery consumption." The data entered by the user is in text format and contains detailed information about the specific task. This data becomes the input for the process.

[0450] Step 2:

[0451] The terminal checks the format of the entered data and converts it to the appropriate format. For example, it checks whether the character code is consistent and whether all required fields are filled in. Data that passes the format check is sent to the server. The input here is the data entered by the user, and the output is the format-checked data.

[0452] Step 3:

[0453] The server receives data sent from the terminal. The received data is temporarily stored in a database. At this time, the server uses a checksum to confirm that the data was received correctly to ensure data integrity. The input is the format-checked data sent from the terminal, and the output is the data stored in the database.

[0454] Step 4:

[0455] The server preprocesses the data it receives. Preprocessing includes removing noise, filling in missing values, and normalizing data. For example, it removes unnecessary spaces and line breaks and standardizes the format of text data. The input is the raw data stored in the database, and the output is the preprocessed data.

[0456] Step 5:

[0457] The server inputs the preprocessed data into a generative AI model, which uses natural language processing and deep learning to analyze the data and generate a solution such as "automatic adjustment of charging schedules." The input is the preprocessed data, and the output is the generated solution.

[0458] Step 6:

[0459] The server formats the generated solution in a user-friendly format. For example, it converts the raw data output by the generative AI model into natural language sentences that are easy for humans to understand. The input is the generated solution, and the output is the formatted solution.

[0460] Step 7:

[0461] The server sends the formatted solution to the terminal, using an encryption protocol to ensure data integrity and security. The input is the formatted solution, and the output is the encrypted data.

[0462] Step 8:

[0463] The device notifies the user of the solution received from the server. Specifically, the result is notified to the user using a pop-up notification or email. The input is the encrypted data sent from the server, and the output is the solution presented to the user.

[0464] Step 9:

[0465] The user checks the solution through the device and provides subsequent feedback if necessary, which is also sent to the server in a similar process for further analysis and use as training data.

[0466] The above steps result in a system that quickly provides highly accurate solutions and provides a seamless experience for users.

[0467] (Application example 1)

[0468] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0469] In modern content distribution services, users face difficulties in selecting the most suitable video content from the vast number of available options. However, the lack of appropriate recommendations based on viewing history and interests leads to a poor user experience. To solve this problem, a system is needed that automatically recommends the most suitable content in real time using user viewing data.

[0470] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0471] In this invention, the server includes means for generating a solution to a specific task using a generative artificial intelligence model, means for receiving data input from a user, means for executing the generative artificial intelligence model based on the received data to generate a result, means for automatically generating data and displaying it through an identification device, and means for returning the generated result to the user, thereby enabling optimal video content to be recommended in real time based on the user's viewing history and interests, improving the user experience.

[0472] A "generative artificial intelligence model" is an algorithm that is trained to generate solutions to specific tasks.

[0473] A "user" is an entity that provides data to the system and receives the results.

[0474] "Data receiving means" is a function for taking data input by the user into the system.

[0475] "Data pre-processing means" is a function that executes a process to convert received data into a format that is easy to analyze.

[0476] An "identification device" is a device for displaying information to a user, such as smart glasses.

[0477] "Means for automatically generating data" is a function that creates new data or content based on input data.

[0478] The "result generation means" is a function that inputs preprocessed data into a generative artificial intelligence model to generate an optimal solution.

[0479] The "result return means" is a communication and display function for providing the generated results to the user.

[0480] The system of the present invention consists of three main components: a server, a terminal, and a user. The server plays a central role in training the generative artificial intelligence model, receiving and processing data to generate solutions and recommendation results.

[0481] Server Operation

[0482] The server trains a generative artificial intelligence model using a specific dataset. The training dataset is cleaned and noise removed. Once training is complete, the generative AI model is ready to generate solutions for specific tasks. When data is submitted by the user, the server receives the data, preprocesses it, and inputs it into the generative AI model. The generative AI model processes the data and generates a solution for the specific task. The results are formatted and forwarded to the user.

[0483] Device behavior

[0484] The device provides an interface for the user to input data related to a specific task. For example, this can be a dedicated application or a form in a web browser. After the user inputs the data, the device sends the input data to a server. The device is also responsible for receiving responses from the server and notifying the user. The device also has the ability to display the results through an identification device such as smart glasses.

[0485] User Roles

[0486] A user is an entity seeking a solution to a particular task. They use a device to input data, which is processed and then the server sends back results. The user can then provide further feedback based on the results.

[0487] Example

[0488] For example, in the case of a personalized video recommendation application for smart glasses, users can use their smart glasses to select video content to watch. Data such as viewing history, interests, and viewing time are sent to a server via the device, and the server analyzes this data to recommend the most suitable content in real time. This allows users to seamlessly enjoy the latest video content that matches their interests.

[0489] Prompt Sentence Examples

[0490] User ID: user123

[0491] Viewing history: Movies, documentaries, news

[0492] Interests: Science fiction, history, modern technology

[0493] Current time: 2023-10-03T18:00:00Z"

[0494] Based on this, a generative AI model recommends the most suitable content to the user.

[0495] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0496] Step 1:

[0497] The user inputs viewing data through the smart glasses.

[0498] Input: User ID, viewing history, interests, current time.

[0499] How it works: Users use the smart glasses interface to input data such as their viewing history, interests, and the current time, which is then collected by the device.

[0500] Output: Collected data is sent to the terminal.

[0501] Step 2:

[0502] The terminal transmits user data to the server.

[0503] Input: User data collected from smart glasses.

[0504] How it works: The device sends collected user data (user ID, viewing history, interests, current time) to the server. This communication uses standard protocols such as HTTP requests.

[0505] Output: User data arrives at the server.

[0506] Step 3:

[0507] Preprocessing data received by the server.

[0508] Input: User data sent from the device.

[0509] How it works: The server cleanses the data it receives, removes noise, and converts it into a format that's easier to analyze, including imputing missing values ​​and normalizing the data.

[0510] Output: Preprocessed data is generated.

[0511] Step 4:

[0512] The server inputs the preprocessed data into the generated artificial intelligence model.

[0513] Input: Preprocessed data.

[0514] How it works: The server inputs the preprocessed data into the generative AI model to perform the analysis task. The generative AI model generates a solution to recommend the best video content based on the data.

[0515] Output: Best video content recommendation results.

[0516] Step 5:

[0517] The server returns the generated recommendation results to the device.

[0518] Input: Best video content recommendation results.

[0519] How it works: The server formats the generated recommendations and sends them back to the device, again using standard protocols such as HTTP requests.

[0520] Output: The recommended results arrive on your terminal.

[0521] Step 6:

[0522] The device notifies the user of the recommended results.

[0523] Input: The recommended results returned by the server.

[0524] How it works: The device notifies the user of the received recommendations and displays them on the smart glasses display, allowing the user to watch the most suitable video content in real time.

[0525] Output: The recommended results are displayed on the smart glasses display.

[0526] Step 7:

[0527] The user watches the recommended video content.

[0528] Input: Recommendation results displayed on smart glasses.

[0529] How it works: The user selects and watches recommended video content displayed on the smart glasses display. After viewing, the data is input back into the device for use in future recommendations.

[0530] Output: New viewing data is generated and used for the next recommendation.

[0531] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0532] To implement this invention, three main components are required: a server, a terminal, and a user. Furthermore, by combining an emotion engine that recognizes the user's emotions, the quality of the provided solution can be improved.

[0533] 1. Server

[0534] The server plays a central role in training the generative AI model, receiving and processing data sent by users to generate solutions and predictions. First, the generative AI model is trained using a specific dataset. The training data is cleaned to remove unnecessary noise. After training is complete, the generative AI model is ready to generate solutions for specific tasks.

[0535] When data is sent by the user, the server receives the data. The received data is preprocessed and input into the generative AI model. At this time, the emotion engine also analyzes the user's input data to detect the user's emotional state. The generative AI model processes the data and emotion information and generates a solution for the specific task. The result is formatted and sent back to the user.

[0536] 2. Terminal

[0537] The device provides an interface for the user to enter data related to a specific task. For example, this can be a dedicated application or a form in a web browser. After the user enters the data, the device sends the input data to the server. The device is also responsible for receiving responses from the server and notifying the user.

[0538] 3. Users

[0539] The user is the one seeking a solution to a particular task. They use a device to input data, which is then processed and the server sends back results, which the user can then use to provide further feedback.

[0540] Example: New product idea contest

[0541] Users can come up with ideas for new smartphone features and use their devices to input details of "AI-powered battery management features," including specific requirements such as "optimizing battery consumption." During this input, the emotion engine analyzes the user's input data and interactions to detect their emotional state.

[0542] The device sends the data and the detected emotion information to a server. The server receives the data, performs preprocessing, and then inputs it into a generative AI model. The generative AI model analyzes the data and emotion information and generates "proposals for battery management functions and automatic charging schedule adjustment functions."

[0543] The results are sent back from the server to the device, where the user can confirm the proposal. Since the user is in a state where they are likely to be convinced of the proposal, it is expected that the results of the emotion engine will also be reflected. Based on the proposal, the user can create and submit an entry form for the contest.

[0544] This maximizes the effectiveness of generative AI models and emotion engines, enabling us to quickly provide users with highly accurate and emotion-sensitive solutions.

[0545] The processing flow will be explained below.

[0546] Step 1:

[0547] The user opens a dedicated application or web interface on the device.

[0548] Step 2:

[0549] Users input data related to a specific task, for example, "AI-powered battery management" as an "idea for a new smartphone feature."

[0550] Step 3:

[0551] The user checks the input contents and presses the send button to send the data to the server.

[0552] Step 4:

[0553] The terminal converts the data entered by the user into JSON format.

[0554] Step 5:

[0555] The device sends an HTTP POST request to the API endpoint of the specified server.

[0556] Step 6:

[0557] The server receives an HTTP request from a client and extracts the input data from the request body.

[0558] Step 7:

[0559] The server checks the format of the received data to ensure it is valid.

[0560] Step 8:

[0561] The server performs pre-processing and inputs the data into the emotion engine.

[0562] Step 9:

[0563] The emotion engine analyzes input data and user interactions to detect the user's emotional state.

[0564] Step 10:

[0565] The server prepares the emotional state detected by the emotion engine to be sent to the generative AI model.

[0566] Step 11:

[0567] The server loads the generative AI model and performs predictions and suggestions based on the received data and emotional information.

[0568] Step 12:

[0569] The server formats the generated results and creates an API response to send back to the user.

[0570] Step 13:

[0571] The terminal receives the response from the server and notifies the user.

[0572] Step 14:

[0573] The user checks the results sent back from the server, and receives, for example, a suggestion for "AI-based battery management and automatic charging schedule adjustment."

[0574] Step 15:

[0575] The user creates a contest entry form based on the content of their proposal and participates in the contest.

[0576] Through these specific steps, the effectiveness of the generative AI model and emotion engine can be maximized, enabling users to quickly provide highly accurate and emotion-sensitive solutions.

[0577] Example 2

[0578] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0579] While systems that use generative artificial intelligence models to generate solutions for specific tasks already exist, they often fail to take into account the user's emotional state. As a result, the generated solutions may not match the user's emotions or the situation. Therefore, there is a need for a system that provides solutions that take the user's emotions into account.

[0580] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0581] In this invention, the server includes a means for analyzing the user's emotions, a means for inputting the analyzed emotion information into the generative artificial intelligence model, and a means for returning the generated results to the user, thereby enabling the generation of solutions that take the user's emotions into consideration.

[0582] A "generative artificial intelligence model" is an artificial intelligence algorithm that generates solutions or predictive outcomes based on specific input data.

[0583] A "specific task" is a specific task or problem for which a user enters data to seek a solution.

[0584] A "solution" is a recommended action, answer, or suggestion generated based on input data.

[0585] "Data" refers to information that the system processes, such as information entered by the user, numbers, text messages, etc.

[0586] An "emotion engine" is a technology or software that analyzes a user's emotional state from input data and quantifies it.

[0587] "Means for receiving" refers to the method or process by which the server obtains the data sent by the user.

[0588] "Preprocessing" refers to a series of processes that clean the data to be input into the raw artificial intelligence model, remove noise, and convert the format.

[0589] "Means for analyzing" refers to the process of detecting the user's emotions using an emotion engine and extracting that information.

[0590] "Return mechanism" refers to the method or protocol by which the server transmits the generated solution to the user.

[0591] To implement this invention, three main components are required: a server, a terminal, and a user. Furthermore, by combining an emotion engine that recognizes the user's emotions, the quality of the provided solution can be improved.

[0592] The server plays a central role in training the generative AI model, receiving and processing data sent by users to generate solutions and predictions. First, the server trains the generative AI model using a specific dataset. For this training, it is recommended to use a machine learning framework such as PyTorch or TensorFlow. The training data is cleaned to remove unnecessary noise. After training is complete, the generative AI model is ready to generate solutions for specific tasks.

[0593] When data is sent by the user, the server receives it. The received data is preprocessed using a data processing library such as Numpy or Pandas. At this time, an emotion engine (such as the Emotion API) analyzes the user's input data and detects the user's emotional state. The preprocessed data and emotional information are input into a generative AI model. This generative AI model generates a solution based on the data and emotional information. The results are formatted in JSON format or similar and sent back to the user.

[0594] The device provides an interface for the user to enter data related to a specific task. For example, this can be a dedicated application or a form in a web browser. It can be a web application built with React or Angular, or a native Android or iOS app. After the user enters the data, the device sends the input data to the server, usually via an HTTP POST request. The device is also responsible for receiving the response from the server and notifying the user.

[0595] Users interact with their devices to find solutions to specific tasks. For example, they might have an idea for a new app feature and use their device to enter details. The data is processed and the server returns the results to the user, who can then provide feedback if they are satisfied with the results.

[0596] As a concrete example, consider the case where a user participates in a new product idea contest. The user uses the device to input ideas for new smartphone features. For example, the user might input a specific requirement such as "optimizing battery consumption" as details for an "AI-based battery management function." The emotion engine analyzes the user's input data and interactions to detect their emotional state. The device then sends this data and the detected emotional information to the server.

[0597] The server receives the data, preprocesses it using Numpy and Pandas, and then inputs it into the generative AI model. The generative AI model analyzes the data and emotional information and generates a "proposal for an automatic charging schedule adjustment function in addition to a battery management function." The server then sends the results back to the device, where the user can confirm the proposal. Since the user is in a state where they are likely to be convinced by the proposal, it is expected that the results of the emotional engine will also be reflected.

[0598] Examples of prompts include:

[0599] "What are your ideas for AI-powered battery management?"

[0600] "Please give me some suggestions for battery optimization features."

[0601] "Generate battery management ideas, including automatic adjustment of charging schedules."

[0602] This maximizes the effectiveness of generative AI models and emotion engines, enabling us to quickly provide users with highly accurate and emotion-sensitive solutions.

[0603] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0604] Step 1:

[0605] The user inputs a prompt via a terminal. For example, the user inputs specific data or a question, such as "AI-based battery management function suggestions," into a smartphone application or web browser interface. This input data becomes the input for the system.

[0606] Step 2:

[0607] The device sends the input data along with the emotion engine to the server. The device (web application or smartphone app) collects the data entered by the user and analyzes the user's emotions using the Emotion API. The analyzed emotion information and the input data are sent to the server via an HTTP POST request.

[0608] Step 3:

[0609] The server receives the data and performs preprocessing. The server cleans the received data using data processing libraries such as Numpy and Pandas to remove unnecessary noise. This processing transforms the data into a format suitable for generative AI models. The input is the raw data sent by the user, and the output is the preprocessed, clean data.

[0610] Step 4:

[0611] The server analyzes the emotional information and inputs it into the generative AI model. The received emotional information is also analyzed to identify the user's emotional state. This completes the dataset to be input into the generative AI model. The input is the emotional data sent from the emotion engine, and the output is the emotional data converted into a format that can be input into the generative AI model.

[0612] Step 5:

[0613] The server runs the generative AI model and generates a solution. The server inputs the preprocessed data and emotional information into the generative AI model (for example, a model trained with PyTorch or TensorFlow). The model generates a solution based on this data. For example, a solution such as "proposing an automatic charging schedule adjustment function in addition to a battery management function" is generated. The input is the formatted data and emotional information, and the output is the generated solution.

[0614] Step 6:

[0615] The server formats the generated solution and sends it back to the device. The generated result is converted into a format that is easy for the user to understand (for example, JSON format) and sent back to the device as an HTTP response. The input is the solution output by the generative AI model, and the output is the formatted solution.

[0616] Step 7:

[0617] The terminal notifies the user of the solution and displays it. The terminal receives a response from the server and displays the solution on the user interface. The user can check the displayed solution and send feedback that reflects their feelings. The input is the solution returned from the server, and the output is the solution displayed to the user.

[0618] This process flow allows users to quickly obtain solutions that are highly accurate and considerate of emotions.

[0619] (Application example 2)

[0620] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0621] Systems using conventional generative AI models have difficulty generating solutions that take user emotions into account, resulting in lower user satisfaction. Furthermore, while there is a need to analyze a user's emotional state in real time and provide appropriate suggestions based on that analysis, current technology makes it difficult to achieve this.

[0622] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for generating a solution for a specific task using a generative AI model, means for receiving data input from a user, means for executing the generative AI model based on the received data and generating a result, means including an emotion engine for analyzing the user's emotional state, and means for returning the generated result and emotion information to the user. This makes it possible to provide high-quality solutions that take the user's emotions into consideration, which is expected to not only improve user satisfaction but also enable the provision of appropriate suggestions based on real-time analysis.

[0623] A "generative artificial intelligence model" refers to an artificial intelligence technology that generates solutions or predicted results for specific tasks based on data input by a user.

[0624] "User" refers to an entity that utilizes the system and inputs data to seek a solution to a particular task.

[0625] "Data receiving means" refers to a mechanism for the server to receive input data sent by the user.

[0626] "Emotion engine" refers to a system element for analyzing a user's emotional state and providing that emotional information.

[0627] "Preprocessing means" refers to a mechanism that performs preprocessing such as noise removal and format conversion on received data before inputting it into the generative artificial intelligence model.

[0628] "Result generation means" refers to a mechanism that runs a generative artificial intelligence model based on preprocessed data to generate solutions or predicted results.

[0629] "Return means" refers to a mechanism for returning generated solutions and prediction results to the user.

[0630] "Server" refers to the central computer system that receives input data, processes it, runs generative AI models, and generates and returns results.

[0631] "System" refers to a device or configuration that includes a set of means for providing a solution to a user's specific task using a generative artificial intelligence model.

[0632] To implement this invention, three main components are required: a server, a terminal, and a user. In addition, by combining an emotion engine that recognizes the user's emotions, the quality of the provided solution can be improved.

[0633] First, the server plays a central role in training the generative AI model, receiving and processing data sent by users to generate solutions and predictions. Specifically, the server trains the generative AI model using training data. This training data is cleaned to remove unnecessary noise. Once training is complete, the generative AI model is ready to generate solutions for specific tasks. When data is sent by users, the server receives it, preprocesses it, and inputs it into the generative AI model. At this time, the emotion engine also analyzes the user's input data to detect the user's emotional state. The generative AI model processes the data and emotional information to generate a solution for the specific task. The result is formatted and sent back to the user.

[0634] The device provides an interface for the user to input data related to a specific task. For example, this can be a dedicated application or a form on a web browser. After the user enters the data, the device sends the input data to the server. The device is also responsible for receiving responses from the server and notifying the user. For example, when using smart glasses, the device can analyze the customer's emotions in real time through the built-in camera and display and provide appropriate suggestions to the store clerk.

[0635] The user is the one seeking a solution to a specific task. They input data using a device, and once the data is processed, the server sends back the results. The user can also provide further feedback based on the results. For example, a sales associate in a physical store could wear smart glasses and receive personalized solutions in real time, while understanding the customer's emotional state through the glasses.

[0636] In this way, the server generates solutions using the generative AI model and then uses the emotion engine to reflect the user's emotional state while returning the solutions to the user, thereby providing higher quality solutions. As a result, user satisfaction is improved and appropriate suggestions can be provided in real time.

[0637] As a concrete example, a user entering a new product idea contest can come up with an idea for a new smartphone feature and input details of an "AI-based battery management function" using their device. During this input, the emotion engine analyzes the user's input data and interactions to detect their emotional state. The device then sends the data and the detected emotion information to a server, which receives the data and inputs it into a generative AI model after preprocessing. The generative AI model analyzes the data and emotion information and generates a "proposal for a battery management function plus an automatic charging schedule adjustment function." The result is sent back from the server to the device, where the user confirms the proposal. Since the user is in a state where they are likely to be convinced by the proposal, it is expected that the emotion engine's results will also be reflected in the proposal. Based on the proposal, an entry form can be created and submitted to the contest.

[0638] Examples of prompt sentences include the following:

[0639] "A new customer walks into the store. It appears the customer is looking for a specific product, but what is the best way to respond? Use the emotion engine and generative AI model to provide the next suggestion. The customer appears confused, so provide suggestions to help the store associate respond appropriately."

[0640] In this way, by combining a generative AI model with an emotion engine, it is possible to respond appropriately to customer needs and emotions, thereby improving customer satisfaction.

[0641] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0642] Step 1:

[0643] A user inputs data using a terminal (smart glasses). For example, when a customer is browsing products in a store, a camera installed in the smart glasses captures the customer's facial expressions and movements.

[0644] Input: Video data including customer facial expressions and movements

[0645] Output: Captured video data

[0646] Step 2:

[0647] The device sends the captured video data to the emotion engine, which analyzes the user's (customer's) emotional state. The emotion engine analyzes facial expressions and movements from the video data to detect the customer's emotional state.

[0648] Input: Captured video data

[0649] Output: Emotional state (e.g., happy, confused, interested, etc.)

[0650] Step 3:

[0651] The device sends the video data along with the detected emotional state to a server, which preprocesses the received data, removes noise, and converts it into a format suitable for generative AI models.

[0652] Input: Video data, emotional state

[0653] Output: Preprocessed data (e.g. cleaned data, formatted data)

[0654] Step 4:

[0655] The server inputs the preprocessed data into a generative AI model to generate solutions for specific tasks. The generative AI model analyzes the input data and emotional information to generate appropriate countermeasures and suggestions.

[0656] Input: Preprocessed data, emotional state

[0657] Output: Solutions or suggestions (e.g., specific product descriptions, service proposals, etc.)

[0658] Step 5:

[0659] The server formats the generated solutions and suggestions and generates data to send back to the user, including emotional information, in a format that is useful to the user.

[0660] Input: Generated solutions and suggestions

[0661] Output: Formatted data (e.g., suggestion message)

[0662] Step 6:

[0663] The terminal displays the formatted data received from the server and notifies the store clerk of suggestions, and specific countermeasures are displayed in real time on the smart glasses display.

[0664] Input: Formatted data

[0665] Output: Suggestions displayed on the smart glasses display

[0666] Step 7:

[0667] The user (store clerk) can respond optimally to the customer based on the suggestions displayed on the smart glasses, for example, explaining the product to a confused customer or providing additional information to an interested customer.

[0668] Input: Suggestions from smart glasses

[0669] Output: Appropriate response to the customer

[0670] This step is expected to improve customer satisfaction. By utilizing an emotion engine and generative AI model in the process of generating solutions for specific tasks, advanced support based on the user's emotions can be realized.

[0671] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0672] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0673] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0674] [Third embodiment]

[0675] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0676] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0677] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0678] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0679] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0680] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0681] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0682] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0683] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0684] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0685] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0686] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0687] Three main components are required to implement the present invention: a server, a terminal, and a user.

[0688] 1. Server

[0689] The server plays a central role in training the generative AI model, receiving and processing data to generate solutions and predictions. First, the server trains the generative AI model with a specific dataset. This dataset is cleaned to remove unwanted noise. Once training is complete, the generative AI model is ready to generate solutions for a specific task.

[0690] When data is sent by the user, the server receives it, preprocesses it, and feeds it into a generative AI model, which processes the data and generates a solution to a specific task. This result is formatted and forwarded to the user.

[0691] 2. Terminal

[0692] The device provides an interface for the user to input data related to a specific task. For example, this can be a dedicated application or a form in a web browser. After the user enters the data, the device sends the input data to the server. The device is also responsible for receiving responses from the server and notifying the user.

[0693] 3. Users

[0694] The user is the one seeking a solution to a particular task. They use a device to input data, and once that data is processed, they see the results sent back from the server. The user can then provide further feedback based on the results.

[0695] Example: New product idea contest

[0696] Users can come up with ideas for new smartphone features and use the device to input details of "AI battery management features," including specific requirements such as "optimizing battery consumption."

[0697] The device sends the data to a server, which receives the data, preprocesses it, and then inputs it into a generative AI model. The generative AI model analyzes the data and generates "proposals for battery management and automatic charging schedule adjustment."

[0698] The server sends the results back to the terminal, where the user can confirm the proposal. Based on the proposal, the user can create and submit an entry form for the contest.

[0699] The present invention maximizes the effectiveness of generative AI models and can quickly provide users with highly accurate solutions, enabling contest participants to quickly generate high-quality proposals and increase their competitiveness.

[0700] The processing flow will be explained below.

[0701] Step 1:

[0702] The user opens a dedicated application or web interface on the device.

[0703] Step 2:

[0704] Users input data related to a specific task, for example, "AI-powered battery management" as an "idea for a new smartphone feature."

[0705] Step 3:

[0706] The user checks the input contents and presses the send button to send the data to the server.

[0707] Step 4:

[0708] The terminal converts the data entered by the user into JSON format.

[0709] Step 5:

[0710] The device sends an HTTP POST request to the API endpoint of the specified server.

[0711] Step 6:

[0712] The server receives an HTTP request from a client and extracts the input data from the request body.

[0713] Step 7:

[0714] The server checks the format of the received data to ensure it is valid.

[0715] Step 8:

[0716] The server performs preprocessing and prepares the data for input into the generative AI model.

[0717] Step 9:

[0718] The server loads the generative AI model and performs predictions and suggestions based on the received data.

[0719] Step 10:

[0720] The server formats the generated results and creates an API response to send back to the user.

[0721] Step 11:

[0722] The terminal receives the response from the server and notifies the user.

[0723] Step 12:

[0724] The user checks the results sent back from the server. For example, they may be offered the option of "AI-based battery management and automatic charging schedule adjustment."

[0725] Step 13:

[0726] The user creates a contest entry form based on the content of their proposal and participates in the contest.

[0727] In this way, through the specific actions taken at each step, the effectiveness of the generative AI model can be maximized and highly accurate solutions can be quickly provided to users.

[0728] Example 1

[0729] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0730] In systems using existing generative AI models, data preprocessing, solution generation, and notification of results to users are often complex and time-consuming. For this reason, there is a demand for systems that can quickly provide highly accurate solutions. Another challenge is to streamline the entire process of data entry, submission, preprocessing, and formatting, and provide a seamless experience for users.

[0731] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0732] In this invention, the server includes means for a user to input data using a terminal, means for transmitting the input data from the terminal to the server, means for preprocessing the data received by the server, means for inputting the preprocessed data into a generative AI model to generate a solution, means for formatting the generated solution, means for transmitting the formatted solution to the terminal, and means for the terminal to notify the user of the solution. This makes it possible to quickly provide highly accurate solutions and provide a seamless experience to the user.

[0733] A "terminal" is a device through which a user inputs, transmits, and receives results.

[0734] The "server" is the central processing unit that receives data, pre-processes it, runs the generative AI model, and generates and transmits solutions.

[0735] A "user" is an end user who inputs data about a particular task and requests a solution.

[0736] "Data entry" is the act of a user providing information for a particular task through a terminal.

[0737] "Data transmission" is the process in which the terminal sends the input data to the server.

[0738] "Preprocessing" refers to the process of removing noise and standardizing the format of data received by the server.

[0739] A "generative AI model" is an algorithm that analyzes input data and generates solutions to specific tasks.

[0740] "Solution generation" is the process in which a generative AI model analyzes preprocessed data and outputs the solution desired by the user.

[0741] "Solution formatting" is the process of arranging the generated solution in a format that is easy for the user to understand.

[0742] "Sending a solution" is the act of the server transferring a formatted solution to the terminal.

[0743] "Result notification" is the process by which the terminal informs the user of the solution received from the server.

[0744] Three main components are required to implement the present invention: a server, a terminal, and a user.

[0745] server

[0746] The server plays a central role in training the generative AI model, receiving data, preprocessing, and generating solutions. Specifically, the server trains the generative AI model using a specific cleaned dataset. Once this training is complete, the generative AI model is ready to generate solutions for specific tasks. The specific functions of the server are as follows:

[0747] Data reception and preprocessing:

[0748] The server receives user data sent from the device. The received data is pre-processed to remove noise and missing values. Pre-processing includes cleaning the data and standardizing the format.

[0749] Inputs and processing for generative AI models:

[0750] The preprocessed data is then fed into a generative AI model, which analyzes the data and generates a solution for the specific task, such as a deep learning model or a natural language processing model.

[0751] Solution format:

[0752] The server formats the generated solutions in a user-friendly format, for example by converting them into easy-to-read sentences in natural language.

[0753] Send solution to device:

[0754] The formatted solution is then sent from the server to the device using encryption protocols to ensure data integrity and security.

[0755] Terminal

[0756] The terminal acts as an interface for users to input data, send data, and accept results. The specific functions of the terminal are as follows:

[0757] Data Input Interface:

[0758] It provides an interface for users to enter data related to a specific task, either through a dedicated application or through a form in a web browser.

[0759] Data transmission:

[0760] The entered data is sent to the server in the appropriate format.

[0761] Result notification:

[0762] The solution received from the server is notified to the user via a popup or email.

[0763] User

[0764] The user is the party seeking a solution to a specific task. The following are the specific operations performed by the user:

[0765] Data Entry:

[0766] A user uses the device to input data about a specific task, for example, a requirement for a new battery management feature called "optimize battery consumption."

[0767] Check the result:

[0768] Check the solution notified by the device and take further action as necessary. For example, consider whether to adopt the proposed "automatic charging schedule adjustment function."

[0769] Example: New product idea contest

[0770] Users come up with ideas for new smartphone features and use their device to input details of an "AI-based battery management feature," including specific requirements such as "optimizing battery consumption." The device then sends the data to a server. The server receives the data, performs preprocessing, and then inputs it into a generative AI model. The generative AI model analyzes the data and generates a "proposal for a battery management feature plus an automatic charging schedule adjustment feature." The server then sends the results back to the device, where the user can review the proposal. The user can then create and submit an entry form for the contest based on their proposal.

[0771] Prompt Sentence Examples

[0772] "Please enter your new ideas for smartphone battery management features. For example, please state specific requirements such as 'optimizing battery consumption' or 'automatically adjusting charging schedules.'"

[0773] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0774] Step 1:

[0775] The user enters data using the device interface. Specifically, the user accesses a form in a smartphone app or web browser and enters a specific requirement, such as "optimize battery consumption." The data entered by the user is in text format and contains detailed information about the specific task. This data becomes the input for the process.

[0776] Step 2:

[0777] The terminal checks the format of the entered data and converts it to the appropriate format. For example, it checks whether the character code is consistent and whether all required fields are filled in. Data that passes the format check is sent to the server. The input here is the data entered by the user, and the output is the format-checked data.

[0778] Step 3:

[0779] The server receives data sent from the terminal. The received data is temporarily stored in a database. At this time, the server uses a checksum to confirm that the data was received correctly to ensure data integrity. The input is the format-checked data sent from the terminal, and the output is the data stored in the database.

[0780] Step 4:

[0781] The server preprocesses the data it receives. Preprocessing includes removing noise, filling in missing values, and normalizing data. For example, it removes unnecessary spaces and line breaks and standardizes the format of text data. The input is the raw data stored in the database, and the output is the preprocessed data.

[0782] Step 5:

[0783] The server inputs the preprocessed data into a generative AI model, which uses natural language processing and deep learning to analyze the data and generate a solution such as "automatic adjustment of charging schedules." The input is the preprocessed data, and the output is the generated solution.

[0784] Step 6:

[0785] The server formats the generated solution in a user-friendly format. For example, it converts the raw data output by the generative AI model into natural language sentences that are easy for humans to understand. The input is the generated solution, and the output is the formatted solution.

[0786] Step 7:

[0787] The server sends the formatted solution to the terminal, using an encryption protocol to ensure data integrity and security. The input is the formatted solution, and the output is the encrypted data.

[0788] Step 8:

[0789] The device notifies the user of the solution received from the server. Specifically, the result is notified to the user using a pop-up notification or email. The input is the encrypted data sent from the server, and the output is the solution presented to the user.

[0790] Step 9:

[0791] The user checks the solution through the device and provides subsequent feedback if necessary, which is also sent to the server in a similar process for further analysis and use as training data.

[0792] The above steps result in a system that quickly provides highly accurate solutions and provides a seamless experience for users.

[0793] (Application example 1)

[0794] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0795] In modern content distribution services, users face difficulties in selecting the most suitable video content from the vast number of available options. However, the lack of appropriate recommendations based on viewing history and interests leads to a poor user experience. To solve this problem, a system is needed that automatically recommends the most suitable content in real time using user viewing data.

[0796] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0797] In this invention, the server includes means for generating a solution to a specific task using a generative artificial intelligence model, means for receiving data input from a user, means for executing the generative artificial intelligence model based on the received data to generate a result, means for automatically generating data and displaying it through an identification device, and means for returning the generated result to the user, thereby enabling optimal video content to be recommended in real time based on the user's viewing history and interests, improving the user experience.

[0798] A "generative artificial intelligence model" is an algorithm that is trained to generate solutions to specific tasks.

[0799] A "user" is an entity that provides data to the system and receives the results.

[0800] "Data receiving means" is a function for taking data input by the user into the system.

[0801] "Data pre-processing means" is a function that executes a process to convert received data into a format that is easy to analyze.

[0802] An "identification device" is a device for displaying information to a user, such as smart glasses.

[0803] "Means for automatically generating data" is a function that creates new data or content based on input data.

[0804] The "result generation means" is a function that inputs preprocessed data into a generative artificial intelligence model to generate an optimal solution.

[0805] The "result return means" is a communication and display function for providing the generated results to the user.

[0806] The system of the present invention consists of three main components: a server, a terminal, and a user. The server plays a central role in training the generative artificial intelligence model, receiving and processing data to generate solutions and recommendation results.

[0807] Server Operation

[0808] The server trains a generative artificial intelligence model using a specific dataset. The training dataset is cleaned and noise removed. Once training is complete, the generative AI model is ready to generate solutions for specific tasks. When data is submitted by the user, the server receives the data, preprocesses it, and inputs it into the generative AI model. The generative AI model processes the data and generates a solution for the specific task. The results are formatted and forwarded to the user.

[0809] Device behavior

[0810] The device provides an interface for the user to input data related to a specific task. For example, this can be a dedicated application or a form in a web browser. After the user inputs the data, the device sends the input data to a server. The device is also responsible for receiving responses from the server and notifying the user. The device also has the ability to display the results through an identification device such as smart glasses.

[0811] User Roles

[0812] A user is an entity seeking a solution to a particular task. They use a device to input data, which is processed and then the server sends back results. The user can then provide further feedback based on the results.

[0813] Example

[0814] For example, in the case of a personalized video recommendation application for smart glasses, users can use their smart glasses to select video content to watch. Data such as viewing history, interests, and viewing time are sent to a server via the device, and the server analyzes this data to recommend the most suitable content in real time. This allows users to seamlessly enjoy the latest video content that matches their interests.

[0815] Prompt Sentence Examples

[0816] User ID: user123

[0817] Viewing history: Movies, documentaries, news

[0818] Interests: Science fiction, history, modern technology

[0819] Current time: 2023-10-03T18:00:00Z"

[0820] Based on this, a generative AI model recommends the most suitable content to the user.

[0821] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0822] Step 1:

[0823] The user inputs viewing data through the smart glasses.

[0824] Input: User ID, viewing history, interests, current time.

[0825] How it works: Users use the smart glasses interface to input data such as their viewing history, interests, and the current time, which is then collected by the device.

[0826] Output: Collected data is sent to the terminal.

[0827] Step 2:

[0828] The terminal transmits user data to the server.

[0829] Input: User data collected from smart glasses.

[0830] How it works: The device sends collected user data (user ID, viewing history, interests, current time) to the server. This communication uses standard protocols such as HTTP requests.

[0831] Output: User data arrives at the server.

[0832] Step 3:

[0833] Preprocessing data received by the server.

[0834] Input: User data sent from the device.

[0835] How it works: The server cleanses the data it receives, removes noise, and converts it into a format that's easier to analyze, including imputing missing values ​​and normalizing the data.

[0836] Output: Preprocessed data is generated.

[0837] Step 4:

[0838] The server inputs the preprocessed data into the generated artificial intelligence model.

[0839] Input: Preprocessed data.

[0840] How it works: The server inputs the preprocessed data into the generative AI model to perform the analysis task. The generative AI model generates a solution to recommend the best video content based on the data.

[0841] Output: Best video content recommendation results.

[0842] Step 5:

[0843] The server returns the generated recommendation results to the device.

[0844] Input: Best video content recommendation results.

[0845] How it works: The server formats the generated recommendations and sends them back to the device, again using standard protocols such as HTTP requests.

[0846] Output: The recommended results arrive on your terminal.

[0847] Step 6:

[0848] The device notifies the user of the recommended results.

[0849] Input: The recommended results returned by the server.

[0850] How it works: The device notifies the user of the received recommendations and displays them on the smart glasses display, allowing the user to watch the most suitable video content in real time.

[0851] Output: The recommended results are displayed on the smart glasses display.

[0852] Step 7:

[0853] The user watches the recommended video content.

[0854] Input: Recommendation results displayed on smart glasses.

[0855] How it works: The user selects and watches recommended video content displayed on the smart glasses display. After viewing, the data is input back into the device for use in future recommendations.

[0856] Output: New viewing data is generated and used for the next recommendation.

[0857] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0858] To implement this invention, three main components are required: a server, a terminal, and a user. Furthermore, by combining an emotion engine that recognizes the user's emotions, the quality of the provided solution can be improved.

[0859] 1. Server

[0860] The server plays a central role in training the generative AI model, receiving and processing data sent by users to generate solutions and predictions. First, the generative AI model is trained using a specific dataset. The training data is cleaned to remove unnecessary noise. After training is complete, the generative AI model is ready to generate solutions for specific tasks.

[0861] When data is sent by the user, the server receives the data. The received data is preprocessed and input into the generative AI model. At this time, the emotion engine also analyzes the user's input data to detect the user's emotional state. The generative AI model processes the data and emotion information and generates a solution for the specific task. The result is formatted and sent back to the user.

[0862] 2. Terminal

[0863] The device provides an interface for the user to enter data related to a specific task. For example, this can be a dedicated application or a form in a web browser. After the user enters the data, the device sends the input data to the server. The device is also responsible for receiving responses from the server and notifying the user.

[0864] 3. Users

[0865] The user is the one seeking a solution to a particular task. They use a device to input data, and once that data is processed, the server sends back results that the user can use to provide further feedback.

[0866] Example: New product idea contest

[0867] Users can come up with ideas for new smartphone features and use their devices to input details of "AI-powered battery management features," including specific requirements such as "optimizing battery consumption." During this input, the emotion engine analyzes the user's input data and interactions to detect their emotional state.

[0868] The device sends the data and the detected emotion information to a server. The server receives the data, performs preprocessing, and then inputs it into a generative AI model. The generative AI model analyzes the data and emotion information and generates "proposals for battery management functions and automatic charging schedule adjustment functions."

[0869] The results are sent back from the server to the device, where the user can confirm the proposal. Since the user is in a state where they are likely to be convinced of the proposal, it is expected that the results of the emotion engine will also be reflected. Based on the proposal, the user can create and submit an entry form for the contest.

[0870] This maximizes the effectiveness of generative AI models and emotion engines, enabling us to quickly provide users with highly accurate and emotion-sensitive solutions.

[0871] The processing flow will be explained below.

[0872] Step 1:

[0873] The user opens a dedicated application or web interface on the device.

[0874] Step 2:

[0875] Users input data related to a specific task, for example, "AI-powered battery management" as an "idea for a new smartphone feature."

[0876] Step 3:

[0877] The user checks the input contents and presses the send button to send the data to the server.

[0878] Step 4:

[0879] The terminal converts the data entered by the user into JSON format.

[0880] Step 5:

[0881] The device sends an HTTP POST request to the API endpoint of the specified server.

[0882] Step 6:

[0883] The server receives an HTTP request from a client and extracts the input data from the request body.

[0884] Step 7:

[0885] The server checks the format of the received data to ensure it is valid.

[0886] Step 8:

[0887] The server performs pre-processing and inputs the data into the emotion engine.

[0888] Step 9:

[0889] The emotion engine analyzes input data and user interactions to detect the user's emotional state.

[0890] Step 10:

[0891] The server prepares the emotional state detected by the emotion engine to be sent to the generative AI model.

[0892] Step 11:

[0893] The server loads the generative AI model and performs predictions and suggestions based on the received data and emotional information.

[0894] Step 12:

[0895] The server formats the generated results and creates an API response to send back to the user.

[0896] Step 13:

[0897] The terminal receives the response from the server and notifies the user.

[0898] Step 14:

[0899] The user checks the results sent back from the server, and receives, for example, a suggestion for "AI-based battery management and automatic charging schedule adjustment."

[0900] Step 15:

[0901] The user creates a contest entry form based on the content of their proposal and participates in the contest.

[0902] Through these specific steps, the effectiveness of the generative AI model and emotion engine can be maximized, enabling users to quickly provide highly accurate and emotion-sensitive solutions.

[0903] Example 2

[0904] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0905] While systems that use generative artificial intelligence models to generate solutions for specific tasks already exist, they often fail to take into account the user's emotional state. As a result, the generated solutions may not match the user's emotions or the situation. Therefore, there is a need for a system that provides solutions that take the user's emotions into account.

[0906] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0907] In this invention, the server includes a means for analyzing the user's emotions, a means for inputting the analyzed emotion information into the generative artificial intelligence model, and a means for returning the generated results to the user, thereby enabling the generation of solutions that take the user's emotions into consideration.

[0908] A "generative artificial intelligence model" is an artificial intelligence algorithm that generates solutions or predictive outcomes based on specific input data.

[0909] A "specific task" is a specific task or problem for which a user enters data to seek a solution.

[0910] A "solution" is a recommended action, answer, or suggestion generated based on input data.

[0911] "Data" refers to information that the system processes, such as information entered by the user, numbers, text messages, etc.

[0912] An "emotion engine" is a technology or software that analyzes a user's emotional state from input data and quantifies it.

[0913] "Means for receiving" refers to the method or process by which the server obtains the data sent by the user.

[0914] "Preprocessing" refers to a series of processes that clean the data to be input into the raw artificial intelligence model, remove noise, and convert the format.

[0915] "Means for analyzing" refers to the process of detecting the user's emotions using an emotion engine and extracting that information.

[0916] "Return mechanism" refers to the method or protocol by which the server transmits the generated solution to the user.

[0917] To implement this invention, three main components are required: a server, a terminal, and a user. Furthermore, by combining an emotion engine that recognizes the user's emotions, the quality of the provided solution can be improved.

[0918] The server plays a central role in training the generative AI model, receiving and processing data sent by users to generate solutions and predictions. First, the server trains the generative AI model using a specific dataset. For this training, it is recommended to use a machine learning framework such as PyTorch or TensorFlow. The training data is cleaned to remove unnecessary noise. After training is complete, the generative AI model is ready to generate solutions for specific tasks.

[0919] When data is sent by the user, the server receives it. The received data is preprocessed using a data processing library such as Numpy or Pandas. At this time, an emotion engine (such as the Emotion API) analyzes the user's input data and detects the user's emotional state. The preprocessed data and emotional information are input into a generative AI model. This generative AI model generates a solution based on the data and emotional information. The results are formatted in JSON format or similar and sent back to the user.

[0920] The device provides an interface for the user to enter data related to a specific task. For example, this can be a dedicated application or a form in a web browser. It can be a web application built with React or Angular, or a native Android or iOS app. After the user enters the data, the device sends the input data to the server, usually via an HTTP POST request. The device is also responsible for receiving the response from the server and notifying the user.

[0921] Users interact with their devices to find solutions to specific tasks. For example, they might have an idea for a new app feature and use their device to enter details. The data is processed and the server returns the results to the user, who can then provide feedback if they are satisfied with the results.

[0922] As a concrete example, consider the case where a user participates in a new product idea contest. The user uses the device to input ideas for new smartphone features. For example, the user might input a specific requirement such as "optimizing battery consumption" as details for an "AI-based battery management function." The emotion engine analyzes the user's input data and interactions to detect their emotional state. The device then sends this data and the detected emotional information to the server.

[0923] The server receives the data, preprocesses it using Numpy and Pandas, and then inputs it into the generative AI model. The generative AI model analyzes the data and emotional information and generates a "proposal for an automatic charging schedule adjustment function in addition to a battery management function." The server then sends the results back to the device, where the user can confirm the proposal. Since the user is in a state where they are likely to be convinced by the proposal, it is expected that the results of the emotional engine will also be reflected.

[0924] Examples of prompts include:

[0925] "What are your ideas for AI-powered battery management?"

[0926] "Please give me some suggestions for battery optimization features."

[0927] "Generate battery management ideas, including automatic adjustment of charging schedules."

[0928] This maximizes the effectiveness of generative AI models and emotion engines, enabling us to quickly provide users with highly accurate and emotion-sensitive solutions.

[0929] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0930] Step 1:

[0931] The user inputs a prompt via a terminal. For example, the user inputs specific data or a question, such as "AI-based battery management function suggestions," into a smartphone application or web browser interface. This input data becomes the input for the system.

[0932] Step 2:

[0933] The device sends the input data along with the emotion engine to the server. The device (web application or smartphone app) collects the data entered by the user and analyzes the user's emotions using the Emotion API. The analyzed emotion information and the input data are sent to the server via an HTTP POST request.

[0934] Step 3:

[0935] The server receives the data and performs preprocessing. The server cleans the received data using data processing libraries such as Numpy and Pandas to remove unnecessary noise. This processing transforms the data into a format suitable for generative AI models. The input is the raw data sent by the user, and the output is the preprocessed, clean data.

[0936] Step 4:

[0937] The server analyzes the emotional information and inputs it into the generative AI model. The received emotional information is also analyzed to identify the user's emotional state. This completes the dataset to be input into the generative AI model. The input is the emotional data sent from the emotion engine, and the output is the emotional data converted into a format that can be input into the generative AI model.

[0938] Step 5:

[0939] The server runs the generative AI model and generates a solution. The server inputs the preprocessed data and emotional information into the generative AI model (for example, a model trained with PyTorch or TensorFlow). The model generates a solution based on this data. For example, a solution such as "proposing an automatic charging schedule adjustment function in addition to a battery management function" is generated. The input is the formatted data and emotional information, and the output is the generated solution.

[0940] Step 6:

[0941] The server formats the generated solution and sends it back to the device. The generated result is converted into a format that is easy for the user to understand (for example, JSON format) and sent back to the device as an HTTP response. The input is the solution output by the generative AI model, and the output is the formatted solution.

[0942] Step 7:

[0943] The terminal notifies the user of the solution and displays it. The terminal receives a response from the server and displays the solution on the user interface. The user can check the displayed solution and send feedback that reflects their feelings. The input is the solution returned from the server, and the output is the solution displayed to the user.

[0944] This process flow allows users to quickly obtain solutions that are highly accurate and considerate of emotions.

[0945] (Application example 2)

[0946] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0947] Systems using conventional generative AI models have difficulty generating solutions that take user emotions into account, resulting in lower user satisfaction. Furthermore, while there is a need to analyze a user's emotional state in real time and provide appropriate suggestions based on that analysis, current technology makes it difficult to achieve this.

[0948] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for generating a solution for a specific task using a generative AI model, means for receiving data input from a user, means for executing the generative AI model based on the received data and generating a result, means including an emotion engine for analyzing the user's emotional state, and means for returning the generated result and emotion information to the user. This makes it possible to provide high-quality solutions that take the user's emotions into consideration, which is expected to not only improve user satisfaction but also enable the provision of appropriate suggestions based on real-time analysis.

[0949] A "generative artificial intelligence model" refers to an artificial intelligence technology that generates solutions or predicted results for specific tasks based on data input by a user.

[0950] "User" refers to an entity that utilizes the system and inputs data to seek a solution to a particular task.

[0951] "Data receiving means" refers to a mechanism for the server to receive input data sent by the user.

[0952] "Emotion engine" refers to a system element for analyzing a user's emotional state and providing that emotional information.

[0953] "Preprocessing means" refers to a mechanism that performs preprocessing such as noise removal and format conversion on received data before inputting it into the generative artificial intelligence model.

[0954] "Result generation means" refers to a mechanism that runs a generative artificial intelligence model based on preprocessed data to generate solutions or predicted results.

[0955] "Return means" refers to a mechanism for returning generated solutions and prediction results to the user.

[0956] "Server" refers to the central computer system that receives input data, processes it, runs generative AI models, and generates and returns results.

[0957] "System" refers to a device or configuration that includes a set of means for providing a solution to a user's specific task using a generative artificial intelligence model.

[0958] To implement this invention, three main components are required: a server, a terminal, and a user. In addition, by combining an emotion engine that recognizes the user's emotions, the quality of the provided solution can be improved.

[0959] First, the server plays a central role in training the generative AI model, receiving and processing data sent by users to generate solutions and predictions. Specifically, the server trains the generative AI model using training data. This training data is cleaned to remove unnecessary noise. Once training is complete, the generative AI model is ready to generate solutions for specific tasks. When data is sent by users, the server receives it, preprocesses it, and inputs it into the generative AI model. At this time, the emotion engine also analyzes the user's input data to detect the user's emotional state. The generative AI model processes the data and emotional information to generate a solution for the specific task. The result is formatted and sent back to the user.

[0960] The device provides an interface for the user to input data related to a specific task. For example, this can be a dedicated application or a form on a web browser. After the user enters the data, the device sends the input data to the server. The device is also responsible for receiving responses from the server and notifying the user. For example, when using smart glasses, the device can analyze the customer's emotions in real time through the built-in camera and display and provide appropriate suggestions to the store clerk.

[0961] The user is the one seeking a solution to a specific task. They input data using a device, and once the data is processed, the server sends back the results. The user can also provide further feedback based on the results. For example, a sales associate in a physical store could wear smart glasses and receive personalized solutions in real time, while understanding the customer's emotional state through the glasses.

[0962] In this way, the server generates solutions using the generative AI model and then uses the emotion engine to reflect the user's emotional state while returning the solutions to the user, thereby providing higher quality solutions. As a result, user satisfaction is improved and appropriate suggestions can be provided in real time.

[0963] As a concrete example, a user entering a new product idea contest can come up with an idea for a new smartphone feature and input details of an "AI-based battery management function" using their device. During this input, the emotion engine analyzes the user's input data and interactions to detect their emotional state. The device then sends the data and the detected emotion information to a server, which receives the data and inputs it into a generative AI model after preprocessing. The generative AI model analyzes the data and emotion information and generates a "proposal for a battery management function plus an automatic charging schedule adjustment function." The result is sent back from the server to the device, where the user confirms the proposal. Since the user is in a state where they are likely to be convinced by the proposal, it is expected that the emotion engine's results will also be reflected in the proposal. Based on the proposal, an entry form can be created and submitted to the contest.

[0964] Examples of prompt sentences include the following:

[0965] "A new customer walks into the store. It appears the customer is looking for a specific product, but what is the best way to respond? Use the emotion engine and generative AI model to provide the next suggestion. The customer appears confused, so provide suggestions to help the store associate respond appropriately."

[0966] In this way, by combining a generative AI model with an emotion engine, it is possible to respond appropriately to customer needs and emotions, thereby improving customer satisfaction.

[0967] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0968] Step 1:

[0969] A user inputs data using a terminal (smart glasses). For example, when a customer is browsing products in a store, a camera installed in the smart glasses captures the customer's facial expressions and movements.

[0970] Input: Video data including customer facial expressions and movements

[0971] Output: Captured video data

[0972] Step 2:

[0973] The device sends the captured video data to the emotion engine, which analyzes the user's (customer's) emotional state. The emotion engine analyzes facial expressions and movements from the video data to detect the customer's emotional state.

[0974] Input: Captured video data

[0975] Output: Emotional state (e.g., happy, confused, interested, etc.)

[0976] Step 3:

[0977] The device sends the video data along with the detected emotional state to a server, which preprocesses the received data, removes noise, and converts it into a format suitable for generative AI models.

[0978] Input: Video data, emotional state

[0979] Output: Preprocessed data (e.g. cleaned data, formatted data)

[0980] Step 4:

[0981] The server inputs the preprocessed data into a generative AI model to generate solutions for specific tasks. The generative AI model analyzes the input data and emotional information to generate appropriate countermeasures and suggestions.

[0982] Input: Preprocessed data, emotional state

[0983] Output: Solutions or suggestions (e.g., specific product descriptions, service proposals, etc.)

[0984] Step 5:

[0985] The server formats the generated solutions and suggestions and generates data to send back to the user, including emotional information, in a format that is useful to the user.

[0986] Input: Generated solutions and suggestions

[0987] Output: Formatted data (e.g., suggestion message)

[0988] Step 6:

[0989] The terminal displays the formatted data received from the server and notifies the store clerk of suggestions, and specific countermeasures are displayed in real time on the smart glasses display.

[0990] Input: Formatted data

[0991] Output: Suggestions displayed on the smart glasses display

[0992] Step 7:

[0993] The user (store clerk) can respond optimally to the customer based on the suggestions displayed on the smart glasses, for example, explaining the product to a confused customer or providing additional information to an interested customer.

[0994] Input: Suggestions from smart glasses

[0995] Output: Appropriate response to the customer

[0996] This step is expected to improve customer satisfaction. By utilizing an emotion engine and generative AI model in the process of generating solutions for specific tasks, advanced support based on the user's emotions can be realized.

[0997] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0998] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0999] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1000] [Fourth embodiment]

[1001] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1002] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1003] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1004] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1005] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1006] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1007] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1008] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1009] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1010] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1011] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1012] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1013] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1014] Three main components are required to implement the present invention: a server, a terminal, and a user.

[1015] 1. Server

[1016] The server plays a central role in training the generative AI model, receiving and processing data to generate solutions and predictions. First, the server trains the generative AI model with a specific dataset. This dataset is cleaned to remove unwanted noise. Once training is complete, the generative AI model is ready to generate solutions for a specific task.

[1017] When data is sent by the user, the server receives it, preprocesses it, and feeds it into a generative AI model, which processes the data and generates a solution to a specific task. This result is formatted and forwarded to the user.

[1018] 2. Terminal

[1019] The device provides an interface for the user to input data related to a specific task. For example, this can be a dedicated application or a form in a web browser. After the user enters the data, the device sends the input data to the server. The device is also responsible for receiving responses from the server and notifying the user.

[1020] 3. Users

[1021] The user is the one seeking a solution to a particular task. They use a device to input data, and once that data is processed, they see the results sent back from the server. The user can then provide further feedback based on the results.

[1022] Example: New product idea contest

[1023] Users can come up with ideas for new smartphone features and use the device to input details of "AI battery management features," including specific requirements such as "optimizing battery consumption."

[1024] The device sends the data to a server, which receives the data, preprocesses it, and then inputs it into a generative AI model. The generative AI model analyzes the data and generates "proposals for battery management and automatic charging schedule adjustment."

[1025] The server sends the results back to the terminal, where the user can confirm the proposal. Based on the proposal, the user can create and submit an entry form for the contest.

[1026] The present invention maximizes the effectiveness of generative AI models and can quickly provide users with highly accurate solutions, enabling contest participants to quickly generate high-quality proposals and increase their competitiveness.

[1027] The processing flow will be explained below.

[1028] Step 1:

[1029] The user opens a dedicated application or web interface on the device.

[1030] Step 2:

[1031] Users input data related to a specific task, for example, "AI-powered battery management" as an "idea for a new smartphone feature."

[1032] Step 3:

[1033] The user checks the input contents and presses the send button to send the data to the server.

[1034] Step 4:

[1035] The terminal converts the data entered by the user into JSON format.

[1036] Step 5:

[1037] The device sends an HTTP POST request to the API endpoint of the specified server.

[1038] Step 6:

[1039] The server receives an HTTP request from a client and extracts the input data from the request body.

[1040] Step 7:

[1041] The server checks the format of the received data to ensure it is valid.

[1042] Step 8:

[1043] The server performs preprocessing and prepares the data for input into the generative AI model.

[1044] Step 9:

[1045] The server loads the generative AI model and performs predictions and suggestions based on the received data.

[1046] Step 10:

[1047] The server formats the generated results and creates an API response to send back to the user.

[1048] Step 11:

[1049] The terminal receives the response from the server and notifies the user.

[1050] Step 12:

[1051] The user checks the results sent back from the server. For example, they may be offered the option of "AI-based battery management and automatic charging schedule adjustment."

[1052] Step 13:

[1053] The user creates a contest entry form based on the content of their proposal and participates in the contest.

[1054] In this way, through the specific actions taken at each step, the effectiveness of the generative AI model can be maximized and highly accurate solutions can be quickly provided to users.

[1055] Example 1

[1056] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1057] In systems using existing generative AI models, data preprocessing, solution generation, and notification of results to users are often complex and time-consuming. For this reason, there is a demand for systems that can quickly provide highly accurate solutions. Another challenge is to streamline the entire process of data entry, submission, preprocessing, and formatting, and provide a seamless experience for users.

[1058] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1059] In this invention, the server includes means for a user to input data using a terminal, means for transmitting the input data from the terminal to the server, means for preprocessing the data received by the server, means for inputting the preprocessed data into a generative AI model to generate a solution, means for formatting the generated solution, means for transmitting the formatted solution to the terminal, and means for the terminal to notify the user of the solution. This makes it possible to quickly provide highly accurate solutions and provide a seamless experience to the user.

[1060] A "terminal" is a device through which a user inputs, transmits, and receives results.

[1061] The "server" is the central processing unit that receives data, pre-processes it, runs the generative AI model, and generates and transmits solutions.

[1062] A "user" is an end user who inputs data about a particular task and requests a solution.

[1063] "Data entry" is the act of a user providing information for a particular task through a terminal.

[1064] "Data transmission" is the process in which the terminal sends the input data to the server.

[1065] "Preprocessing" refers to the process of removing noise and standardizing the format of data received by the server.

[1066] A "generative AI model" is an algorithm that analyzes input data and generates solutions to specific tasks.

[1067] "Solution generation" is the process in which a generative AI model analyzes preprocessed data and outputs the solution desired by the user.

[1068] "Solution formatting" is the process of arranging the generated solution in a format that is easy for the user to understand.

[1069] "Sending a solution" is the act of the server transferring a formatted solution to the terminal.

[1070] "Result notification" is the process by which the terminal informs the user of the solution received from the server.

[1071] Three main components are required to implement the present invention: a server, a terminal, and a user.

[1072] server

[1073] The server plays a central role in training the generative AI model, receiving data, preprocessing, and generating solutions. Specifically, the server trains the generative AI model using a specific cleaned dataset. Once this training is complete, the generative AI model is ready to generate solutions for specific tasks. The specific functions of the server are as follows:

[1074] Data reception and preprocessing:

[1075] The server receives user data sent from the device. The received data is pre-processed to remove noise and missing values. Pre-processing includes cleaning the data and standardizing the format.

[1076] Inputs and processing for generative AI models:

[1077] The preprocessed data is then fed into a generative AI model, which analyzes the data and generates a solution for the specific task, such as a deep learning model or a natural language processing model.

[1078] Solution format:

[1079] The server formats the generated solutions in a user-friendly format, for example by converting them into easy-to-read sentences in natural language.

[1080] Send solution to device:

[1081] The formatted solution is then sent from the server to the device using encryption protocols to ensure data integrity and security.

[1082] Terminal

[1083] The terminal acts as an interface for users to input data, send data, and accept results. The specific functions of the terminal are as follows:

[1084] Data Input Interface:

[1085] It provides an interface for users to enter data related to a specific task, either through a dedicated application or through a form in a web browser.

[1086] Data transmission:

[1087] The entered data is sent to the server in the appropriate format.

[1088] Result notification:

[1089] The solution received from the server is notified to the user via a popup or email.

[1090] User

[1091] The user is the party seeking a solution to a specific task. The following are the specific operations performed by the user:

[1092] Data Entry:

[1093] A user uses the device to input data about a specific task, for example, a requirement for a new battery management feature called "optimize battery consumption."

[1094] Check the result:

[1095] Check the solution notified by the device and take further action as necessary. For example, consider whether to adopt the proposed "automatic charging schedule adjustment function."

[1096] Example: New product idea contest

[1097] Users come up with ideas for new smartphone features and use their device to input details of an "AI-based battery management feature," including specific requirements such as "optimizing battery consumption." The device then sends the data to a server. The server receives the data, performs preprocessing, and then inputs it into a generative AI model. The generative AI model analyzes the data and generates a "proposal for a battery management feature plus an automatic charging schedule adjustment feature." The server then sends the results back to the device, where the user can review the proposal. The user can then create and submit an entry form for the contest based on their proposal.

[1098] Prompt Sentence Examples

[1099] "Please enter your new ideas for smartphone battery management features. For example, please state specific requirements such as 'optimizing battery consumption' or 'automatically adjusting charging schedules.'"

[1100] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1101] Step 1:

[1102] The user enters data using the device interface. Specifically, the user accesses a form in a smartphone app or web browser and enters a specific requirement, such as "optimize battery consumption." The data entered by the user is in text format and contains detailed information about the specific task. This data becomes the input for the process.

[1103] Step 2:

[1104] The terminal checks the format of the entered data and converts it to the appropriate format. For example, it checks whether the character code is consistent and whether all required fields are filled in. Data that passes the format check is sent to the server. The input here is the data entered by the user, and the output is the format-checked data.

[1105] Step 3:

[1106] The server receives data sent from the terminal. The received data is temporarily stored in a database. At this time, the server uses a checksum to confirm that the data was received correctly to ensure data integrity. The input is the format-checked data sent from the terminal, and the output is the data stored in the database.

[1107] Step 4:

[1108] The server preprocesses the data it receives. Preprocessing includes removing noise, filling in missing values, and normalizing data. For example, it removes unnecessary spaces and line breaks and standardizes the format of text data. The input is the raw data stored in the database, and the output is the preprocessed data.

[1109] Step 5:

[1110] The server inputs the preprocessed data into a generative AI model, which uses natural language processing and deep learning to analyze the data and generate a solution such as "automatic adjustment of charging schedules." The input is the preprocessed data, and the output is the generated solution.

[1111] Step 6:

[1112] The server formats the generated solution in a user-friendly format. For example, it converts the raw data output by the generative AI model into natural language sentences that are easy for humans to understand. The input is the generated solution, and the output is the formatted solution.

[1113] Step 7:

[1114] The server sends the formatted solution to the terminal, using an encryption protocol to ensure data integrity and security. The input is the formatted solution, and the output is the encrypted data.

[1115] Step 8:

[1116] The device notifies the user of the solution received from the server. Specifically, the result is notified to the user using a pop-up notification or email. The input is the encrypted data sent from the server, and the output is the solution presented to the user.

[1117] Step 9:

[1118] The user checks the solution through the device and provides subsequent feedback if necessary, which is also sent to the server in a similar process for further analysis and use as training data.

[1119] The above steps result in a system that quickly provides highly accurate solutions and provides a seamless experience for users.

[1120] (Application example 1)

[1121] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1122] In modern content distribution services, users face difficulties in selecting the most suitable video content from the vast number of available options. However, the lack of appropriate recommendations based on viewing history and interests leads to a poor user experience. To solve this problem, a system is needed that automatically recommends the most suitable content in real time using user viewing data.

[1123] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1124] In this invention, the server includes means for generating a solution to a specific task using a generative artificial intelligence model, means for receiving data input from a user, means for executing the generative artificial intelligence model based on the received data to generate a result, means for automatically generating data and displaying it through an identification device, and means for returning the generated result to the user, thereby enabling optimal video content to be recommended in real time based on the user's viewing history and interests, improving the user experience.

[1125] A "generative artificial intelligence model" is an algorithm that is trained to generate solutions to specific tasks.

[1126] A "user" is an entity that provides data to the system and receives the results.

[1127] "Data receiving means" is a function for taking data input by the user into the system.

[1128] "Data pre-processing means" is a function that executes a process to convert received data into a format that is easy to analyze.

[1129] An "identification device" is a device for displaying information to a user, such as smart glasses.

[1130] "Means for automatically generating data" is a function that creates new data or content based on input data.

[1131] The "result generation means" is a function that inputs preprocessed data into a generative artificial intelligence model to generate an optimal solution.

[1132] The "result return means" is a communication and display function for providing the generated results to the user.

[1133] The system of the present invention consists of three main components: a server, a terminal, and a user. The server plays a central role in training the generative artificial intelligence model, receiving and processing data to generate solutions and recommendation results.

[1134] Server Operation

[1135] The server trains a generative artificial intelligence model using a specific dataset. The training dataset is cleaned and noise removed. Once training is complete, the generative AI model is ready to generate solutions for specific tasks. When data is submitted by the user, the server receives the data, preprocesses it, and inputs it into the generative AI model. The generative AI model processes the data and generates a solution for the specific task. The results are formatted and forwarded to the user.

[1136] Device behavior

[1137] The device provides an interface for the user to input data related to a specific task. For example, this can be a dedicated application or a form in a web browser. After the user inputs the data, the device sends the input data to a server. The device is also responsible for receiving responses from the server and notifying the user. The device also has the ability to display the results through an identification device such as smart glasses.

[1138] User Roles

[1139] A user is an entity seeking a solution to a particular task. They use a device to input data, which is processed and then the server sends back results. The user can then provide further feedback based on the results.

[1140] Example

[1141] For example, in the case of a personalized video recommendation application for smart glasses, users can use their smart glasses to select video content to watch. Data such as viewing history, interests, and viewing time are sent to a server via the device, and the server analyzes this data to recommend the most suitable content in real time. This allows users to seamlessly enjoy the latest video content that matches their interests.

[1142] Prompt Sentence Examples

[1143] User ID: user123

[1144] Viewing history: Movies, documentaries, news

[1145] Interests: Science fiction, history, modern technology

[1146] Current time: 2023-10-03T18:00:00Z"

[1147] Based on this, a generative AI model recommends the most suitable content to the user.

[1148] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1149] Step 1:

[1150] The user inputs viewing data through the smart glasses.

[1151] Input: User ID, viewing history, interests, current time.

[1152] How it works: Users use the smart glasses interface to input data such as their viewing history, interests, and the current time, which is then collected by the device.

[1153] Output: Collected data is sent to the terminal.

[1154] Step 2:

[1155] The terminal transmits user data to the server.

[1156] Input: User data collected from smart glasses.

[1157] How it works: The device sends collected user data (user ID, viewing history, interests, current time) to the server. This communication uses standard protocols such as HTTP requests.

[1158] Output: User data arrives at the server.

[1159] Step 3:

[1160] Preprocessing data received by the server.

[1161] Input: User data sent from the device.

[1162] How it works: The server cleanses the data it receives, removes noise, and converts it into a format that's easier to analyze, including imputing missing values ​​and normalizing the data.

[1163] Output: Preprocessed data is generated.

[1164] Step 4:

[1165] The server inputs the preprocessed data into the generated artificial intelligence model.

[1166] Input: Preprocessed data.

[1167] How it works: The server inputs the preprocessed data into the generative AI model to perform the analysis task. The generative AI model generates a solution to recommend the best video content based on the data.

[1168] Output: Best video content recommendation results.

[1169] Step 5:

[1170] The server returns the generated recommendation results to the device.

[1171] Input: Best video content recommendation results.

[1172] How it works: The server formats the generated recommendations and sends them back to the device, again using standard protocols such as HTTP requests.

[1173] Output: The recommended results arrive on your terminal.

[1174] Step 6:

[1175] The device notifies the user of the recommended results.

[1176] Input: The recommended results returned by the server.

[1177] How it works: The device notifies the user of the received recommendations and displays them on the smart glasses display, allowing the user to watch the most suitable video content in real time.

[1178] Output: The recommended results are displayed on the smart glasses display.

[1179] Step 7:

[1180] The user watches the recommended video content.

[1181] Input: Recommendation results displayed on smart glasses.

[1182] How it works: The user selects and watches recommended video content displayed on the smart glasses display. After viewing, the data is input back into the device for use in future recommendations.

[1183] Output: New viewing data is generated and used for the next recommendation.

[1184] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1185] To implement this invention, three main components are required: a server, a terminal, and a user. Furthermore, by combining an emotion engine that recognizes the user's emotions, the quality of the provided solution can be improved.

[1186] 1. Server

[1187] The server plays a central role in training the generative AI model, receiving and processing data sent by users to generate solutions and predictions. First, the generative AI model is trained using a specific dataset. The training data is cleaned to remove unnecessary noise. After training is complete, the generative AI model is ready to generate solutions for specific tasks.

[1188] When data is sent by the user, the server receives the data. The received data is preprocessed and input into the generative AI model. At this time, the emotion engine also analyzes the user's input data to detect the user's emotional state. The generative AI model processes the data and emotion information and generates a solution for the specific task. The result is formatted and sent back to the user.

[1189] 2. Terminal

[1190] The device provides an interface for the user to enter data related to a specific task. For example, this can be a dedicated application or a form in a web browser. After the user enters the data, the device sends the input data to the server. The device is also responsible for receiving responses from the server and notifying the user.

[1191] 3. Users

[1192] The user is the one seeking a solution to a particular task. They use a device to input data, which is then processed and the server sends back results, which the user can then use to provide further feedback.

[1193] Example: New product idea contest

[1194] Users can come up with ideas for new smartphone features and use their devices to input details of "AI-powered battery management features," including specific requirements such as "optimizing battery consumption." During this input, the emotion engine analyzes the user's input data and interactions to detect their emotional state.

[1195] The device sends the data and the detected emotion information to a server. The server receives the data, performs preprocessing, and then inputs it into a generative AI model. The generative AI model analyzes the data and emotion information and generates "proposals for battery management functions and automatic charging schedule adjustment functions."

[1196] The results are sent back from the server to the device, where the user can confirm the proposal. Since the user is in a state where they are likely to be convinced of the proposal, it is expected that the results of the emotion engine will also be reflected. Based on the proposal, the user can create and submit an entry form for the contest.

[1197] This maximizes the effectiveness of generative AI models and emotion engines, enabling us to quickly provide users with highly accurate and emotion-sensitive solutions.

[1198] The processing flow will be explained below.

[1199] Step 1:

[1200] The user opens a dedicated application or web interface on the device.

[1201] Step 2:

[1202] Users input data related to a specific task, for example, "AI-powered battery management" as an "idea for a new smartphone feature."

[1203] Step 3:

[1204] The user checks the input contents and presses the send button to send the data to the server.

[1205] Step 4:

[1206] The terminal converts the data entered by the user into JSON format.

[1207] Step 5:

[1208] The device sends an HTTP POST request to the API endpoint of the specified server.

[1209] Step 6:

[1210] The server receives an HTTP request from a client and extracts the input data from the request body.

[1211] Step 7:

[1212] The server checks the format of the received data to ensure it is valid.

[1213] Step 8:

[1214] The server performs pre-processing and inputs the data into the emotion engine.

[1215] Step 9:

[1216] The emotion engine analyzes input data and user interactions to detect the user's emotional state.

[1217] Step 10:

[1218] The server prepares the emotional state detected by the emotion engine to be sent to the generative AI model.

[1219] Step 11:

[1220] The server loads the generative AI model and performs predictions and suggestions based on the received data and emotional information.

[1221] Step 12:

[1222] The server formats the generated results and creates an API response to send back to the user.

[1223] Step 13:

[1224] The terminal receives the response from the server and notifies the user.

[1225] Step 14:

[1226] The user checks the results sent back from the server, and receives, for example, a suggestion for "AI-based battery management and automatic charging schedule adjustment."

[1227] Step 15:

[1228] The user creates a contest entry form based on the content of their proposal and participates in the contest.

[1229] Through these specific steps, the effectiveness of the generative AI model and emotion engine can be maximized, enabling users to quickly provide highly accurate and emotion-sensitive solutions.

[1230] Example 2

[1231] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1232] While systems that use generative artificial intelligence models to generate solutions for specific tasks already exist, they often fail to take into account the user's emotional state. As a result, the generated solutions may not match the user's emotions or the situation. Therefore, there is a need for a system that provides solutions that take the user's emotions into account.

[1233] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1234] In this invention, the server includes a means for analyzing the user's emotions, a means for inputting the analyzed emotion information into the generative artificial intelligence model, and a means for returning the generated results to the user, thereby enabling the generation of solutions that take the user's emotions into consideration.

[1235] A "generative artificial intelligence model" is an artificial intelligence algorithm that generates solutions or predictive outcomes based on specific input data.

[1236] A "specific task" is a specific task or problem for which a user enters data to seek a solution.

[1237] A "solution" is a recommended action, answer, or suggestion generated based on input data.

[1238] "Data" refers to information that the system processes, such as information entered by the user, numbers, text messages, etc.

[1239] An "emotion engine" is a technology or software that analyzes a user's emotional state from input data and quantifies it.

[1240] "Means for receiving" refers to the method or process by which the server obtains the data sent by the user.

[1241] "Preprocessing" refers to a series of processes that clean the data to be input into the raw artificial intelligence model, remove noise, and convert the format.

[1242] "Means for analyzing" refers to the process of detecting the user's emotions using an emotion engine and extracting that information.

[1243] "Return mechanism" refers to the method or protocol by which the server transmits the generated solution to the user.

[1244] To implement this invention, three main components are required: a server, a terminal, and a user. Furthermore, by combining an emotion engine that recognizes the user's emotions, the quality of the provided solution can be improved.

[1245] The server plays a central role in training the generative AI model, receiving and processing data sent by users to generate solutions and predictions. First, the server trains the generative AI model using a specific dataset. For this training, it is recommended to use a machine learning framework such as PyTorch or TensorFlow. The training data is cleaned to remove unnecessary noise. After training is complete, the generative AI model is ready to generate solutions for specific tasks.

[1246] When data is sent by the user, the server receives it. The received data is preprocessed using a data processing library such as Numpy or Pandas. At this time, an emotion engine (such as the Emotion API) analyzes the user's input data and detects the user's emotional state. The preprocessed data and emotional information are input into a generative AI model. This generative AI model generates a solution based on the data and emotional information. The results are formatted in JSON format or similar and sent back to the user.

[1247] The device provides an interface for the user to enter data related to a specific task. For example, this can be a dedicated application or a form in a web browser. It can be a web application built with React or Angular, or a native Android or iOS app. After the user enters the data, the device sends the input data to the server, usually via an HTTP POST request. The device is also responsible for receiving the response from the server and notifying the user.

[1248] Users interact with their devices to find solutions to specific tasks. For example, they might have an idea for a new app feature and use their device to enter details. The data is processed and the server returns the results to the user, who can then provide feedback if they are satisfied with the results.

[1249] As a concrete example, consider the case where a user participates in a new product idea contest. The user uses the device to input ideas for new smartphone features. For example, the user might input a specific requirement such as "optimizing battery consumption" as details for an "AI-based battery management function." The emotion engine analyzes the user's input data and interactions to detect their emotional state. The device then sends this data and the detected emotional information to the server.

[1250] The server receives the data, preprocesses it using Numpy and Pandas, and then inputs it into the generative AI model. The generative AI model analyzes the data and emotional information and generates a "proposal for an automatic charging schedule adjustment function in addition to a battery management function." The server then sends the results back to the device, where the user can confirm the proposal. Since the user is in a state where they are likely to be convinced by the proposal, it is expected that the results of the emotional engine will also be reflected.

[1251] Examples of prompts include:

[1252] "What are your ideas for AI-powered battery management?"

[1253] "Please give me some suggestions for battery optimization features."

[1254] "Generate battery management ideas, including automatic adjustment of charging schedules."

[1255] This maximizes the effectiveness of generative AI models and emotion engines, enabling us to quickly provide users with highly accurate and emotion-sensitive solutions.

[1256] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1257] Step 1:

[1258] The user inputs a prompt via a terminal. For example, the user inputs specific data or a question, such as "AI-based battery management function suggestions," into a smartphone application or web browser interface. This input data becomes the input for the system.

[1259] Step 2:

[1260] The device sends the input data along with the emotion engine to the server. The device (web application or smartphone app) collects the data entered by the user and analyzes the user's emotions using the Emotion API. The analyzed emotion information and the input data are sent to the server via an HTTP POST request.

[1261] Step 3:

[1262] The server receives the data and performs preprocessing. The server cleans the received data using data processing libraries such as Numpy and Pandas to remove unnecessary noise. This processing transforms the data into a format suitable for generative AI models. The input is the raw data sent by the user, and the output is the preprocessed, clean data.

[1263] Step 4:

[1264] The server analyzes the emotional information and inputs it into the generative AI model. The received emotional information is also analyzed to identify the user's emotional state. This completes the dataset to be input into the generative AI model. The input is the emotional data sent from the emotion engine, and the output is the emotional data converted into a format that can be input into the generative AI model.

[1265] Step 5:

[1266] The server runs the generative AI model and generates a solution. The server inputs the preprocessed data and emotional information into the generative AI model (for example, a model trained with PyTorch or TensorFlow). The model generates a solution based on this data. For example, a solution such as "proposing an automatic charging schedule adjustment function in addition to a battery management function" is generated. The input is the formatted data and emotional information, and the output is the generated solution.

[1267] Step 6:

[1268] The server formats the generated solution and sends it back to the device. The generated result is converted into a format that is easy for the user to understand (for example, JSON format) and sent back to the device as an HTTP response. The input is the solution output by the generative AI model, and the output is the formatted solution.

[1269] Step 7:

[1270] The terminal notifies the user of the solution and displays it. The terminal receives a response from the server and displays the solution on the user interface. The user can check the displayed solution and send feedback that reflects their feelings. The input is the solution returned from the server, and the output is the solution displayed to the user.

[1271] This process flow allows users to quickly obtain solutions that are highly accurate and considerate of emotions.

[1272] (Application example 2)

[1273] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1274] Systems using conventional generative AI models have difficulty generating solutions that take user emotions into account, resulting in lower user satisfaction. Furthermore, while there is a need to analyze a user's emotional state in real time and provide appropriate suggestions based on that analysis, current technology makes it difficult to achieve this.

[1275] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for generating a solution for a specific task using a generative AI model, means for receiving data input from a user, means for executing the generative AI model based on the received data and generating a result, means including an emotion engine for analyzing the user's emotional state, and means for returning the generated result and emotion information to the user. This makes it possible to provide high-quality solutions that take the user's emotions into consideration, which is expected to not only improve user satisfaction but also enable the provision of appropriate suggestions based on real-time analysis.

[1276] A "generative artificial intelligence model" refers to an artificial intelligence technology that generates solutions or predicted results for specific tasks based on data input by a user.

[1277] "User" refers to an entity that utilizes the system and inputs data to seek a solution to a particular task.

[1278] "Data receiving means" refers to a mechanism for the server to receive input data sent by the user.

[1279] "Emotion engine" refers to a system element for analyzing a user's emotional state and providing that emotional information.

[1280] "Preprocessing means" refers to a mechanism that performs preprocessing such as noise removal and format conversion on received data before inputting it into the generative artificial intelligence model.

[1281] "Result generation means" refers to a mechanism that runs a generative artificial intelligence model based on preprocessed data to generate solutions or predicted results.

[1282] "Return means" refers to a mechanism for returning generated solutions and prediction results to the user.

[1283] "Server" refers to the central computer system that receives input data, processes it, runs generative AI models, and generates and returns results.

[1284] "System" refers to a device or configuration that includes a set of means for providing a solution to a user's specific task using a generative artificial intelligence model.

[1285] To implement this invention, three main components are required: a server, a terminal, and a user. In addition, by combining an emotion engine that recognizes the user's emotions, the quality of the provided solution can be improved.

[1286] First, the server plays a central role in training the generative AI model, receiving and processing data sent by users to generate solutions and predictions. Specifically, the server trains the generative AI model using training data. This training data is cleaned to remove unnecessary noise. Once training is complete, the generative AI model is ready to generate solutions for specific tasks. When data is sent by users, the server receives it, preprocesses it, and inputs it into the generative AI model. At this time, the emotion engine also analyzes the user's input data to detect the user's emotional state. The generative AI model processes the data and emotional information to generate a solution for the specific task. The result is formatted and sent back to the user.

[1287] The device provides an interface for the user to input data related to a specific task. For example, this can be a dedicated application or a form on a web browser. After the user enters the data, the device sends the input data to the server. The device is also responsible for receiving responses from the server and notifying the user. For example, when using smart glasses, the device can analyze the customer's emotions in real time through the built-in camera and display and provide appropriate suggestions to the store clerk.

[1288] The user is the one seeking a solution to a specific task. They input data using a device, and once the data is processed, the server sends back the results. The user can also provide further feedback based on the results. For example, a sales associate in a physical store could wear smart glasses and receive personalized solutions in real time, while understanding the customer's emotional state through the glasses.

[1289] In this way, the server generates solutions using the generative AI model and then uses the emotion engine to reflect the user's emotional state while returning the solutions to the user, thereby providing higher quality solutions. As a result, user satisfaction is improved and appropriate suggestions can be provided in real time.

[1290] As a concrete example, a user entering a new product idea contest can come up with an idea for a new smartphone feature and input details of an "AI-based battery management function" using their device. During this input, the emotion engine analyzes the user's input data and interactions to detect their emotional state. The device then sends the data and the detected emotion information to a server, which receives the data and inputs it into a generative AI model after preprocessing. The generative AI model analyzes the data and emotion information and generates a "proposal for a battery management function plus an automatic charging schedule adjustment function." The result is sent back from the server to the device, where the user confirms the proposal. Since the user is in a state where they are likely to be convinced by the proposal, it is expected that the emotion engine's results will also be reflected in the proposal. Based on the proposal, an entry form can be created and submitted to the contest.

[1291] Examples of prompt sentences include the following:

[1292] "A new customer walks into the store. It appears the customer is looking for a specific product, but what is the best way to respond? Use the emotion engine and generative AI model to provide the next suggestion. The customer appears confused, so provide suggestions to help the store associate respond appropriately."

[1293] In this way, by combining a generative AI model with an emotion engine, it is possible to respond appropriately to customer needs and emotions, thereby improving customer satisfaction.

[1294] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1295] Step 1:

[1296] A user inputs data using a terminal (smart glasses). For example, when a customer is browsing products in a store, a camera installed in the smart glasses captures the customer's facial expressions and movements.

[1297] Input: Video data including customer facial expressions and movements

[1298] Output: Captured video data

[1299] Step 2:

[1300] The device sends the captured video data to the emotion engine, which analyzes the user's (customer's) emotional state. The emotion engine analyzes facial expressions and movements from the video data to detect the customer's emotional state.

[1301] Input: Captured video data

[1302] Output: Emotional state (e.g., happy, confused, interested, etc.)

[1303] Step 3:

[1304] The device sends the video data along with the detected emotional state to a server, which preprocesses the received data, removes noise, and converts it into a format suitable for generative AI models.

[1305] Input: Video data, emotional state

[1306] Output: Preprocessed data (e.g. cleaned data, formatted data)

[1307] Step 4:

[1308] The server inputs the preprocessed data into a generative AI model to generate solutions for specific tasks. The generative AI model analyzes the input data and emotional information to generate appropriate countermeasures and suggestions.

[1309] Input: Preprocessed data, emotional state

[1310] Output: Solutions or suggestions (e.g., specific product descriptions, service proposals, etc.)

[1311] Step 5:

[1312] The server formats the generated solutions and suggestions and generates data to send back to the user, including emotional information, in a format that is useful to the user.

[1313] Input: Generated solutions and suggestions

[1314] Output: Formatted data (e.g., suggestion message)

[1315] Step 6:

[1316] The terminal displays the formatted data received from the server and notifies the store clerk of suggestions, and specific countermeasures are displayed in real time on the smart glasses display.

[1317] Input: Formatted data

[1318] Output: Suggestions displayed on the smart glasses display

[1319] Step 7:

[1320] The user (store clerk) can respond optimally to the customer based on the suggestions displayed on the smart glasses, for example, explaining the product to a confused customer or providing additional information to an interested customer.

[1321] Input: Suggestions from smart glasses

[1322] Output: Appropriate response to the customer

[1323] This step is expected to improve customer satisfaction. By utilizing an emotion engine and generative AI model in the process of generating solutions for specific tasks, advanced support based on the user's emotions can be realized.

[1324] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1325] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1326] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1327] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1328] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1329] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1330] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1331] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1332] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1333] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1334] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1335] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1336] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1337] 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.

[1338] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1339] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1340] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1341] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1342] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1343] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1344] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1345] The following is further disclosed regarding the above embodiment.

[1346] (Claim 1)

[1347] means for generating solutions to specific tasks using a generative artificial intelligence model;

[1348] means for receiving data input from a user;

[1349] means for executing the generative artificial intelligence model based on received data to generate a result;

[1350] means for returning the generated results to the user;

[1351] A system including:

[1352] (Claim 2)

[1353] 10. The system of claim 1, wherein the generative artificial intelligence model is trained using a specific dataset.

[1354] (Claim 3)

[1355] 2. The system of claim 1, further comprising means for pre-processing data input to said generative artificial intelligence model.

[1356] "Example 1"

[1357] (Claim 1)

[1358] means for a user to input data using a terminal;

[1359] means for transmitting data input from the terminal to a server;

[1360] means for preprocessing data received by the server;

[1361] A means of inputting the preprocessed data into a generative AI model to generate a solution; and

[1362] a means for formatting the generated solution;

[1363] means for transmitting the formatted solution to a terminal;

[1364] a means for the terminal to notify the user of the solution;

[1365] A system including:

[1366] (Claim 2)

[1367] 10. The system of claim 1, wherein the generative AI model is trained using a specific dataset.

[1368] (Claim 3)

[1369] 10. The system of claim 1, further comprising means for pre-processing data input to the generative AI model.

[1370] "Application Example 1"

[1371] (Claim 1)

[1372] means for generating solutions to specific tasks using a generative artificial intelligence model;

[1373] means for receiving data input from a user;

[1374] means for executing the generative artificial intelligence model based on received data to generate a result;

[1375] means for automatically generating and displaying data through an identification device;

[1376] means for returning the generated results to the user;

[1377] A system including:

[1378] (Claim 2)

[1379] 10. The system of claim 1, wherein the generative artificial intelligence model is trained using a specific dataset.

[1380] (Claim 3)

[1381] 2. The system of claim 1, further comprising means for pre-processing data input to said generative artificial intelligence model.

[1382] "Example 2: Combining Emotion Engines"

[1383] (Claim 1)

[1384] means for generating solutions to a particular task using a generative artificial intelligence model;

[1385] means for receiving data input from a user;

[1386] means for executing the generative artificial intelligence model based on received data to generate a result;

[1387] means for returning the generated results to the user;

[1388] means for analyzing user emotions;

[1389] A means for inputting the analyzed emotion information into the generative artificial intelligence model;

[1390] A system including:

[1391] (Claim 2)

[1392] 10. The system of claim 1, wherein the generative artificial intelligence model is trained using a specific dataset.

[1393] (Claim 3)

[1394] 2. The system of claim 1, further comprising means for pre-processing data input to said generative artificial intelligence model.

[1395] "Application example 2 when combining emotion engines"

[1396] (Claim 1)

[1397] means for generating solutions to specific tasks using a generative artificial intelligence model;

[1398] means for receiving data input from a user;

[1399] means for executing the generative artificial intelligence model based on received data to generate a result;

[1400] means including an emotion engine for analyzing an emotional state of a user;

[1401] means for returning the generated results and emotion information to the user;

[1402] A system including:

[1403] (Claim 2)

[1404] 10. The system of claim 1, wherein the generative artificial intelligence model is trained using a new data set.

[1405] (Claim 3)

[1406] 2. The system of claim 1, further comprising means for pre-processing data and emotion information input to said generative artificial intelligence model. [Explanation of symbols]

[1407] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for generating solutions to specific tasks using a generative artificial intelligence model; means for receiving data input from a user; means for executing the generative artificial intelligence model based on received data to generate a result; means for returning the generated results to the user; A system including:

2. The system of claim 1 , wherein the generative artificial intelligence model is trained using a specific data set.

3. 2. The system of claim 1, further comprising means for pre-processing data input to said generative artificial intelligence model.

Images