System

Abstract

A system is provided.SOLUTION: A system comprising: means for automatically adjusting resources in real-time in response to a number of cloud server users; means for automating user responses, such as chat services and customer support, using a generative artificial intelligence model; and means for automatically generating in-game content and updates using the generative artificial intelligence model.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] Many online games face difficulties in continuing their services due to maintenance costs and personnel resource constraints, forcing them to end their services. This situation leaves users disappointed and game developers losing potential profits. Furthermore, existing technologies require manual operation, making it difficult to reduce costs. There is a need for a solution to these issues, an ultra-low-cost method for automating online game operations, and a means to continue services. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems with a system that includes a means for automatically adjusting resources in real time based on the number of users of a cloud server, a means for automating user chat services and customer support responses using a generative artificial intelligence model, and a means for automatically generating in-game content and updates using a generative artificial intelligence model. Specifically, the system measures resources based on the number of users of the cloud server and calculates the amount of resources, and automatically adjusts server instances based on scaling. The system also uses a generative artificial intelligence model to automatically generate new stages, characters, and character dialogue, and generates chat dialogue for customer support. Furthermore, the system activates a speech synthesis model in response to specific trigger words to generate voice data. In this way, online game operations are automated at low cost, making the service sustainable.

[0006] "Cloud Server" refers to server resources and functionality provided over the internet, allowing remote access to data storage and computing power.

[0007] "User Count" refers to the total number of users currently actively participating in a particular online game.

[0008] "Resources" refers to resources including computing and storage capacity such as CPU, memory, and storage of a cloud server.

[0009] A "generative artificial intelligence model" is a machine learning model that has the ability to learn large amounts of data in advance and automatically generate new data and content.

[0010] "Chat service" refers to a service that allows users to communicate with each other in real time in text format.

[0011] "Customer support" refers to services that assist users with inquiries and problem resolution.

[0012] "Content" refers to elements such as stages, characters, dialogue, and story available in the game.

[0013] "Scaling" refers to the process of dynamically adjusting the amount of resources on a cloud server.

[0014] "Server instance" refers to a unit of virtual server running in a cloud environment.

[0015] A "trigger word" is a keyword that triggers a specific action or process.

[0016] A "speech synthesis model" refers to a machine learning model for generating speech based on text data.

[0017] "Audio data" refers to digital data containing generated audio information. [Brief explanation of the drawings]

[0018] [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

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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."

[0039] The system of the present invention includes automatic resource adjustment according to the number of cloud server users, automated chat service and customer support using generative artificial intelligence models, and means for automatically generating in-game content and updates in order to avoid the termination of online game services and to operate them automatically at low cost.

[0040] The operation of the system of the present invention will be specifically described below.

[0041] Cloud Server Management

[0042] server

[0043] The server measures the current number of active users at regular intervals.

[0044] Example: The server measures the number of active users every hour and adjusts resources based on that number. For example, if the number of active users decreases at night, unnecessary instances are automatically released to reduce costs.

[0045] The server calculates the amount of resources needed based on the number of active users.

[0046] Example: If the number of active users increases, the server will launch new instances and instantly add the required CPU, memory, and storage.

[0047] Leveraging generative AI models

[0048] Terminal

[0049] The device receives requests from users and sends them to the AI ​​model.

[0050] Example: When a user sends a message to customer support, the device forwards the message to the AI ​​model, which then generates a response appropriate to the inquiry and sends it back to the device.

[0051] The terminal displays the generated response to the user.

[0052] Example: The device displays responses from the AI ​​model in a chat window, providing the user with a quick response.

[0053] Automatic updates

[0054] server

[0055] The server periodically sends game data to the AI ​​model.

[0056] Example: Every weekend, the server collects game data and pushes it to an AI model, which uses this data to generate new stages and character dialogue.

[0057] The server reflects the generated content in the game.

[0058] Example: The server integrates new content returned by the AI ​​model into the existing game data and automatically applies updates.

[0059] Voice support

[0060] Terminal

[0061] The device will activate the AI ​​voice bot when triggered by user action.

[0062] Example: When a user interacts with a specific character, the device detects when the "speak" button is pressed and sends text to an AI voice bot.

[0063] The terminal provides the generated voice data to the user.

[0064] Example: The device receives audio files from an AI voice bot and plays them in the game, allowing users to enjoy natural voice interaction.

[0065] Based on the above process, all operational processes, including cloud server operation, user support, content generation, and voice response, are automated using AI, enabling continuous operation of online games, which also significantly reduces operational costs and eases the burden on human resources.

[0066] The processing flow will be explained below.

[0067] Cloud Server Management

[0068] Step 1: Measure active users

[0069] The server measures the current number of active users at regular intervals.

[0070] Specifically, the server checks the sessions of all users connected to each game instance and tally the total number of active sessions.

[0071] Step 2: Calculate resources

[0072] The server calculates the amount of resources needed based on the number of active users.

[0073] For example, the server dynamically calculates new amounts of CPU, memory, and storage when the number of active users exceeds a certain threshold.

[0074] Step 3: Performing scaling

[0075] The server uses auto-scaling to adjust resources.

[0076] The servers automatically launch new instances to accommodate increased user load, and release unneeded instances to reduce costs when the number of users decreases.

[0077] Leveraging generative AI models

[0078] Step 1: Get the user request

[0079] The terminal receives a request from the user.

[0080] The device collects user messages using an in-game chat interface and customer support.

[0081] Step 2: Send to AI model

[0082] The device sends the user request to the appropriate AI model.

[0083] The device sends the message received from the user in text format to the API endpoint of the AI ​​model.

[0084] Step 3: Generation by AI model

[0085] The server receives the response generated by the AI ​​model.

[0086] The server receives and stores the response messages sent by the AI ​​model.

[0087] Step 4: Deliver to users

[0088] The terminal returns the generated response to the user.

[0089] The device displays the response from the AI ​​model on the chat interface and provides it to the user instantly.

[0090] Automatic updates

[0091] Step 1: Collect data

[0092] The server periodically collects the latest game data.

[0093] The server collects game setting files, character data, stage information, and other information all at once.

[0094] Step 2: Prepare to send data

[0095] The server prepares to send the collected game data to the AI ​​model.

[0096] The server formats various data and prepares it in a form that can be processed by the AI ​​model.

[0097] Step 3: Generation by AI model

[0098] The server sends game data to the AI ​​model and requests it to generate new content.

[0099] The AI ​​model generates new stages and character lines based on the data sent and sends them back to the server.

[0100] Step 4: Reflecting content

[0101] The server reflects the generated new content in the game.

[0102] The server incorporates the data returned from the AI ​​model into the game data and provides it to the user as new content.

[0103] Voice support

[0104] Step 1: Detecting trigger words

[0105] The device detects whether the user has used a specific trigger word.

[0106] The device monitors messages entered by users in the chat interface and detects defined trigger words.

[0107] Step 2: Launch your AI voicebot

[0108] If the device detects a trigger word, it will activate an AI voice bot.

[0109] Based on the detected trigger word, the device prepares to send text to the speech synthesis API.

[0110] Step 3: Speech generation

[0111] The server generates voice data using an AI voice bot.

[0112] The server inputs the transmitted text data into a speech synthesis model and generates an audio file.

[0113] Step 4: Streaming audio data

[0114] The terminal provides the generated voice data to the user.

[0115] The terminal plays back the generated audio data and lets the user hear it.

[0116] Example 1

[0117] 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."

[0118] When operating an online game, it is important to avoid service termination and ensure continuous operation at low cost. However, managing resources to respond to fluctuations in user numbers, providing user support, automatically generating content, and providing voice dialogue manually is extremely labor-intensive and increases operational costs. For this reason, an efficient, automated system is needed.

[0119] 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.

[0120] In this invention, the server includes means for automatically adjusting resources in real time according to the number of cloud server users, means for automating user chat services and customer support using a generative artificial intelligence model, means for automatically generating in-game content and updates using the generative artificial intelligence model, and means for providing voice interaction functionality using the generative artificial intelligence model, thereby enabling efficient resource management, automated user support, continuous content updates, and the provision of natural voice interaction.

[0121] A "cloud server" is a server system that provides multiple distributed computing resources accessible via the Internet.

[0122] "Automatic resource adjustment" is the process of dynamically changing the allocation of computing resources (CPU, memory, storage, etc.) depending on the number of users and load.

[0123] A "generative artificial intelligence model" is a machine learning algorithm and its implementation that can generate new information and content based on given data and conditions.

[0124] "User Chat Service" is a collective term for the interface that allows users to have text-based interactions with the system and the system that operates behind the interface.

[0125] "Customer support" refers to a service that responds to inquiries and problems from users and provides solutions.

[0126] "In-game content" means all elements (stages, characters, items, etc.) that users can operate, view, or use within an online game.

[0127] "Voice interaction functions" refer to the functions of a system that interacts based on a user's voice input and the voice output that it generates.

[0128] "Real-time" means that the delay between data generation, processing, and notification is close to zero.

[0129] "Scaling" is the process of increasing or decreasing system resources according to certain conditions or criteria.

[0130] A "server instance" is an individual virtual machine or container running on a cloud service.

[0131] The system of the present invention aims to prevent service terminations of online games and automate their operation at low cost. The system includes automatic resource adjustment based on the number of cloud server users, automated chat service and customer support using generative AI models, and automatic generation of in-game content and updates. Furthermore, it provides voice interaction functionality to create a more interactive user experience.

[0132] Cloud Server Management

[0133] The server measures the current number of active users at regular intervals. For example, the server obtains the number of active users from the game's login data at 00 minutes past the hour. This measurement data is recorded in a database and used in the next step. Based on the obtained number of active users, the server calculates the required amount of resources. If one instance is required for 200 users, and the current number of active users is 400, it calculates that a total of two instances are required. Based on this calculation, the server automatically adds or releases the necessary resources. For example, if the number of active users drops to 100 overnight, it will run only one instance and release the unnecessary instances.

[0134] Leveraging generative AI models

[0135] The device receives requests from the user and sends them to the generative AI model. For example, when a user sends a message to customer support, the device forwards the content to the AI ​​model. An example of a prompt sentence is, "User inquiry: I can't log in to my account. Please suggest a solution." The AI ​​model generates a response appropriate to the inquiry and sends it back to the device. The device then displays the generated response to the user. For example, the response from the AI ​​model can be displayed in a chat window, allowing the user to receive a prompt reply.

[0136] Automatic updates

[0137] The server periodically sends game data to the generative AI model. For example, the server collects game data every weekend and pushes it to the AI ​​model. A specific example of a prompt might be, "Generate new stages and character dialogue based on last week's data." The AI ​​model then generates new content (stages and character dialogue) based on this data. The generated new content is integrated with the existing game data and automatically reflected in the game.

[0138] Voice support

[0139] The device triggers the AI ​​voice bot with user actions. For example, when a user interacts with a specific character, it detects that the "Speak" button has been pressed and sends text to the AI ​​voice bot. An example of a prompt to send is "The user is interacting with Character A. Please generate a greeting line in voice." The device then plays back the voice data received from the AI ​​voice bot. This allows the user to enjoy a conversation in a natural voice.

[0140] The above process enables efficient resource management of cloud servers, automated user support, automatic game updates, and voice interaction, ensuring continuous operation of online games, while significantly reducing operational costs and the burden on personnel resources.

[0141] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0142] Cloud Server Management

[0143] Step 1:

[0144] The server measures the current number of active users at regular intervals. Specifically, the server obtains the number of active users from the game's login data at 00 minutes past the hour. The information is recorded in a database. The input is the login data, and the output is the number of active users.

[0145] Step 2:

[0146] The server calculates the required amount of resources based on the measured number of active users. For example, if it calculates that one instance is required for 200 users, and the number of active users is 400, two instances are required. This calculation result is sent to the resource management system. The input is the number of active users, and the output is the required amount of resources.

[0147] Step 3:

[0148] The server automatically adds or releases resources based on the calculation results. For example, if the number of active users drops to 100 overnight, it will run only one instance and release unnecessary instances. The input is the amount of resources required, and the output is the adjusted number of instances.

[0149] Leveraging generative AI models

[0150] Step 1:

[0151] The terminal receives requests from the user, such as when a user sends a message to customer support. The input is the user message, and the output is the converted prompt.

[0152] Step 2:

[0153] The device sends the received message to the generative AI model. It uses a REST API to send a request to the AI ​​model, for example, using a prompt such as "User inquiry: I can't log in to my account. Please suggest a solution." The input is the converted prompt, and the output is the response from the AI ​​model.

[0154] Step 3:

[0155] The device displays the generated response to the user. For example, it displays the response from the AI ​​model in a chat window, providing a quick reply to the user. The input is the response from the AI ​​model, and the output is the response displayed to the user.

[0156] Automatic updates

[0157] Step 1:

[0158] The server periodically collects game data, for example, summarizing game activity data every weekend. The input is the game activity data, and the output is the collected data.

[0159] Step 2:

[0160] The server sends the collected data to the generative AI model via an API, using a prompt such as, "Generate a new stage and character dialogue based on last week's data." The input is the collected data and the prompt, and the output is the generated new content.

[0161] Step 3:

[0162] The server reflects the generated new content in the game. It integrates the generated stage data and character dialogue into the existing game database and automatically updates the online game. The input is the generated new content, and the output is the updated game data.

[0163] Voice support

[0164] Step 1:

[0165] The device activates the AI ​​voice bot as a trigger of user actions. For example, when a user interacts with a specific character, it detects when the "Speak" button is pressed. The input is the user's actions, and the output is the transmitted text.

[0166] Step 2:

[0167] The device sends the detected text to an AI voice bot. The text is sent to a generative AI model, and a prompt such as "The user will interact with Character A. Please generate a greeting line in voice." The input is the text to be sent and the prompt, and the output is the generated voice data.

[0168] Step 3:

[0169] The device receives and plays back the voice data generated by the AI ​​voice bot. The voice file is then loaded by the player and played in the game. The input is the generated voice data, and the output is the voice that is played.

[0170] (Application example 1)

[0171] 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."

[0172] In today's online services and e-commerce platforms, efficient management of server resources, user support, and content updates are chronically draining human resources. Furthermore, providing voice support and quickly generating new product descriptions and reviews to improve the user experience are also challenges. Systems that can efficiently automate these tasks are needed.

[0173] 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.

[0174] In this invention, the server includes means for automatically adjusting resources in real time according to the number of cloud server users, means for automating user chat services and customer support using a generative artificial intelligence model, means for automatically generating online content and updates using the generative artificial intelligence model, and means for generating voice data and providing voice dialogue using the generative artificial intelligence model, thereby enabling efficient operation of the server, provision of high-quality user services, and automated content updates.

[0175] A "cloud server" is a server with computing resources and storage provided via the Internet.

[0176] "Real-time" refers to the instantaneous processing of data and information, meaning that there is very little delay.

[0177] "Automatic resource adjustment" refers to dynamically increasing or decreasing resources such as CPU, memory, and storage depending on server usage.

[0178] A "generative artificial intelligence model" is an artificial intelligence algorithm that is trained to generate content such as text, audio, or images.

[0179] "Chat service" refers to a service that allows real-time communication via text messages.

[0180] "Customer support" refers to support services provided to resolve inquiries and problems regarding products and services.

[0181] "Online content" refers to various media content, such as text, images, audio, and video, that is distributed via the Internet.

[0182] "Auto-generation" refers to content being created anew by a system or algorithm without human intervention.

[0183] "Speech data" refers to digital recordings of speech, typically used for speech recognition and synthesis.

[0184] "Voice interaction" refers to an interface in which the user interacts with the system using voice.

[0185] A "product description" is text or media content that provides detailed explanations of a product's features, functions, specifications, etc.

[0186] A "review" is content that describes a user's evaluation or opinion of a product or service.

[0187] "Recommendation" refers to a system or function that recommends products or services based on a user's preferences and behavioral history.

[0188] System Overview

[0189] This invention relates to a system that efficiently manages cloud server resources and utilizes generative artificial intelligence models to provide chat services, customer support, voice dialogue, and automatic content generation for users. Specific embodiments of this system are described below.

[0190] Hardware and Software Used

[0191] Hardware:

[0192] Smartphone

[0193] Cloud infrastructure (e.g. AWS, GCP)

[0194] software:

[0195] Programming languages: Python, Java (server side), Swift / Kotlin (mobile apps)

[0196] Frameworks: TensorFlow (generative AI model), Flask / Django (server-side API)

[0197] Libraries: NLTK, Spacy (natural language processing)

[0198] API: Google Cloud Speech-to-Text, Google Cloud Text-to-Speech

[0199] Processing Overview

[0200] 1. Cloud server resource management

[0201] The server measures the number of people using the cloud server at regular intervals and calculates the required amount of resources based on the data. Before resources become overloaded, it automatically launches new instances and adds the necessary CPU, memory, and storage. It also reduces costs by automatically releasing unnecessary instances when usage decreases.

[0202] 2. AI chat support

[0203] When a user sends a message to customer support from their device, the message is forwarded to the AI ​​model, which generates a response appropriate to the inquiry and sends it back to the device. This response is then displayed in the chat window, allowing the user to receive a prompt reply.

[0204] Example prompt sentence:

[0205] User: I want to know more about this product

[0206] AI model response: We will provide you with detailed product information. The main features of this product are...

[0207] 3. Automated content generation

[0208] The server periodically sends new product data to the AI ​​model and receives the generated product descriptions and recommendations. The generated content is automatically updated in the device application, ensuring that the latest information is always provided.

[0209] Example prompt sentence:

[0210] Generate a testimonial for your new smartphone

[0211] AI model response:

[0212] This latest smartphone is packed with innovative features and beautiful design, most notably...

[0213] 4. Voice support

[0214] When a user taps the microphone icon to start voice input, the recorded voice is converted into text by Google Cloud Speech-to-Text. The generated text is sent to an AI model, which returns an appropriate response. Google Cloud Text-to-Speech then generates audio data and plays it back on the device, allowing users to enjoy natural voice interaction.

[0215] The combination of these measures enables efficient operation of cloud servers, fast customer support, automated content generation and voice interaction, significantly reducing the operating costs of online services and providing a high-quality user experience.

[0216] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0217] Step 1:

[0218] The server measures the number of people using the cloud server at regular intervals. The input is the current number of active users, and the output is the calculated amount of resources required. This measurement is based on server log data and real-time access data. Specifically, the current number of active users is obtained by analyzing the server's access log.

[0219] Step 2:

[0220] The server calculates the required amount of resources based on the number of active users measured, and automatically adjusts the server instances. The input is the number of active users data output from Step 1, and the output is information about the instances to be newly added or released. Specifically, AWS's Auto Scaling function is used to dynamically add or reduce the required CPU and memory.

[0221] Step 3:

[0222] The device receives customer support messages from users and sends them to the AI ​​model. The input is the message entered by the user into the device, and the output is a prompt for the generative artificial intelligence model. Specifically, when the user enters a message and presses the send button, the message is transferred to the AI ​​model via the server.

[0223] Step 4:

[0224] The server receives the response generated by the AI ​​model and sends it to the terminal. The input is the response data generated by the AI ​​model, and the output is data in the format displayed in the chat window. Specifically, the AI ​​model generates a response appropriate to the inquiry content and sends it to the terminal in JSON format.

[0225] Step 5:

[0226] The server periodically sends new product data to the AI ​​model and receives the generated product descriptions and recommendations. The input is product attribute data, and the output is the generated product descriptions and recommendation lists. Specifically, information from the product database is periodically pushed to the AI ​​model to generate new descriptions and recommendation lists.

[0227] Step 6:

[0228] The device displays product descriptions and recommendations received from the server. The input is the generated data transferred from the server, and the output is the content displayed on the device's UI. Specifically, the generated descriptions and recommended item lists are rendered in the display area within the app.

[0229] Step 7:

[0230] The user starts voice input, and the device converts the recorded voice into text using the Google Cloud Speech-to-Text API. The input is the user's voice data, and the output is text data. Specifically, voice recording begins when the microphone button is pressed, and the recorded data is sent to the cloud API and converted into text.

[0231] Step 8:

[0232] The user's speech, converted into text, is sent to an AI model to generate an appropriate voice response. The input is text data, and the output is the response text data. Specifically, the converted text is sent to the AI ​​model as a prompt, and an appropriate reply is generated.

[0233] Step 9:

[0234] The server uses the Google Cloud Text-to-Speech API to convert the generated text data into audio data and send it to the device. The input is the text data of the response content, and the output is audio data. Specifically, the generated response text is sent to the cloud API, which generates an audio file and sends it to the device.

[0235] Step 10:

[0236] The device plays back the received voice data and provides it to the user. The input is the voice data sent from the server, and the output is the user's auditory feedback. Specifically, the received voice file is provided to the user using the playback function, realizing natural voice interaction.

[0237] 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.

[0238] The system of the present invention provides a more interactive and personalized experience by combining automatic resource adjustment according to the number of cloud server users, automated user support using a generative artificial intelligence model, and automatic generation of in-game content with an emotion engine that recognizes user emotions.

[0239] The operation process of the system of the present invention will be specifically described below.

[0240] Cloud Server Management

[0241] server

[0242] The server measures the current number of active users at regular intervals.

[0243] Example: The server measures the number of active users every hour and adjusts resources based on that number. For example, if the number of active users decreases at night, unnecessary instances are automatically released to reduce costs.

[0244] The server calculates the amount of resources needed based on the number of active users.

[0245] Example: If the number of active users increases, the server will launch new instances and instantly add the required CPU, memory, and storage.

[0246] Leveraging generative AI models

[0247] Terminal

[0248] The device receives requests from users and sends them to the AI ​​model.

[0249] Example: When a user sends a message to customer support, the device forwards the message to the AI ​​model, which then generates a response appropriate to the inquiry and sends it back to the device.

[0250] The terminal displays the generated response to the user.

[0251] Example: The device displays responses from the AI ​​model in a chat window, providing the user with a quick response.

[0252] Automatic updates

[0253] server

[0254] The server periodically sends game data to the AI ​​model.

[0255] Example: Every weekend, the server collects game data and pushes it to an AI model, which uses this data to generate new stages and character dialogue.

[0256] The server reflects the generated content in the game.

[0257] Example: The server integrates new content returned by the AI ​​model into the existing game data and automatically applies updates.

[0258] Utilizing the Emotion Engine

[0259] Terminal

[0260] The device recognizes emotions from the user's voice and text.

[0261] Example: The device analyzes messages typed by the user in a chat interface and the content of voice calls to detect the user's emotions.

[0262] server

[0263] The server then tailors responses for chat services and customer support based on the perceived emotion.

[0264] For example: If the emotion engine detects "anger" or "sadness," the server may change the response to be more polite and comforting. Conversely, if it detects "joy" or "excitement," the server may adjust the response to a friendlier tone.

[0265] Terminal

[0266] The device changes the movements and expressions of the in-game characters in real time according to the user's emotions.

[0267] Example: If the device's emotion engine recognizes that the user is sad, it will change the in-game character to make comforting gestures and say comforting lines.

[0268] Voice support

[0269] Terminal

[0270] The device will activate the AI ​​voice bot when triggered by user action.

[0271] Example: When a user interacts with a specific character, the device detects when the "speak" button is pressed and sends text to an AI voice bot.

[0272] server

[0273] The server generates voice data using an AI voice bot.

[0274] Example: The server uses a speech synthesis model to generate an audio file based on the text sent and sends it back to the device.

[0275] Terminal

[0276] The terminal plays the generated audio data to the user.

[0277] Example: The device plays the generated audio data so that the user can hear it.

[0278] As a result, the system of the present invention achieves effective resource management of cloud servers, automated user response through generative AI models, and interactive and emotionally responsive experiences through an emotion engine, which significantly reduces operational costs and alleviates the burden on human resources.

[0279] The processing flow will be explained below.

[0280] Cloud Server Management

[0281] Step 1: Measure active users

[0282] The server measures the current number of active users at regular intervals.

[0283] Example: The server checks and aggregates the session information of active users every hour, thereby determining the real-time number of users.

[0284] Step 2: Calculate resources

[0285] The server calculates the amount of resources needed based on the number of active users.

[0286] Example: A server calculates how many additional resources (CPU, memory, storage) to add when the number of active users exceeds a certain threshold (e.g., 500 users).

[0287] Step 3: Performing scaling

[0288] The server uses auto-scaling to adjust resources.

[0289] Example: Servers launch new instances to add necessary resources as the number of users increases, while unnecessary instances are stopped to reduce costs when the number of users decreases.

[0290] Leveraging generative AI models

[0291] Step 1: Get the user request

[0292] The terminal receives a request from the user.

[0293] Example: When a user contacts customer support, the device receives the message.

[0294] Step 2: Send to AI model

[0295] The device sends the user request to the AI ​​model.

[0296] Example: The device sends the received message to the API endpoint of the AI ​​model, initiating processing to generate an appropriate response.

[0297] Step 3: Generation by AI model

[0298] The server receives the response generated by the AI ​​model.

[0299] Example: The server receives and stores the response message generated by the AI ​​model.

[0300] Step 4: Deliver to users

[0301] The terminal returns the generated response to the user.

[0302] Example: The device displays a reply message from the AI ​​model on the chat interface and provides it to the user.

[0303] Automatic updates

[0304] Step 1: Collect data

[0305] The server periodically collects the latest game data.

[0306] Example: Every weekend, the server collects game configuration files, character data, stage information, etc.

[0307] Step 2: Prepare data for transmission

[0308] The server prepares to send the collected game data to the AI ​​model.

[0309] Example: The server formats the data in a way that is easy for the AI ​​model to parse.

[0310] Step 3: Generation by AI model

[0311] The server sends game data to the AI ​​model and requests it to generate new content.

[0312] Example: An AI model generates new levels and character dialogue and sends it back to the server.

[0313] Step 4: Reflecting content

[0314] The server reflects the generated new content in the game.

[0315] Example: The server integrates new content returned by the AI ​​model into the existing game data and updates it so that the new content is immediately available to the user.

[0316] Utilizing the Emotion Engine

[0317] Step 1: Collecting emotion data

[0318] The device recognizes emotions from the user's voice and text.

[0319] Example: The device analyzes messages entered by the user in a chat interface to detect the user's emotions (happiness, sadness, anger, excitement).

[0320] Step 2: Generate an emotion-based response

[0321] The server adjusts the response content based on the user's emotions recognized by the emotion engine.

[0322] Example: If the server detects "anger," it might make its response polite and comforting, but if it detects "happiness," it might use a friendlier tone.

[0323] Step 3: Generate emotion-based content

[0324] The server dynamically generates content within the game according to the user's emotions.

[0325] Example: If the user is sad, an in-game character can automatically generate comforting lines and actions.

[0326] Voice support

[0327] Step 1: Detecting trigger words

[0328] The device detects whether the user has used a specific trigger word.

[0329] Example: The device monitors and detects trigger words such as "talk" in a chat interface.

[0330] Step 2: Launch your AI voicebot

[0331] The device will activate an AI voice bot if it detects a trigger word.

[0332] Example: The device sends the detected trigger word to an AI voice bot to start the voice synthesis process.

[0333] Step 3: Speech generation

[0334] The server generates voice data using an AI voice bot.

[0335] Example: The server inputs the submitted text data into a speech synthesis model and saves the generated audio file.

[0336] Step 4: Streaming audio data

[0337] The terminal provides the generated voice data to the user.

[0338] Example: The device plays the generated audio data so that the user can hear it.

[0339] Example 2

[0340] 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."

[0341] Conventional cloud server systems face challenges in efficient resource management, making it difficult to flexibly adjust and respond to user usage and emotions. They also lack the ability to automatically generate in-game content and provide interactive experiences based on user emotions. This has resulted in high system operating costs and limited user experience.

[0342] 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.

[0343] In this invention, the server includes means for automatically adjusting resources in real time according to the number of cloud server users, means for automating user chat services and customer support responses using a generative artificial intelligence model, means for automatically generating in-game content and updates using a generative artificial intelligence model, means for recognizing emotions from user voice and text using an emotion recognition engine and adjusting response content based on the emotions, and means for converting text into voice data based on user operations using a speech synthesis engine and playing the voice data back to the user. This enables efficient resource management and cost reduction, and makes it possible to provide users with a more interactive and personalized experience.

[0344] A "cloud server" is a computer server that provides remote computer resources accessible over the Internet.

[0345] "Real-time" is a term that refers to events and data processing occurring as soon as they occur.

[0346] "Resources" are the hardware and software capabilities that a computer system provides, such as computation, memory, and storage.

[0347] A "generative artificial intelligence model" is an algorithm and machine learning model that automatically generates data and information based on instructions given by humans.

[0348] "Chat service" is a communication service that allows sending and receiving text messages in real time.

[0349] "Customer Support" means services that provide assistance to customers with questions or problems.

[0350] An "emotion recognition engine" is an algorithm and system for analyzing and recognizing emotions from human voice and text.

[0351] A "speech synthesis engine" is a technology and program for converting text data into voice data.

[0352] "Scaling" is the process of increasing or decreasing a system's processing power or resources to adapt to load or demand.

[0353] An "instance" is an individual execution environment for virtual machines and computer resources that run on a cloud server.

[0354] The present invention is a system that utilizes a cloud server to efficiently manage resources based on the user's usage status and emotions, and combines a generative artificial intelligence model and an emotion recognition engine to provide an advanced user experience.

[0355] First, the server uses the cloud provider's monitoring tools (for example, a general cloud management service) to measure the current number of active users at regular intervals. Based on the measured number of active users, the server calculates the amount of resources required and automatically adjusts the resources. Specifically, this involves adding or removing virtual machine instances using a scaling policy.

[0356] Next, the device receives the user's request and sends it to a generative artificial intelligence model (e.g., a general-purpose generative AI model). When the user sends a message to customer support, the content is sent to the generative AI model, which generates an appropriate response. For example, if the user asks, "I'd like to return an item. What should I do?", the generative AI model will generate a response such as, "We will inform you of the return procedure. First, please fill out the return form."

[0357] Furthermore, the server periodically collects the latest game data and sends it to the generative AI model, which then generates new stages and character dialogue and integrates them with the existing game data, updating the game database and automatically distributing the updates to the server.

[0358] The device analyzes the user's voice and text and recognizes the user's emotions using an emotion recognition engine (e.g., a general emotion analysis service). This emotion information is sent to the server and used to adjust the response content and the in-game character's movements and facial expressions in real time. For example, if the user types "Today was a tough day," the emotion recognition engine recognizes this as "sadness," and the in-game character will say encouraging words like "Cheer up!"

[0359] Furthermore, the device activates a speech synthesis engine in response to a user operation, converts the text into voice data, and plays it back to the user. For example, when the user presses the "speak" button, the text is sent to the speech synthesis engine, and the generated voice data is played back.

[0360] This allows the system of the present invention to achieve efficient resource management, reduce costs, and provide users with an interactive and personalized experience.

[0361] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0362] Step 1:

[0363] The server uses the cloud provider's monitoring tool to measure the current number of active users at regular intervals. Specifically, it periodically retrieves metric data generated by the monitoring tool and analyzes the data with a Python script.

[0364] Input: Metric data from cloud provider monitoring tools

[0365] Output: Analysis result of current number of active users

[0366] Step 2:

[0367] The server calculates the required amount of resources based on the number of active users measured, and automatically adds or removes virtual machine instances using a scaling policy, specifically using an auto-scaling function such as AWS Lambda.

[0368] Input: Number of active users

[0369] Output: Instances added or removed due to resource throttling

[0370] Step 3:

[0371] The user sends a message to customer support through the device, which receives the user's request and sends it to the generative AI model.

[0372] Input: Customer support message from the user

[0373] Output: The request sent to the generative AI model

[0374] Step 4:

[0375] The generative AI model generates a response appropriate to the user's request and returns the response to the device. Specifically, the generative AI model uses natural language processing to generate text appropriate to the inquiry.

[0376] Input: Customer Support Request

[0377] Output: Generated customer support response text

[0378] Step 5:

[0379] The device displays the response returned by the generative AI model to the user, specifically, by displaying the generated response in a chat window.

[0380] Input: Response text from the generative AI model

[0381] Output: Response displayed in the chat window

[0382] Step 6:

[0383] The server periodically collects the latest game data and sends it to the generative AI model, which then converts the collected game data into JSON format and sends it to the AI ​​model.

[0384] Input: Latest game data

[0385] Output: Game data sent to the AI ​​model

[0386] Step 7:

[0387] The generative AI model generates new game content (e.g., stages and character dialogue) and sends that content back to the server.

[0388] Input: Game data

[0389] Output: Generated game content

[0390] Step 8:

[0391] The server integrates the generated new game content into the existing game database and automatically updates the game data.

[0392] Input: Generated game content

[0393] Output: Updated game database

[0394] Step 9:

[0395] The device sends the user's voice and text to an emotion recognition engine to analyze the user's emotions. Specifically, the device sends the voice and text to an emotion analysis service to obtain emotional information.

[0396] Input: User voice or text

[0397] Output: Parsed emotion information

[0398] Step 10:

[0399] The server adjusts the response based on the analyzed user's emotions. For example, if the emotion recognition engine detects "sadness," it changes the response to something comforting.

[0400] Input: Parsed emotion information

[0401] Output: Adjusted response content

[0402] Step 11:

[0403] The user interacts with the in-game character through the device, which then changes the character's behavior and facial expressions in real time based on the user's emotional information. Specifically, the device controls the character's behavior using the game engine's API.

[0404] Input: User's emotional information

[0405] Output: Modified character movements and expressions

[0406] Step 12:

[0407] The device activates a speech synthesis engine in response to user operations and converts text into voice data. Specifically, when the user presses the "speak" button, the device sends the text to the speech synthesis engine.

[0408] Input: User text input

[0409] Output: Generated audio data

[0410] Step 13:

[0411] The terminal plays the generated audio data to the user. Specifically, it plays the audio file in a streaming format and lets the user listen to it.

[0412] Input: Generated audio data

[0413] Output: The audio played to the user

[0414] The above is the specific processing flow of this system.

[0415] (Application example 2)

[0416] 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."

[0417] Conventional food delivery services have faced issues with server resource shortages during sudden user increases, resulting in service delays and outages. Furthermore, customer support has been handled manually, resulting in issues of delayed responses and inconsistent quality. Furthermore, personalized responses based on user sentiment are required, but the means to achieve this have been limited. Even with voice support, only text-based support was available, limiting the user experience.

[0418] 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 automatically adjusting resources in real time according to the number of cloud server users, means for automating user chat services, customer support, and other responses using a generative artificial intelligence model, means for automatically generating in-game content and updates using a generative artificial intelligence model, means for using an emotion engine to recognize user emotions and adjust responses, and means for generating and playing voice data using a generative artificial intelligence model in response to user operations as a voice response. This makes it possible for food delivery services to provide stable service even to a rapidly increasing number of users and to realize interactive and personalized responses that correspond to user emotions.

[0419] A "cloud server" is a collection of server resources provided over the Internet, and is a remote computing environment for storing and processing data.

[0420] "Automatic resource adjustment" is a function that dynamically changes the allocation of computer resources such as servers and storage according to current usage.

[0421] A "generative artificial intelligence model" is an AI model that has the ability to learn implicit rules and patterns and generate new data such as text, images, and audio based on given input.

[0422] "Chat service" refers to a means of communication for exchanging messages in real time, and is intended to enable users to exchange information with each other and between users and support staff.

[0423] "Customer support" refers to services that assist customers in resolving inquiries and problems.

[0424] "In-game content" refers to elements such as stages, characters, items, and dialogue that are provided for the enjoyment of game players.

[0425] An "emotion engine" is a system that determines emotions from a user's voice or text and adjusts the response accordingly.

[0426] "Voice support" is a function that enables interaction using voice data generated based on user operations.

[0427] An "instance" is a unit of computer resources that runs as a virtual machine or container in a cloud environment.

[0428] "Scaling" refers to the act of adding or removing resources to increase or decrease the performance or capacity of a system.

[0429] This invention is a system that provides an interactive and personalized experience in a food delivery service by automatically adjusting cloud server resources, automating customer support using a generative artificial intelligence model, and improving user response using an emotion engine.

[0430] Cloud Server Management

[0431] server

[0432] The server measures the current number of active users at regular intervals. For example, it measures the number of active users every hour and adjusts resources based on that number. For example, if the number of active users decreases at night, unnecessary instances are automatically deactivated to reduce costs.

[0433] The server calculates the amount of resources needed based on the number of active users. For example, if the number of active users increases, the server will launch new instances and instantly add the required CPU, memory, and storage.

[0434] Leveraging generative AI models

[0435] Terminal

[0436] The device receives requests from users and sends them to the generative AI model. For example, when a user sends a message to customer support, the content is forwarded to the generative AI model. The generative AI model then generates a response appropriate to the inquiry and sends it back to the device.

[0437] The device displays the generated response to the user. For example, the device displays the response from the generative AI model in a chat window, providing the user with a quick reply.

[0438] Utilizing the Emotion Engine

[0439] Terminal

[0440] The device recognizes emotions from the user's voice and text. For example, the device analyzes messages typed by the user in a chat interface or the content of voice calls to detect the user's emotions.

[0441] server

[0442] The server adjusts the content of responses from chat services and customer support based on the recognized emotions. For example, if the emotion engine detects "anger" or "sadness," it changes the response to be more polite and comforting. Conversely, if it detects "joy" or "excitement," it adjusts the response to a friendlier tone.

[0443] Voice support

[0444] Terminal

[0445] The device generates voice data based on the generative AI model in response to user actions. For example, if a user types "Please tell me the status of my order," the device sends the text to the generative AI model, which then converts the resulting text into speech.

[0446] server

[0447] The server generates voice data using a generative AI model. For example, the server uses a speech synthesis model to generate an audio file based on the text sent to it and sends it back to the device.

[0448] Terminal

[0449] The terminal plays the generated audio data to the user. In a specific example, the terminal plays the generated audio data so that the user can hear it.

[0450] Examples of concrete examples and prompts

[0451] As a concrete example, if a user sends the message "Please tell me the status of my order," the system will act as follows:

[0452] 1. The number of active users is checked and the required resources are adjusted.

[0453] 2. The emotion "excitement" is recognized from the user's text, and a positive response is generated: "Great! How can I assist you today?"

[0454] 3. The generated text is converted into speech and played back to the user.

[0455] Example prompt sentence:

[0456] User: "What's the status of my order?"

[0457] Sentiment analysis result: Positive

[0458] Response: "Great! How can I assist you today?"

[0459] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0460] Step 1:

[0461] The server measures the current number of active users at regular intervals. The measured number of active users becomes input data. Based on this data, the server adjusts resources. For example, if the number of active users decreases at night, it automatically deactivates unnecessary instances to reduce costs.

[0462] Step 2:

[0463] The server calculates the required resources based on the number of active users it measures. This calculation results in output data. If the number of active users increases, the server launches new instances, providing additional CPU, memory, and storage immediately.

[0464] Step 3:

[0465] The device receives requests from users and sends the contents of those requests to the generative AI model. The contents of those requests become input data. Specifically, when a user sends a message to customer support, the contents of that message are forwarded to the generative AI model.

[0466] Step 4:

[0467] The generative AI model generates an appropriate response based on the received request. The generated response becomes the output data. This response is sent back to the device. For example, in response to a request such as "Please tell me the status of my order," the generative AI model generates a response such as "Sorry for the wait. Your order is currently being delivered."

[0468] Step 5:

[0469] The device receives the response from the generative AI model and displays it to the user. This response message serves as input data. For example, the device displays this message in a chat window to provide the user with a prompt reply.

[0470] Step 6:

[0471] The device recognizes emotions from the user's voice and text. Input data is messages typed by the user in the chat interface or the contents of voice calls. The device sends this to the emotion engine, which analyzes the user's emotions.

[0472] Step 7:

[0473] The emotion engine analyzes input data and generates output data based on the recognized emotions. The server receives the results and adjusts the chat service or customer support response. For example, if the emotion engine detects "anger," it can change the response to be more polite and comforting.

[0474] Step 8:

[0475] The device generates voice data based on the generative AI model in response to user actions. The text sent by the user is the input data. This text is sent to the generative AI model to generate voice data.

[0476] Step 9:

[0477] The server generates voice data using a generative AI model. The text data is the input data, and the voice file is the output data. The generated voice file is sent back to the device.

[0478] Step 10:

[0479] The terminal plays the generated voice data to the user. The voice data is input data, and the voice is played back so that the user can hear it. As a specific example, in response to a user request such as "Please tell me the status of my order," the voice response played back is "Sorry to keep you waiting. Your order is currently being delivered."

[0480] 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.

[0481] 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.

[0482] 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.

[0483] [Second embodiment]

[0484] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0485] 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.

[0486] 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).

[0487] 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.

[0488] 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.

[0489] 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).

[0490] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0491] 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.

[0492] 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.

[0493] 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.

[0494] 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.

[0495] 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."

[0496] The system of the present invention includes automatic resource adjustment according to the number of cloud server users, automated chat service and customer support using generative artificial intelligence models, and means for automatically generating in-game content and updates in order to avoid the termination of online game services and to operate them automatically at low cost.

[0497] The operation of the system of the present invention will be specifically described below.

[0498] Cloud Server Management

[0499] server

[0500] The server measures the current number of active users at regular intervals.

[0501] Example: The server measures the number of active users every hour and adjusts resources based on that number. For example, if the number of active users decreases at night, unnecessary instances are automatically released to reduce costs.

[0502] The server calculates the amount of resources needed based on the number of active users.

[0503] Example: If the number of active users increases, the server will launch new instances and instantly add the required CPU, memory, and storage.

[0504] Leveraging generative AI models

[0505] Terminal

[0506] The device receives requests from users and sends them to the AI ​​model.

[0507] Example: When a user sends a message to customer support, the device forwards the message to the AI ​​model, which then generates a response appropriate to the inquiry and sends it back to the device.

[0508] The terminal displays the generated response to the user.

[0509] Example: The device displays responses from the AI ​​model in a chat window, providing the user with a quick response.

[0510] Automatic updates

[0511] server

[0512] The server periodically sends game data to the AI ​​model.

[0513] Example: Every weekend, the server collects game data and pushes it to an AI model, which uses this data to generate new stages and character dialogue.

[0514] The server reflects the generated content in the game.

[0515] Example: The server integrates new content returned by the AI ​​model into the existing game data and automatically applies updates.

[0516] Voice support

[0517] Terminal

[0518] The device will activate the AI ​​voice bot when triggered by user action.

[0519] Example: When a user interacts with a specific character, the device detects when the "speak" button is pressed and sends text to an AI voice bot.

[0520] The terminal provides the generated voice data to the user.

[0521] Example: The device receives audio files from an AI voice bot and plays them in the game, allowing users to enjoy natural voice interaction.

[0522] Based on the above process, all operational processes, including cloud server operation, user support, content generation, and voice response, are automated using AI, enabling continuous operation of online games, which also significantly reduces operational costs and eases the burden on human resources.

[0523] The processing flow will be explained below.

[0524] Cloud Server Management

[0525] Step 1: Measure active users

[0526] The server measures the current number of active users at regular intervals.

[0527] Specifically, the server checks the sessions of all users connected to each game instance and tally the total number of active sessions.

[0528] Step 2: Calculate resources

[0529] The server calculates the amount of resources needed based on the number of active users.

[0530] For example, the server dynamically calculates new amounts of CPU, memory, and storage when the number of active users exceeds a certain threshold.

[0531] Step 3: Performing scaling

[0532] The server uses auto-scaling to adjust resources.

[0533] The servers automatically launch new instances to accommodate increased user load, and release unneeded instances to reduce costs when the number of users decreases.

[0534] Leveraging generative AI models

[0535] Step 1: Get the user request

[0536] The terminal receives a request from the user.

[0537] The device collects user messages using an in-game chat interface and customer support.

[0538] Step 2: Send to AI model

[0539] The device sends the user request to the appropriate AI model.

[0540] The device sends the message received from the user in text format to the API endpoint of the AI ​​model.

[0541] Step 3: Generation by AI model

[0542] The server receives the response generated by the AI ​​model.

[0543] The server receives and stores the response messages sent by the AI ​​model.

[0544] Step 4: Deliver to users

[0545] The terminal returns the generated response to the user.

[0546] The device displays the response from the AI ​​model on the chat interface and provides it to the user instantly.

[0547] Automatic updates

[0548] Step 1: Collect data

[0549] The server periodically collects the latest game data.

[0550] The server collects game setting files, character data, stage information, and other information all at once.

[0551] Step 2: Prepare to send data

[0552] The server prepares to send the collected game data to the AI ​​model.

[0553] The server formats various data and prepares it in a form that can be processed by the AI ​​model.

[0554] Step 3: Generation by AI model

[0555] The server sends game data to the AI ​​model and requests it to generate new content.

[0556] The AI ​​model generates new stages and character lines based on the data sent and sends them back to the server.

[0557] Step 4: Reflecting content

[0558] The server reflects the generated new content in the game.

[0559] The server incorporates the data returned from the AI ​​model into the game data and provides it to the user as new content.

[0560] Voice support

[0561] Step 1: Detecting trigger words

[0562] The device detects whether the user has used a specific trigger word.

[0563] The device monitors messages entered by users in the chat interface and detects defined trigger words.

[0564] Step 2: Launch your AI voicebot

[0565] If the device detects a trigger word, it will activate an AI voice bot.

[0566] Based on the detected trigger word, the device prepares to send text to the speech synthesis API.

[0567] Step 3: Speech generation

[0568] The server generates voice data using an AI voice bot.

[0569] The server inputs the transmitted text data into a speech synthesis model and generates an audio file.

[0570] Step 4: Streaming audio data

[0571] The terminal provides the generated voice data to the user.

[0572] The terminal plays back the generated audio data and lets the user hear it.

[0573] Example 1

[0574] 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."

[0575] When operating an online game, it is important to avoid service termination and ensure continuous operation at low cost. However, managing resources to respond to fluctuations in user numbers, providing user support, automatically generating content, and providing voice dialogue manually is extremely labor-intensive and increases operational costs. For this reason, an efficient, automated system is needed.

[0576] 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.

[0577] In this invention, the server includes means for automatically adjusting resources in real time according to the number of cloud server users, means for automating user chat services and customer support using a generative artificial intelligence model, means for automatically generating in-game content and updates using the generative artificial intelligence model, and means for providing voice interaction functionality using the generative artificial intelligence model, thereby enabling efficient resource management, automated user support, continuous content updates, and the provision of natural voice interaction.

[0578] A "cloud server" is a server system that provides multiple distributed computing resources accessible via the Internet.

[0579] "Automatic resource adjustment" is the process of dynamically changing the allocation of computing resources (CPU, memory, storage, etc.) depending on the number of users and load.

[0580] A "generative artificial intelligence model" is a machine learning algorithm and its implementation that can generate new information and content based on given data and conditions.

[0581] "User Chat Service" is a collective term for the interface that allows users to have text-based interactions with the system and the system that operates behind the interface.

[0582] "Customer support" refers to a service that responds to inquiries and problems from users and provides solutions.

[0583] "In-game content" means all elements (stages, characters, items, etc.) that users can operate, view, or use within an online game.

[0584] "Voice interaction functions" refer to the functions of a system that interacts based on a user's voice input and the voice output that it generates.

[0585] "Real-time" means that the delay between data generation, processing, and notification is close to zero.

[0586] "Scaling" is the process of increasing or decreasing system resources according to certain conditions or criteria.

[0587] A "server instance" is an individual virtual machine or container running on a cloud service.

[0588] The system of the present invention aims to prevent service terminations of online games and automate their operation at low cost. The system includes automatic resource adjustment based on the number of cloud server users, automated chat service and customer support using generative AI models, and automatic generation of in-game content and updates. Furthermore, it provides voice interaction functionality to create a more interactive user experience.

[0589] Cloud Server Management

[0590] The server measures the current number of active users at regular intervals. For example, the server obtains the number of active users from the game's login data at 00 minutes past the hour. This measurement data is recorded in a database and used in the next step. Based on the obtained number of active users, the server calculates the required amount of resources. If one instance is required for 200 users, and the current number of active users is 400, it calculates that a total of two instances are required. Based on this calculation, the server automatically adds or releases the necessary resources. For example, if the number of active users drops to 100 overnight, it will run only one instance and release the unnecessary instances.

[0591] Leveraging generative AI models

[0592] The device receives requests from the user and sends them to the generative AI model. For example, when a user sends a message to customer support, the device forwards the content to the AI ​​model. An example of a prompt sentence is, "User inquiry: I can't log in to my account. Please suggest a solution." The AI ​​model generates a response appropriate to the inquiry and sends it back to the device. The device then displays the generated response to the user. For example, the response from the AI ​​model can be displayed in a chat window, allowing the user to receive a prompt reply.

[0593] Automatic updates

[0594] The server periodically sends game data to the generative AI model. For example, the server collects game data every weekend and pushes it to the AI ​​model. A specific example of a prompt might be, "Generate new stages and character dialogue based on last week's data." The AI ​​model then generates new content (stages and character dialogue) based on this data. The generated new content is integrated with the existing game data and automatically reflected in the game.

[0595] Voice support

[0596] The device triggers the AI ​​voice bot with user actions. For example, when a user interacts with a specific character, it detects that the "Speak" button has been pressed and sends text to the AI ​​voice bot. An example of a prompt to send is "The user is interacting with Character A. Please generate a greeting line in voice." The device then plays back the voice data received from the AI ​​voice bot. This allows the user to enjoy a conversation in a natural voice.

[0597] The above process enables efficient resource management of cloud servers, automated user support, automatic game updates, and voice interaction, ensuring continuous operation of online games, while significantly reducing operational costs and the burden on personnel resources.

[0598] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0599] Cloud Server Management

[0600] Step 1:

[0601] The server measures the current number of active users at regular intervals. Specifically, the server obtains the number of active users from the game's login data at 00 minutes past the hour. The information is recorded in a database. The input is the login data, and the output is the number of active users.

[0602] Step 2:

[0603] The server calculates the required amount of resources based on the measured number of active users. For example, if it calculates that one instance is required for 200 users, and the number of active users is 400, two instances are required. This calculation result is sent to the resource management system. The input is the number of active users, and the output is the required amount of resources.

[0604] Step 3:

[0605] The server automatically adds or releases resources based on the calculation results. For example, if the number of active users drops to 100 overnight, it will run only one instance and release unnecessary instances. The input is the amount of resources required, and the output is the adjusted number of instances.

[0606] Leveraging generative AI models

[0607] Step 1:

[0608] The terminal receives requests from the user, such as when a user sends a message to customer support. The input is the user message, and the output is the converted prompt.

[0609] Step 2:

[0610] The device sends the received message to the generative AI model. It uses a REST API to send a request to the AI ​​model, for example, using a prompt such as "User inquiry: I can't log in to my account. Please suggest a solution." The input is the converted prompt, and the output is the response from the AI ​​model.

[0611] Step 3:

[0612] The device displays the generated response to the user. For example, it displays the response from the AI ​​model in a chat window, providing a quick reply to the user. The input is the response from the AI ​​model, and the output is the response displayed to the user.

[0613] Automatic updates

[0614] Step 1:

[0615] The server periodically collects game data, for example, summarizing game activity data every weekend. The input is the game activity data, and the output is the collected data.

[0616] Step 2:

[0617] The server sends the collected data to the generative AI model via an API, using a prompt such as, "Generate a new stage and character dialogue based on last week's data." The input is the collected data and the prompt, and the output is the generated new content.

[0618] Step 3:

[0619] The server reflects the generated new content in the game. It integrates the generated stage data and character dialogue into the existing game database and automatically updates the online game. The input is the generated new content, and the output is the updated game data.

[0620] Voice support

[0621] Step 1:

[0622] The device activates the AI ​​voice bot as a trigger of user actions. For example, when a user interacts with a specific character, it detects when the "Speak" button is pressed. The input is the user's actions, and the output is the transmitted text.

[0623] Step 2:

[0624] The device sends the detected text to an AI voice bot. The text is sent to a generative AI model, and a prompt such as "The user will interact with Character A. Please generate a greeting line in voice." The input is the text to be sent and the prompt, and the output is the generated voice data.

[0625] Step 3:

[0626] The device receives and plays back the voice data generated by the AI ​​voice bot. The voice file is then loaded by the player and played in the game. The input is the generated voice data, and the output is the voice that is played.

[0627] (Application example 1)

[0628] 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."

[0629] In today's online services and e-commerce platforms, efficient management of server resources, user support, and content updates are chronically draining human resources. Furthermore, providing voice support and quickly generating new product descriptions and reviews to improve the user experience are also challenges. Systems that can efficiently automate these tasks are needed.

[0630] 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.

[0631] In this invention, the server includes means for automatically adjusting resources in real time according to the number of cloud server users, means for automating user chat services and customer support using a generative artificial intelligence model, means for automatically generating online content and updates using the generative artificial intelligence model, and means for generating voice data and providing voice dialogue using the generative artificial intelligence model, thereby enabling efficient operation of the server, provision of high-quality user services, and automated content updates.

[0632] A "cloud server" is a server with computing resources and storage provided via the Internet.

[0633] "Real-time" refers to the instantaneous processing of data and information, meaning that there is very little delay.

[0634] "Automatic resource adjustment" refers to dynamically increasing or decreasing resources such as CPU, memory, and storage depending on server usage.

[0635] A "generative artificial intelligence model" is an artificial intelligence algorithm that is trained to generate content such as text, audio, or images.

[0636] "Chat service" refers to a service that allows real-time communication via text messages.

[0637] "Customer support" refers to support services provided to resolve inquiries and problems regarding products and services.

[0638] "Online content" refers to various media content, such as text, images, audio, and video, that is distributed via the Internet.

[0639] "Auto-generation" refers to content being created anew by a system or algorithm without human intervention.

[0640] "Speech data" refers to digital recordings of speech, typically used for speech recognition and synthesis.

[0641] "Voice interaction" refers to an interface in which the user interacts with the system using voice.

[0642] A "product description" is text or media content that provides detailed explanations of a product's features, functions, specifications, etc.

[0643] A "review" is content that describes a user's evaluation or opinion of a product or service.

[0644] "Recommendation" refers to a system or function that recommends products or services based on a user's preferences and behavioral history.

[0645] System Overview

[0646] This invention relates to a system that efficiently manages cloud server resources and utilizes generative artificial intelligence models to provide chat services, customer support, voice dialogue, and automatic content generation for users. Specific embodiments of this system are described below.

[0647] Hardware and Software Used

[0648] Hardware:

[0649] Smartphone

[0650] Cloud infrastructure (e.g. AWS, GCP)

[0651] software:

[0652] Programming languages: Python, Java (server side), Swift / Kotlin (mobile apps)

[0653] Frameworks: TensorFlow (generative AI model), Flask / Django (server-side API)

[0654] Libraries: NLTK, Spacy (natural language processing)

[0655] API: Google Cloud Speech-to-Text, Google Cloud Text-to-Speech

[0656] Processing Overview

[0657] 1. Cloud server resource management

[0658] The server measures the number of people using the cloud server at regular intervals and calculates the required amount of resources based on the data. Before resources become overloaded, it automatically launches new instances and adds the necessary CPU, memory, and storage. It also reduces costs by automatically releasing unnecessary instances when usage decreases.

[0659] 2. AI chat support

[0660] When a user sends a message to customer support from their device, the message is forwarded to the AI ​​model, which generates a response appropriate to the inquiry and sends it back to the device. This response is then displayed in the chat window, allowing the user to receive a prompt reply.

[0661] Example prompt sentence:

[0662] User: I want to know more about this product

[0663] AI model response: We will provide you with detailed product information. The main features of this product are...

[0664] 3. Automated content generation

[0665] The server periodically sends new product data to the AI ​​model and receives the generated product descriptions and recommendations. The generated content is automatically updated in the device application, ensuring that the latest information is always provided.

[0666] Example prompt sentence:

[0667] Generate a testimonial for your new smartphone

[0668] AI model response:

[0669] This latest smartphone is packed with innovative features and beautiful design, most notably...

[0670] 4. Voice support

[0671] When a user taps the microphone icon to start voice input, the recorded voice is converted into text by Google Cloud Speech-to-Text. The generated text is sent to an AI model, which returns an appropriate response. Google Cloud Text-to-Speech then generates audio data and plays it back on the device, allowing users to enjoy natural voice interaction.

[0672] The combination of these measures enables efficient operation of cloud servers, fast customer support, automated content generation and voice interaction, significantly reducing the operating costs of online services and providing a high-quality user experience.

[0673] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0674] Step 1:

[0675] The server measures the number of people using the cloud server at regular intervals. The input is the current number of active users, and the output is the calculated amount of resources required. This measurement is based on server log data and real-time access data. Specifically, the current number of active users is obtained by analyzing the server's access log.

[0676] Step 2:

[0677] The server calculates the required amount of resources based on the number of active users measured, and automatically adjusts the server instances. The input is the number of active users data output from Step 1, and the output is information about the instances to be newly added or released. Specifically, AWS's Auto Scaling function is used to dynamically add or reduce the required CPU and memory.

[0678] Step 3:

[0679] The device receives customer support messages from users and sends them to the AI ​​model. The input is the message entered by the user into the device, and the output is a prompt for the generative artificial intelligence model. Specifically, when the user enters a message and presses the send button, the message is transferred to the AI ​​model via the server.

[0680] Step 4:

[0681] The server receives the response generated by the AI ​​model and sends it to the terminal. The input is the response data generated by the AI ​​model, and the output is data in the format displayed in the chat window. Specifically, the AI ​​model generates a response appropriate to the inquiry content and sends it to the terminal in JSON format.

[0682] Step 5:

[0683] The server periodically sends new product data to the AI ​​model and receives the generated product descriptions and recommendations. The input is product attribute data, and the output is the generated product descriptions and recommendation lists. Specifically, information from the product database is periodically pushed to the AI ​​model to generate new descriptions and recommendation lists.

[0684] Step 6:

[0685] The device displays product descriptions and recommendations received from the server. The input is the generated data transferred from the server, and the output is the content displayed on the device's UI. Specifically, the generated descriptions and recommended item lists are rendered in the display area within the app.

[0686] Step 7:

[0687] The user starts voice input, and the device converts the recorded voice into text using the Google Cloud Speech-to-Text API. The input is the user's voice data, and the output is text data. Specifically, voice recording begins when the microphone button is pressed, and the recorded data is sent to the cloud API and converted into text.

[0688] Step 8:

[0689] The user's speech, converted into text, is sent to an AI model to generate an appropriate voice response. The input is text data, and the output is the response text data. Specifically, the converted text is sent to the AI ​​model as a prompt, and an appropriate reply is generated.

[0690] Step 9:

[0691] The server uses the Google Cloud Text-to-Speech API to convert the generated text data into audio data and send it to the device. The input is the text data of the response content, and the output is audio data. Specifically, the generated response text is sent to the cloud API, which generates an audio file and sends it to the device.

[0692] Step 10:

[0693] The device plays back the received voice data and provides it to the user. The input is the voice data sent from the server, and the output is the user's auditory feedback. Specifically, the received voice file is provided to the user using the playback function, realizing natural voice interaction.

[0694] 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.

[0695] The system of the present invention provides a more interactive and personalized experience by combining automatic resource adjustment according to the number of cloud server users, automated user support using a generative artificial intelligence model, and automatic generation of in-game content with an emotion engine that recognizes user emotions.

[0696] The operation process of the system of the present invention will be specifically described below.

[0697] Cloud Server Management

[0698] server

[0699] The server measures the current number of active users at regular intervals.

[0700] Example: The server measures the number of active users every hour and adjusts resources based on that number. For example, if the number of active users decreases at night, unnecessary instances are automatically released to reduce costs.

[0701] The server calculates the amount of resources needed based on the number of active users.

[0702] Example: If the number of active users increases, the server will launch new instances and instantly add the required CPU, memory, and storage.

[0703] Leveraging generative AI models

[0704] Terminal

[0705] The device receives requests from users and sends them to the AI ​​model.

[0706] Example: When a user sends a message to customer support, the device forwards the message to the AI ​​model, which then generates a response appropriate to the inquiry and sends it back to the device.

[0707] The terminal displays the generated response to the user.

[0708] Example: The device displays responses from the AI ​​model in a chat window, providing the user with a quick response.

[0709] Automatic updates

[0710] server

[0711] The server periodically sends game data to the AI ​​model.

[0712] Example: Every weekend, the server collects game data and pushes it to an AI model, which uses this data to generate new stages and character dialogue.

[0713] The server reflects the generated content in the game.

[0714] Example: The server integrates new content returned by the AI ​​model into the existing game data and automatically applies updates.

[0715] Utilizing the Emotion Engine

[0716] Terminal

[0717] The device recognizes emotions from the user's voice and text.

[0718] Example: The device analyzes messages typed by the user in a chat interface and the content of voice calls to detect the user's emotions.

[0719] server

[0720] The server then tailors responses for chat services and customer support based on the perceived emotion.

[0721] For example: If the emotion engine detects "anger" or "sadness," the server may change the response to be more polite and comforting. Conversely, if it detects "joy" or "excitement," the server may adjust the response to a friendlier tone.

[0722] Terminal

[0723] The device changes the movements and expressions of the in-game characters in real time according to the user's emotions.

[0724] Example: If the device's emotion engine recognizes that the user is sad, it will change the in-game character to make comforting gestures and say comforting lines.

[0725] Voice support

[0726] Terminal

[0727] The device will activate the AI ​​voice bot when triggered by user action.

[0728] Example: When a user interacts with a specific character, the device detects when the "speak" button is pressed and sends text to an AI voice bot.

[0729] server

[0730] The server generates voice data using an AI voice bot.

[0731] Example: The server uses a speech synthesis model to generate an audio file based on the text sent and sends it back to the device.

[0732] Terminal

[0733] The terminal plays the generated audio data to the user.

[0734] Example: The device plays the generated audio data so that the user can hear it.

[0735] As a result, the system of the present invention achieves effective resource management of cloud servers, automated user response through generative AI models, and interactive and emotionally responsive experiences through an emotion engine, which significantly reduces operational costs and alleviates the burden on human resources.

[0736] The processing flow will be explained below.

[0737] Cloud Server Management

[0738] Step 1: Measure active users

[0739] The server measures the current number of active users at regular intervals.

[0740] Example: The server checks and aggregates the session information of active users every hour, thereby determining the real-time number of users.

[0741] Step 2: Calculate resources

[0742] The server calculates the amount of resources needed based on the number of active users.

[0743] Example: A server calculates how many additional resources (CPU, memory, storage) to add when the number of active users exceeds a certain threshold (e.g., 500 users).

[0744] Step 3: Performing scaling

[0745] The server uses auto-scaling to adjust resources.

[0746] Example: Servers launch new instances to add necessary resources as the number of users increases, while unnecessary instances are stopped to reduce costs when the number of users decreases.

[0747] Leveraging generative AI models

[0748] Step 1: Get the user request

[0749] The terminal receives a request from the user.

[0750] Example: When a user contacts customer support, the device receives the message.

[0751] Step 2: Send to AI model

[0752] The device sends the user request to the AI ​​model.

[0753] Example: The device sends the received message to the API endpoint of the AI ​​model, initiating processing to generate an appropriate response.

[0754] Step 3: Generation by AI model

[0755] The server receives the response generated by the AI ​​model.

[0756] Example: The server receives and stores the response message generated by the AI ​​model.

[0757] Step 4: Deliver to users

[0758] The terminal returns the generated response to the user.

[0759] Example: The device displays a reply message from the AI ​​model on the chat interface and provides it to the user.

[0760] Automatic updates

[0761] Step 1: Collect data

[0762] The server periodically collects the latest game data.

[0763] Example: Every weekend, the server collects game configuration files, character data, stage information, etc.

[0764] Step 2: Prepare data for transmission

[0765] The server prepares to send the collected game data to the AI ​​model.

[0766] Example: The server formats the data in a way that is easy for the AI ​​model to parse.

[0767] Step 3: Generation by AI model

[0768] The server sends game data to the AI ​​model and requests it to generate new content.

[0769] Example: An AI model generates new levels and character dialogue and sends it back to the server.

[0770] Step 4: Reflecting content

[0771] The server reflects the generated new content in the game.

[0772] Example: The server integrates new content returned by the AI ​​model into the existing game data and updates it so that the new content is immediately available to the user.

[0773] Utilizing the Emotion Engine

[0774] Step 1: Collecting emotion data

[0775] The device recognizes emotions from the user's voice and text.

[0776] Example: The device analyzes messages entered by the user in a chat interface to detect the user's emotions (happiness, sadness, anger, excitement).

[0777] Step 2: Generate an emotion-based response

[0778] The server adjusts the response content based on the user's emotions recognized by the emotion engine.

[0779] Example: If the server detects "anger," it might make its response polite and comforting, but if it detects "happiness," it might use a friendlier tone.

[0780] Step 3: Generate emotion-based content

[0781] The server dynamically generates content within the game according to the user's emotions.

[0782] Example: If the user is sad, an in-game character can automatically generate comforting lines and actions.

[0783] Voice support

[0784] Step 1: Detecting trigger words

[0785] The device detects whether the user has used a specific trigger word.

[0786] Example: The device monitors and detects trigger words such as "talk" in a chat interface.

[0787] Step 2: Launch your AI voicebot

[0788] The device will activate an AI voice bot if it detects a trigger word.

[0789] Example: The device sends the detected trigger word to an AI voice bot to start the voice synthesis process.

[0790] Step 3: Speech generation

[0791] The server generates voice data using an AI voice bot.

[0792] Example: The server inputs the submitted text data into a speech synthesis model and saves the generated audio file.

[0793] Step 4: Streaming audio data

[0794] The terminal provides the generated voice data to the user.

[0795] Example: The device plays the generated audio data so that the user can hear it.

[0796] Example 2

[0797] 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."

[0798] Conventional cloud server systems face challenges in efficient resource management, making it difficult to flexibly adjust and respond to user usage and emotions. They also lack the ability to automatically generate in-game content and provide interactive experiences based on user emotions. This has resulted in high system operating costs and limited user experience.

[0799] 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.

[0800] In this invention, the server includes means for automatically adjusting resources in real time according to the number of cloud server users, means for automating user chat services and customer support responses using a generative artificial intelligence model, means for automatically generating in-game content and updates using a generative artificial intelligence model, means for recognizing emotions from user voice and text using an emotion recognition engine and adjusting response content based on the emotions, and means for converting text into voice data based on user operations using a speech synthesis engine and playing the voice data back to the user. This enables efficient resource management and cost reduction, and makes it possible to provide users with a more interactive and personalized experience.

[0801] A "cloud server" is a computer server that provides remote computer resources accessible over the Internet.

[0802] "Real-time" is a term that refers to events and data processing occurring as soon as they occur.

[0803] "Resources" are the hardware and software capabilities that a computer system provides, such as computation, memory, and storage.

[0804] A "generative artificial intelligence model" is an algorithm and machine learning model that automatically generates data and information based on instructions given by humans.

[0805] "Chat service" is a communication service that allows sending and receiving text messages in real time.

[0806] "Customer Support" means services that provide assistance to customers with questions or problems.

[0807] An "emotion recognition engine" is an algorithm and system for analyzing and recognizing emotions from human voice and text.

[0808] A "speech synthesis engine" is a technology and program for converting text data into voice data.

[0809] "Scaling" is the process of increasing or decreasing a system's processing power or resources to adapt to load or demand.

[0810] An "instance" is an individual execution environment for virtual machines and computer resources that run on a cloud server.

[0811] The present invention is a system that utilizes a cloud server to efficiently manage resources based on the user's usage status and emotions, and combines a generative artificial intelligence model and an emotion recognition engine to provide an advanced user experience.

[0812] First, the server uses the cloud provider's monitoring tools (for example, a general cloud management service) to measure the current number of active users at regular intervals. Based on the measured number of active users, the server calculates the amount of resources required and automatically adjusts the resources. Specifically, this involves adding or removing virtual machine instances using a scaling policy.

[0813] Next, the device receives the user's request and sends it to a generative artificial intelligence model (e.g., a general-purpose generative AI model). When the user sends a message to customer support, the content is sent to the generative AI model, which generates an appropriate response. For example, if the user asks, "I'd like to return an item. What should I do?", the generative AI model will generate a response such as, "We will inform you of the return procedure. First, please fill out the return form."

[0814] Furthermore, the server periodically collects the latest game data and sends it to the generative AI model, which then generates new stages and character dialogue and integrates them with the existing game data, updating the game database and automatically distributing the updates to the server.

[0815] The device analyzes the user's voice and text and recognizes the user's emotions using an emotion recognition engine (e.g., a general emotion analysis service). This emotion information is sent to the server and used to adjust the response content and the in-game character's movements and facial expressions in real time. For example, if the user types "Today was a tough day," the emotion recognition engine recognizes this as "sadness," and the in-game character will say encouraging words like "Cheer up!"

[0816] Furthermore, the device activates a speech synthesis engine in response to a user operation, converts the text into voice data, and plays it back to the user. For example, when the user presses the "speak" button, the text is sent to the speech synthesis engine, and the generated voice data is played back.

[0817] This allows the system of the present invention to achieve efficient resource management, reduce costs, and provide users with an interactive and personalized experience.

[0818] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0819] Step 1:

[0820] The server uses the cloud provider's monitoring tool to measure the current number of active users at regular intervals. Specifically, it periodically retrieves metric data generated by the monitoring tool and analyzes the data with a Python script.

[0821] Input: Metric data from cloud provider monitoring tools

[0822] Output: Analysis result of current number of active users

[0823] Step 2:

[0824] The server calculates the required amount of resources based on the number of active users measured, and automatically adds or removes virtual machine instances using a scaling policy, specifically using an auto-scaling function such as AWS Lambda.

[0825] Input: Number of active users

[0826] Output: Instances added or removed due to resource throttling

[0827] Step 3:

[0828] The user sends a message to customer support through the device, which receives the user's request and sends it to the generative AI model.

[0829] Input: Customer support message from the user

[0830] Output: The request sent to the generative AI model

[0831] Step 4:

[0832] The generative AI model generates a response appropriate to the user's request and returns the response to the device. Specifically, the generative AI model uses natural language processing to generate text appropriate to the inquiry.

[0833] Input: Customer Support Request

[0834] Output: Generated customer support response text

[0835] Step 5:

[0836] The device displays the response returned by the generative AI model to the user, specifically, by displaying the generated response in a chat window.

[0837] Input: Response text from the generative AI model

[0838] Output: Response displayed in the chat window

[0839] Step 6:

[0840] The server periodically collects the latest game data and sends it to the generative AI model, which then converts the collected game data into JSON format and sends it to the AI ​​model.

[0841] Input: Latest game data

[0842] Output: Game data sent to the AI ​​model

[0843] Step 7:

[0844] The generative AI model generates new game content (e.g., stages and character dialogue) and sends that content back to the server.

[0845] Input: Game data

[0846] Output: Generated game content

[0847] Step 8:

[0848] The server integrates the generated new game content into the existing game database and automatically updates the game data.

[0849] Input: Generated game content

[0850] Output: Updated game database

[0851] Step 9:

[0852] The device sends the user's voice and text to an emotion recognition engine to analyze the user's emotions. Specifically, the device sends the voice and text to an emotion analysis service to obtain emotional information.

[0853] Input: User voice or text

[0854] Output: Parsed emotion information

[0855] Step 10:

[0856] The server adjusts the response based on the analyzed user's emotions. For example, if the emotion recognition engine detects "sadness," it changes the response to something comforting.

[0857] Input: Parsed emotion information

[0858] Output: Adjusted response content

[0859] Step 11:

[0860] The user interacts with the in-game character through the device, which then changes the character's behavior and facial expressions in real time based on the user's emotional information. Specifically, the device controls the character's behavior using the game engine's API.

[0861] Input: User's emotional information

[0862] Output: Modified character movements and expressions

[0863] Step 12:

[0864] The device activates a speech synthesis engine in response to user operations and converts text into voice data. Specifically, when the user presses the "speak" button, the device sends the text to the speech synthesis engine.

[0865] Input: User text input

[0866] Output: Generated audio data

[0867] Step 13:

[0868] The terminal plays the generated audio data to the user. Specifically, it plays the audio file in a streaming format and lets the user listen to it.

[0869] Input: Generated audio data

[0870] Output: The audio played to the user

[0871] The above is the specific processing flow of this system.

[0872] (Application example 2)

[0873] 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."

[0874] Conventional food delivery services have faced issues with server resource shortages during sudden user increases, resulting in service delays and outages. Furthermore, customer support has been handled manually, resulting in issues of delayed responses and inconsistent quality. Furthermore, personalized responses based on user sentiment are required, but the means to achieve this have been limited. Even with voice support, only text-based support was available, limiting the user experience.

[0875] 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 automatically adjusting resources in real time according to the number of cloud server users, means for automating user chat services, customer support, and other responses using a generative artificial intelligence model, means for automatically generating in-game content and updates using a generative artificial intelligence model, means for using an emotion engine to recognize user emotions and adjust responses, and means for generating and playing voice data using a generative artificial intelligence model in response to user operations as a voice response. This makes it possible for food delivery services to provide stable service even to a rapidly increasing number of users and to realize interactive and personalized responses that correspond to user emotions.

[0876] A "cloud server" is a collection of server resources provided over the Internet, and is a remote computing environment for storing and processing data.

[0877] "Automatic resource adjustment" is a function that dynamically changes the allocation of computer resources such as servers and storage according to current usage.

[0878] A "generative artificial intelligence model" is an AI model that has the ability to learn implicit rules and patterns and generate new data such as text, images, and audio based on given input.

[0879] "Chat service" refers to a means of communication for exchanging messages in real time, and is intended to enable users to exchange information with each other and between users and support staff.

[0880] "Customer support" refers to services that assist customers in resolving inquiries and problems.

[0881] "In-game content" refers to elements such as stages, characters, items, and dialogue that are provided for the enjoyment of game players.

[0882] An "emotion engine" is a system that determines emotions from a user's voice or text and adjusts the response accordingly.

[0883] "Voice support" is a function that enables interaction using voice data generated based on user operations.

[0884] An "instance" is a unit of computer resources that runs as a virtual machine or container in a cloud environment.

[0885] "Scaling" refers to the act of adding or removing resources to increase or decrease the performance or capacity of a system.

[0886] This invention is a system that provides an interactive and personalized experience in a food delivery service by automatically adjusting cloud server resources, automating customer support using a generative artificial intelligence model, and improving user response using an emotion engine.

[0887] Cloud Server Management

[0888] server

[0889] The server measures the current number of active users at regular intervals. For example, it measures the number of active users every hour and adjusts resources based on that number. For example, if the number of active users decreases at night, unnecessary instances are automatically deactivated to reduce costs.

[0890] The server calculates the amount of resources needed based on the number of active users. For example, if the number of active users increases, the server will launch new instances and instantly add the required CPU, memory, and storage.

[0891] Leveraging generative AI models

[0892] Terminal

[0893] The device receives requests from users and sends them to the generative AI model. For example, when a user sends a message to customer support, the content is forwarded to the generative AI model. The generative AI model then generates a response appropriate to the inquiry and sends it back to the device.

[0894] The device displays the generated response to the user. For example, the device displays the response from the generative AI model in a chat window, providing the user with a quick reply.

[0895] Utilizing the Emotion Engine

[0896] Terminal

[0897] The device recognizes emotions from the user's voice and text. For example, the device analyzes messages typed by the user in a chat interface or the content of voice calls to detect the user's emotions.

[0898] server

[0899] The server adjusts the content of responses from chat services and customer support based on the recognized emotions. For example, if the emotion engine detects "anger" or "sadness," it changes the response to be more polite and comforting. Conversely, if it detects "joy" or "excitement," it adjusts the response to a friendlier tone.

[0900] Voice support

[0901] Terminal

[0902] The device generates voice data based on the generative AI model in response to user actions. For example, if a user types "Please tell me the status of my order," the device sends the text to the generative AI model, which then converts the resulting text into speech.

[0903] server

[0904] The server generates voice data using a generative AI model. For example, the server uses a speech synthesis model to generate an audio file based on the text sent to it and sends it back to the device.

[0905] Terminal

[0906] The terminal plays the generated audio data to the user. In a specific example, the terminal plays the generated audio data so that the user can hear it.

[0907] Examples of concrete examples and prompts

[0908] As a concrete example, if a user sends the message "Please tell me the status of my order," the system will act as follows:

[0909] 1. The number of active users is checked and the required resources are adjusted.

[0910] 2. The emotion "excitement" is recognized from the user's text, and a positive response is generated: "Great! How can I assist you today?"

[0911] 3. The generated text is converted into speech and played back to the user.

[0912] Example prompt sentence:

[0913] User: "What's the status of my order?"

[0914] Sentiment analysis result: Positive

[0915] Response: "Great! How can I assist you today?"

[0916] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0917] Step 1:

[0918] The server measures the current number of active users at regular intervals. The measured number of active users becomes input data. Based on this data, the server adjusts resources. For example, if the number of active users decreases at night, it automatically deactivates unnecessary instances to reduce costs.

[0919] Step 2:

[0920] The server calculates the required resources based on the number of active users it measures. This calculation results in output data. If the number of active users increases, the server launches new instances, providing additional CPU, memory, and storage immediately.

[0921] Step 3:

[0922] The device receives requests from users and sends the contents of those requests to the generative AI model. The contents of those requests become input data. Specifically, when a user sends a message to customer support, the contents of that message are forwarded to the generative AI model.

[0923] Step 4:

[0924] The generative AI model generates an appropriate response based on the received request. The generated response becomes the output data. This response is sent back to the device. For example, in response to a request such as "Please tell me the status of my order," the generative AI model generates a response such as "Sorry for the wait. Your order is currently being delivered."

[0925] Step 5:

[0926] The device receives the response from the generative AI model and displays it to the user. This response message serves as input data. For example, the device displays this message in a chat window to provide the user with a prompt reply.

[0927] Step 6:

[0928] The device recognizes emotions from the user's voice and text. Input data is messages typed by the user in the chat interface or the contents of voice calls. The device sends this to the emotion engine, which analyzes the user's emotions.

[0929] Step 7:

[0930] The emotion engine analyzes input data and generates output data based on the recognized emotions. The server receives the results and adjusts the chat service or customer support response. For example, if the emotion engine detects "anger," it can change the response to be more polite and comforting.

[0931] Step 8:

[0932] The device generates voice data based on the generative AI model in response to user actions. The text sent by the user is the input data. This text is sent to the generative AI model to generate voice data.

[0933] Step 9:

[0934] The server generates voice data using a generative AI model. The text data is the input data, and the voice file is the output data. The generated voice file is sent back to the device.

[0935] Step 10:

[0936] The terminal plays the generated voice data to the user. The voice data is input data, and the voice is played back so that the user can hear it. As a specific example, in response to a user request such as "Please tell me the status of my order," the voice response played back is "Sorry to keep you waiting. Your order is currently being delivered."

[0937] 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.

[0938] 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.

[0939] 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.

[0940] [Third embodiment]

[0941] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0942] 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.

[0943] 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).

[0944] 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.

[0945] 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.

[0946] 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).

[0947] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0948] 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.

[0949] 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.

[0950] 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.

[0951] 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.

[0952] 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."

[0953] The system of the present invention includes automatic resource adjustment according to the number of cloud server users, automated chat service and customer support using generative artificial intelligence models, and means for automatically generating in-game content and updates in order to avoid the termination of online game services and to operate them automatically at low cost.

[0954] The operation of the system of the present invention will be specifically described below.

[0955] Cloud Server Management

[0956] server

[0957] The server measures the current number of active users at regular intervals.

[0958] Example: The server measures the number of active users every hour and adjusts resources based on that number. For example, if the number of active users decreases at night, unnecessary instances are automatically released to reduce costs.

[0959] The server calculates the amount of resources needed based on the number of active users.

[0960] Example: If the number of active users increases, the server will launch new instances and instantly add the required CPU, memory, and storage.

[0961] Leveraging generative AI models

[0962] Terminal

[0963] The device receives requests from users and sends them to the AI ​​model.

[0964] Example: When a user sends a message to customer support, the device forwards the message to the AI ​​model, which then generates a response appropriate to the inquiry and sends it back to the device.

[0965] The terminal displays the generated response to the user.

[0966] Example: The device displays responses from the AI ​​model in a chat window, providing the user with a quick response.

[0967] Automatic updates

[0968] server

[0969] The server periodically sends game data to the AI ​​model.

[0970] Example: Every weekend, the server collects game data and pushes it to an AI model, which uses this data to generate new stages and character dialogue.

[0971] The server reflects the generated content in the game.

[0972] Example: The server integrates new content returned by the AI ​​model into the existing game data and automatically applies updates.

[0973] Voice support

[0974] Terminal

[0975] The device will activate the AI ​​voice bot when triggered by user action.

[0976] Example: When a user interacts with a specific character, the device detects when the "speak" button is pressed and sends text to an AI voice bot.

[0977] The terminal provides the generated voice data to the user.

[0978] Example: The device receives audio files from an AI voice bot and plays them in the game, allowing users to enjoy natural voice interaction.

[0979] Based on the above process, all operational processes, including cloud server operation, user support, content generation, and voice response, are automated using AI, enabling continuous operation of online games, which also significantly reduces operational costs and eases the burden on human resources.

[0980] The processing flow will be explained below.

[0981] Cloud Server Management

[0982] Step 1: Measure active users

[0983] The server measures the current number of active users at regular intervals.

[0984] Specifically, the server checks the sessions of all users connected to each game instance and tally the total number of active sessions.

[0985] Step 2: Calculate resources

[0986] The server calculates the amount of resources needed based on the number of active users.

[0987] For example, the server dynamically calculates new amounts of CPU, memory, and storage when the number of active users exceeds a certain threshold.

[0988] Step 3: Performing scaling

[0989] The server uses auto-scaling to adjust resources.

[0990] The servers automatically launch new instances to accommodate increased user load, and release unneeded instances to reduce costs when the number of users decreases.

[0991] Leveraging generative AI models

[0992] Step 1: Get the user request

[0993] The terminal receives a request from the user.

[0994] The device collects user messages using an in-game chat interface and customer support.

[0995] Step 2: Send to AI model

[0996] The device sends the user request to the appropriate AI model.

[0997] The device sends the message received from the user in text format to the API endpoint of the AI ​​model.

[0998] Step 3: Generation by AI model

[0999] The server receives the response generated by the AI ​​model.

[1000] The server receives and stores the response messages sent by the AI ​​model.

[1001] Step 4: Deliver to users

[1002] The terminal returns the generated response to the user.

[1003] The device displays the response from the AI ​​model on the chat interface and provides it to the user instantly.

[1004] Automatic updates

[1005] Step 1: Collect data

[1006] The server periodically collects the latest game data.

[1007] The server collects game setting files, character data, stage information, and other information all at once.

[1008] Step 2: Prepare to send data

[1009] The server prepares to send the collected game data to the AI ​​model.

[1010] The server formats various data and prepares it in a form that can be processed by the AI ​​model.

[1011] Step 3: Generation by AI model

[1012] The server sends game data to the AI ​​model and requests it to generate new content.

[1013] The AI ​​model generates new stages and character lines based on the data sent and sends them back to the server.

[1014] Step 4: Reflecting content

[1015] The server reflects the generated new content in the game.

[1016] The server incorporates the data returned from the AI ​​model into the game data and provides it to the user as new content.

[1017] Voice support

[1018] Step 1: Detecting trigger words

[1019] The device detects whether the user has used a specific trigger word.

[1020] The device monitors messages entered by users in the chat interface and detects defined trigger words.

[1021] Step 2: Launch your AI voicebot

[1022] If the device detects a trigger word, it will activate an AI voice bot.

[1023] Based on the detected trigger word, the device prepares to send text to the speech synthesis API.

[1024] Step 3: Speech generation

[1025] The server generates voice data using an AI voice bot.

[1026] The server inputs the transmitted text data into a speech synthesis model and generates an audio file.

[1027] Step 4: Streaming audio data

[1028] The terminal provides the generated voice data to the user.

[1029] The terminal plays back the generated audio data and lets the user hear it.

[1030] Example 1

[1031] 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."

[1032] When operating an online game, it is important to avoid service termination and ensure continuous operation at low cost. However, managing resources to respond to fluctuations in user numbers, providing user support, automatically generating content, and providing voice dialogue manually is extremely labor-intensive and increases operational costs. For this reason, an efficient, automated system is needed.

[1033] 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.

[1034] In this invention, the server includes means for automatically adjusting resources in real time according to the number of cloud server users, means for automating user chat services and customer support using a generative artificial intelligence model, means for automatically generating in-game content and updates using the generative artificial intelligence model, and means for providing voice interaction functionality using the generative artificial intelligence model, thereby enabling efficient resource management, automated user support, continuous content updates, and the provision of natural voice interaction.

[1035] A "cloud server" is a server system that provides multiple distributed computing resources accessible via the Internet.

[1036] "Automatic resource adjustment" is the process of dynamically changing the allocation of computing resources (CPU, memory, storage, etc.) depending on the number of users and load.

[1037] A "generative artificial intelligence model" is a machine learning algorithm and its implementation that can generate new information and content based on given data and conditions.

[1038] "User Chat Service" is a collective term for the interface that allows users to have text-based interactions with the system and the system that operates behind the interface.

[1039] "Customer support" refers to a service that responds to inquiries and problems from users and provides solutions.

[1040] "In-game content" means all elements (stages, characters, items, etc.) that users can operate, view, or use within an online game.

[1041] "Voice interaction functions" refer to the functions of a system that interacts based on a user's voice input and the voice output that it generates.

[1042] "Real-time" means that the delay between data generation, processing, and notification is close to zero.

[1043] "Scaling" is the process of increasing or decreasing system resources according to certain conditions or criteria.

[1044] A "server instance" is an individual virtual machine or container running on a cloud service.

[1045] The system of the present invention aims to prevent service terminations of online games and automate their operation at low cost. The system includes automatic resource adjustment based on the number of cloud server users, automated chat service and customer support using generative AI models, and automatic generation of in-game content and updates. Furthermore, it provides voice interaction functionality to create a more interactive user experience.

[1046] Cloud Server Management

[1047] The server measures the current number of active users at regular intervals. For example, the server obtains the number of active users from the game's login data at 00 minutes past the hour. This measurement data is recorded in a database and used in the next step. Based on the obtained number of active users, the server calculates the required amount of resources. If one instance is required for 200 users, and the current number of active users is 400, it calculates that a total of two instances are required. Based on this calculation, the server automatically adds or releases the necessary resources. For example, if the number of active users drops to 100 overnight, it will run only one instance and release the unnecessary instances.

[1048] Leveraging generative AI models

[1049] The device receives requests from the user and sends them to the generative AI model. For example, when a user sends a message to customer support, the device forwards the content to the AI ​​model. An example of a prompt sentence is, "User inquiry: I can't log in to my account. Please suggest a solution." The AI ​​model generates a response appropriate to the inquiry and sends it back to the device. The device then displays the generated response to the user. For example, the response from the AI ​​model can be displayed in a chat window, allowing the user to receive a prompt reply.

[1050] Automatic updates

[1051] The server periodically sends game data to the generative AI model. For example, the server collects game data every weekend and pushes it to the AI ​​model. A specific example of a prompt might be, "Generate new stages and character dialogue based on last week's data." The AI ​​model then generates new content (stages and character dialogue) based on this data. The generated new content is integrated with the existing game data and automatically reflected in the game.

[1052] Voice support

[1053] The device triggers the AI ​​voice bot with user actions. For example, when a user interacts with a specific character, it detects that the "Speak" button has been pressed and sends text to the AI ​​voice bot. An example of a prompt to send is "The user is interacting with Character A. Please generate a greeting line in voice." The device then plays back the voice data received from the AI ​​voice bot. This allows the user to enjoy a conversation in a natural voice.

[1054] The above process enables efficient resource management of cloud servers, automated user support, automatic game updates, and voice interaction, ensuring continuous operation of online games, while significantly reducing operational costs and the burden on personnel resources.

[1055] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1056] Cloud Server Management

[1057] Step 1:

[1058] The server measures the current number of active users at regular intervals. Specifically, the server obtains the number of active users from the game's login data at 00 minutes past the hour. The information is recorded in a database. The input is the login data, and the output is the number of active users.

[1059] Step 2:

[1060] The server calculates the required amount of resources based on the measured number of active users. For example, if it calculates that one instance is required for 200 users, and the number of active users is 400, two instances are required. This calculation result is sent to the resource management system. The input is the number of active users, and the output is the required amount of resources.

[1061] Step 3:

[1062] The server automatically adds or releases resources based on the calculation results. For example, if the number of active users drops to 100 overnight, it will run only one instance and release unnecessary instances. The input is the amount of resources required, and the output is the adjusted number of instances.

[1063] Leveraging generative AI models

[1064] Step 1:

[1065] The terminal receives requests from the user, such as when a user sends a message to customer support. The input is the user message, and the output is the converted prompt.

[1066] Step 2:

[1067] The device sends the received message to the generative AI model. It uses a REST API to send a request to the AI ​​model, for example, using a prompt such as "User inquiry: I can't log in to my account. Please suggest a solution." The input is the converted prompt, and the output is the response from the AI ​​model.

[1068] Step 3:

[1069] The device displays the generated response to the user. For example, it displays the response from the AI ​​model in a chat window, providing a quick reply to the user. The input is the response from the AI ​​model, and the output is the response displayed to the user.

[1070] Automatic updates

[1071] Step 1:

[1072] The server periodically collects game data, for example, summarizing game activity data every weekend. The input is the game activity data, and the output is the collected data.

[1073] Step 2:

[1074] The server sends the collected data to the generative AI model via an API, using a prompt such as, "Generate a new stage and character dialogue based on last week's data." The input is the collected data and the prompt, and the output is the generated new content.

[1075] Step 3:

[1076] The server reflects the generated new content in the game. It integrates the generated stage data and character dialogue into the existing game database and automatically updates the online game. The input is the generated new content, and the output is the updated game data.

[1077] Voice support

[1078] Step 1:

[1079] The device activates the AI ​​voice bot as a trigger of user actions. For example, when a user interacts with a specific character, it detects when the "Speak" button is pressed. The input is the user's actions, and the output is the transmitted text.

[1080] Step 2:

[1081] The device sends the detected text to an AI voice bot. The text is sent to a generative AI model, and a prompt such as "The user will interact with Character A. Please generate a greeting line in voice." The input is the text to be sent and the prompt, and the output is the generated voice data.

[1082] Step 3:

[1083] The device receives and plays back the voice data generated by the AI ​​voice bot. The voice file is then loaded by the player and played in the game. The input is the generated voice data, and the output is the voice that is played.

[1084] (Application example 1)

[1085] 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."

[1086] In today's online services and e-commerce platforms, efficient management of server resources, user support, and content updates are chronically draining human resources. Furthermore, providing voice support and quickly generating new product descriptions and reviews to improve the user experience are also challenges. Systems that can efficiently automate these tasks are needed.

[1087] 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.

[1088] In this invention, the server includes means for automatically adjusting resources in real time according to the number of cloud server users, means for automating user chat services and customer support using a generative artificial intelligence model, means for automatically generating online content and updates using the generative artificial intelligence model, and means for generating voice data and providing voice dialogue using the generative artificial intelligence model, thereby enabling efficient operation of the server, provision of high-quality user services, and automated content updates.

[1089] A "cloud server" is a server with computing resources and storage provided via the Internet.

[1090] "Real-time" refers to the instantaneous processing of data and information, meaning that there is very little delay.

[1091] "Automatic resource adjustment" refers to dynamically increasing or decreasing resources such as CPU, memory, and storage depending on server usage.

[1092] A "generative artificial intelligence model" is an artificial intelligence algorithm that is trained to generate content such as text, audio, or images.

[1093] "Chat service" refers to a service that allows real-time communication via text messages.

[1094] "Customer support" refers to support services provided to resolve inquiries and problems regarding products and services.

[1095] "Online content" refers to various media content, such as text, images, audio, and video, that is distributed via the Internet.

[1096] "Auto-generation" refers to content being created anew by a system or algorithm without human intervention.

[1097] "Speech data" refers to digital recordings of speech, typically used for speech recognition and synthesis.

[1098] "Voice interaction" refers to an interface in which the user interacts with the system using voice.

[1099] A "product description" is text or media content that provides detailed explanations of a product's features, functions, specifications, etc.

[1100] A "review" is content that describes a user's evaluation or opinion of a product or service.

[1101] "Recommendation" refers to a system or function that recommends products or services based on a user's preferences and behavioral history.

[1102] System Overview

[1103] This invention relates to a system that efficiently manages cloud server resources and utilizes generative artificial intelligence models to provide chat services, customer support, voice dialogue, and automatic content generation for users. Specific embodiments of this system are described below.

[1104] Hardware and Software Used

[1105] Hardware:

[1106] Smartphone

[1107] Cloud infrastructure (e.g. AWS, GCP)

[1108] software:

[1109] Programming languages: Python, Java (server side), Swift / Kotlin (mobile apps)

[1110] Frameworks: TensorFlow (generative AI model), Flask / Django (server-side API)

[1111] Libraries: NLTK, Spacy (natural language processing)

[1112] API: Google Cloud Speech-to-Text, Google Cloud Text-to-Speech

[1113] Processing Overview

[1114] 1. Cloud server resource management

[1115] The server measures the number of people using the cloud server at regular intervals and calculates the required amount of resources based on the data. Before resources become overloaded, it automatically launches new instances and adds the necessary CPU, memory, and storage. It also reduces costs by automatically releasing unnecessary instances when usage decreases.

[1116] 2. AI chat support

[1117] When a user sends a message to customer support from their device, the message is forwarded to the AI ​​model, which generates a response appropriate to the inquiry and sends it back to the device. This response is then displayed in the chat window, allowing the user to receive a prompt reply.

[1118] Example prompt sentence:

[1119] User: I want to know more about this product

[1120] AI model response: We will provide you with detailed product information. The main features of this product are...

[1121] 3. Automated content generation

[1122] The server periodically sends new product data to the AI ​​model and receives the generated product descriptions and recommendations. The generated content is automatically updated in the device application, ensuring that the latest information is always provided.

[1123] Example prompt sentence:

[1124] Generate a testimonial for your new smartphone

[1125] AI model response:

[1126] This latest smartphone is packed with innovative features and beautiful design, most notably...

[1127] 4. Voice support

[1128] When a user taps the microphone icon to start voice input, the recorded voice is converted into text by Google Cloud Speech-to-Text. The generated text is sent to an AI model, which returns an appropriate response. Google Cloud Text-to-Speech then generates audio data and plays it back on the device, allowing users to enjoy natural voice interaction.

[1129] The combination of these measures enables efficient operation of cloud servers, fast customer support, automated content generation and voice interaction, significantly reducing the operating costs of online services and providing a high-quality user experience.

[1130] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1131] Step 1:

[1132] The server measures the number of people using the cloud server at regular intervals. The input is the current number of active users, and the output is the calculated amount of resources required. This measurement is based on server log data and real-time access data. Specifically, the current number of active users is obtained by analyzing the server's access log.

[1133] Step 2:

[1134] The server calculates the required amount of resources based on the number of active users measured, and automatically adjusts the server instances. The input is the number of active users data output from Step 1, and the output is information about the instances to be newly added or released. Specifically, AWS's Auto Scaling function is used to dynamically add or reduce the required CPU and memory.

[1135] Step 3:

[1136] The device receives customer support messages from users and sends them to the AI ​​model. The input is the message entered by the user into the device, and the output is a prompt for the generative artificial intelligence model. Specifically, when the user enters a message and presses the send button, the message is transferred to the AI ​​model via the server.

[1137] Step 4:

[1138] The server receives the response generated by the AI ​​model and sends it to the terminal. The input is the response data generated by the AI ​​model, and the output is data in the format displayed in the chat window. Specifically, the AI ​​model generates a response appropriate to the inquiry content and sends it to the terminal in JSON format.

[1139] Step 5:

[1140] The server periodically sends new product data to the AI ​​model and receives the generated product descriptions and recommendations. The input is product attribute data, and the output is the generated product descriptions and recommendation lists. Specifically, information from the product database is periodically pushed to the AI ​​model to generate new descriptions and recommendation lists.

[1141] Step 6:

[1142] The device displays product descriptions and recommendations received from the server. The input is the generated data transferred from the server, and the output is the content displayed on the device's UI. Specifically, the generated descriptions and recommended item lists are rendered in the display area within the app.

[1143] Step 7:

[1144] The user starts voice input, and the device converts the recorded voice into text using the Google Cloud Speech-to-Text API. The input is the user's voice data, and the output is text data. Specifically, voice recording begins when the microphone button is pressed, and the recorded data is sent to the cloud API and converted into text.

[1145] Step 8:

[1146] The user's speech, converted into text, is sent to an AI model to generate an appropriate voice response. The input is text data, and the output is the response text data. Specifically, the converted text is sent to the AI ​​model as a prompt, and an appropriate reply is generated.

[1147] Step 9:

[1148] The server uses the Google Cloud Text-to-Speech API to convert the generated text data into audio data and send it to the device. The input is the text data of the response content, and the output is audio data. Specifically, the generated response text is sent to the cloud API, which generates an audio file and sends it to the device.

[1149] Step 10:

[1150] The device plays back the received voice data and provides it to the user. The input is the voice data sent from the server, and the output is the user's auditory feedback. Specifically, the received voice file is provided to the user using the playback function, realizing natural voice interaction.

[1151] 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.

[1152] The system of the present invention provides a more interactive and personalized experience by combining automatic resource adjustment according to the number of cloud server users, automated user support using a generative artificial intelligence model, and automatic generation of in-game content with an emotion engine that recognizes user emotions.

[1153] The operation process of the system of the present invention will be specifically described below.

[1154] Cloud Server Management

[1155] server

[1156] The server measures the current number of active users at regular intervals.

[1157] Example: The server measures the number of active users every hour and adjusts resources based on that number. For example, if the number of active users decreases at night, unnecessary instances are automatically released to reduce costs.

[1158] The server calculates the amount of resources needed based on the number of active users.

[1159] Example: If the number of active users increases, the server will launch new instances and instantly add the required CPU, memory, and storage.

[1160] Leveraging generative AI models

[1161] Terminal

[1162] The device receives requests from users and sends them to the AI ​​model.

[1163] Example: When a user sends a message to customer support, the device forwards the message to the AI ​​model, which then generates a response appropriate to the inquiry and sends it back to the device.

[1164] The terminal displays the generated response to the user.

[1165] Example: The device displays responses from the AI ​​model in a chat window, providing the user with a quick response.

[1166] Automatic updates

[1167] server

[1168] The server periodically sends game data to the AI ​​model.

[1169] Example: Every weekend, the server collects game data and pushes it to an AI model, which uses this data to generate new stages and character dialogue.

[1170] The server reflects the generated content in the game.

[1171] Example: The server integrates new content returned by the AI ​​model into the existing game data and automatically applies updates.

[1172] Utilizing the Emotion Engine

[1173] Terminal

[1174] The device recognizes emotions from the user's voice and text.

[1175] Example: The device analyzes messages typed by the user in a chat interface and the content of voice calls to detect the user's emotions.

[1176] server

[1177] The server then tailors responses for chat services and customer support based on the perceived emotion.

[1178] For example: If the emotion engine detects "anger" or "sadness," the server may change the response to be more polite and comforting. Conversely, if it detects "joy" or "excitement," the server may adjust the response to a friendlier tone.

[1179] Terminal

[1180] The device changes the movements and expressions of the in-game characters in real time according to the user's emotions.

[1181] Example: If the device's emotion engine recognizes that the user is sad, it will change the in-game character to make comforting gestures and say comforting lines.

[1182] Voice support

[1183] Terminal

[1184] The device will activate the AI ​​voice bot when triggered by user action.

[1185] Example: When a user interacts with a specific character, the device detects when the "speak" button is pressed and sends text to an AI voice bot.

[1186] server

[1187] The server generates voice data using an AI voice bot.

[1188] Example: The server uses a speech synthesis model to generate an audio file based on the text sent and sends it back to the device.

[1189] Terminal

[1190] The terminal plays the generated audio data to the user.

[1191] Example: The device plays the generated audio data so that the user can hear it.

[1192] As a result, the system of the present invention achieves effective resource management of cloud servers, automated user response through generative AI models, and interactive and emotionally responsive experiences through an emotion engine, which significantly reduces operational costs and alleviates the burden on human resources.

[1193] The processing flow will be explained below.

[1194] Cloud Server Management

[1195] Step 1: Measure active users

[1196] The server measures the current number of active users at regular intervals.

[1197] Example: The server checks and aggregates the session information of active users every hour, thereby determining the real-time number of users.

[1198] Step 2: Calculate resources

[1199] The server calculates the amount of resources needed based on the number of active users.

[1200] Example: A server calculates how many additional resources (CPU, memory, storage) to add when the number of active users exceeds a certain threshold (e.g., 500 users).

[1201] Step 3: Performing scaling

[1202] The server uses auto-scaling to adjust resources.

[1203] Example: Servers launch new instances to add necessary resources as the number of users increases, while unnecessary instances are stopped to reduce costs when the number of users decreases.

[1204] Leveraging generative AI models

[1205] Step 1: Get the user request

[1206] The terminal receives a request from the user.

[1207] Example: When a user contacts customer support, the device receives the message.

[1208] Step 2: Send to AI model

[1209] The device sends the user request to the AI ​​model.

[1210] Example: The device sends the received message to the API endpoint of the AI ​​model, initiating processing to generate an appropriate response.

[1211] Step 3: Generation by AI model

[1212] The server receives the response generated by the AI ​​model.

[1213] Example: The server receives and stores the response message generated by the AI ​​model.

[1214] Step 4: Deliver to users

[1215] The terminal returns the generated response to the user.

[1216] Example: The device displays a reply message from the AI ​​model on the chat interface and provides it to the user.

[1217] Automatic updates

[1218] Step 1: Collect data

[1219] The server periodically collects the latest game data.

[1220] Example: Every weekend, the server collects game configuration files, character data, stage information, etc.

[1221] Step 2: Prepare data for transmission

[1222] The server prepares to send the collected game data to the AI ​​model.

[1223] Example: The server formats the data in a way that is easy for the AI ​​model to parse.

[1224] Step 3: Generation by AI model

[1225] The server sends game data to the AI ​​model and requests it to generate new content.

[1226] Example: An AI model generates new levels and character dialogue and sends it back to the server.

[1227] Step 4: Reflecting content

[1228] The server reflects the generated new content in the game.

[1229] Example: The server integrates new content returned by the AI ​​model into the existing game data and updates it so that the new content is immediately available to the user.

[1230] Utilizing the Emotion Engine

[1231] Step 1: Collecting emotion data

[1232] The device recognizes emotions from the user's voice and text.

[1233] Example: The device analyzes messages entered by the user in a chat interface to detect the user's emotions (happiness, sadness, anger, excitement).

[1234] Step 2: Generate an emotion-based response

[1235] The server adjusts the response content based on the user's emotions recognized by the emotion engine.

[1236] Example: If the server detects "anger," it might make its response polite and comforting, but if it detects "happiness," it might use a friendlier tone.

[1237] Step 3: Generate emotion-based content

[1238] The server dynamically generates content within the game according to the user's emotions.

[1239] Example: If the user is sad, an in-game character can automatically generate comforting lines and actions.

[1240] Voice support

[1241] Step 1: Detecting trigger words

[1242] The device detects whether the user has used a specific trigger word.

[1243] Example: The device monitors and detects trigger words such as "talk" in a chat interface.

[1244] Step 2: Launch your AI voicebot

[1245] The device will activate an AI voice bot if it detects a trigger word.

[1246] Example: The device sends the detected trigger word to an AI voice bot to start the voice synthesis process.

[1247] Step 3: Speech generation

[1248] The server generates voice data using an AI voice bot.

[1249] Example: The server inputs the submitted text data into a speech synthesis model and saves the generated audio file.

[1250] Step 4: Streaming audio data

[1251] The terminal provides the generated voice data to the user.

[1252] Example: The device plays the generated audio data so that the user can hear it.

[1253] Example 2

[1254] 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."

[1255] Conventional cloud server systems face challenges in efficient resource management, making it difficult to flexibly adjust and respond to user usage and emotions. They also lack the ability to automatically generate in-game content and provide interactive experiences based on user emotions. This has resulted in high system operating costs and limited user experience.

[1256] 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.

[1257] In this invention, the server includes means for automatically adjusting resources in real time according to the number of cloud server users, means for automating user chat services and customer support responses using a generative artificial intelligence model, means for automatically generating in-game content and updates using a generative artificial intelligence model, means for recognizing emotions from user voice and text using an emotion recognition engine and adjusting response content based on the emotions, and means for converting text into voice data based on user operations using a speech synthesis engine and playing the voice data back to the user. This enables efficient resource management and cost reduction, and makes it possible to provide users with a more interactive and personalized experience.

[1258] A "cloud server" is a computer server that provides remote computer resources accessible over the Internet.

[1259] "Real-time" is a term that refers to events and data processing occurring as soon as they occur.

[1260] "Resources" are the hardware and software capabilities that a computer system provides, such as computation, memory, and storage.

[1261] A "generative artificial intelligence model" is an algorithm and machine learning model that automatically generates data and information based on instructions given by humans.

[1262] "Chat service" is a communication service that allows sending and receiving text messages in real time.

[1263] "Customer Support" means services that provide assistance to customers with questions or problems.

[1264] An "emotion recognition engine" is an algorithm and system for analyzing and recognizing emotions from human voice and text.

[1265] A "speech synthesis engine" is a technology and program for converting text data into voice data.

[1266] "Scaling" is the process of increasing or decreasing a system's processing power or resources to adapt to load or demand.

[1267] An "instance" is an individual execution environment for virtual machines and computer resources that run on a cloud server.

[1268] The present invention is a system that utilizes a cloud server to efficiently manage resources based on the user's usage status and emotions, and combines a generative artificial intelligence model and an emotion recognition engine to provide an advanced user experience.

[1269] First, the server uses the cloud provider's monitoring tools (for example, a general cloud management service) to measure the current number of active users at regular intervals. Based on the measured number of active users, the server calculates the amount of resources required and automatically adjusts the resources. Specifically, this involves adding or removing virtual machine instances using a scaling policy.

[1270] Next, the device receives the user's request and sends it to a generative artificial intelligence model (e.g., a general-purpose generative AI model). When the user sends a message to customer support, the content is sent to the generative AI model, which generates an appropriate response. For example, if the user asks, "I'd like to return an item. What should I do?", the generative AI model will generate a response such as, "We will inform you of the return procedure. First, please fill out the return form."

[1271] Furthermore, the server periodically collects the latest game data and sends it to the generative AI model, which then generates new stages and character dialogue and integrates them with the existing game data, updating the game database and automatically distributing the updates to the server.

[1272] The device analyzes the user's voice and text and recognizes the user's emotions using an emotion recognition engine (e.g., a general emotion analysis service). This emotion information is sent to the server and used to adjust the response content and the in-game character's movements and facial expressions in real time. For example, if the user types "Today was a tough day," the emotion recognition engine recognizes this as "sadness," and the in-game character will say encouraging words like "Cheer up!"

[1273] Furthermore, the device activates a speech synthesis engine in response to a user operation, converts the text into voice data, and plays it back to the user. For example, when the user presses the "speak" button, the text is sent to the speech synthesis engine, and the generated voice data is played back.

[1274] This allows the system of the present invention to achieve efficient resource management, reduce costs, and provide users with an interactive and personalized experience.

[1275] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1276] Step 1:

[1277] The server uses the cloud provider's monitoring tool to measure the current number of active users at regular intervals. Specifically, it periodically retrieves metric data generated by the monitoring tool and analyzes the data with a Python script.

[1278] Input: Metric data from cloud provider monitoring tools

[1279] Output: Analysis result of current number of active users

[1280] Step 2:

[1281] The server calculates the required amount of resources based on the number of active users measured, and automatically adds or removes virtual machine instances using a scaling policy, specifically using an auto-scaling function such as AWS Lambda.

[1282] Input: Number of active users

[1283] Output: Instances added or removed due to resource throttling

[1284] Step 3:

[1285] The user sends a message to customer support through the device, which receives the user's request and sends it to the generative AI model.

[1286] Input: Customer support message from the user

[1287] Output: The request sent to the generative AI model

[1288] Step 4:

[1289] The generative AI model generates a response appropriate to the user's request and returns the response to the device. Specifically, the generative AI model uses natural language processing to generate text appropriate to the inquiry.

[1290] Input: Customer Support Request

[1291] Output: Generated customer support response text

[1292] Step 5:

[1293] The device displays the response returned by the generative AI model to the user, specifically, by displaying the generated response in a chat window.

[1294] Input: Response text from the generative AI model

[1295] Output: Response displayed in the chat window

[1296] Step 6:

[1297] The server periodically collects the latest game data and sends it to the generative AI model, which then converts the collected game data into JSON format and sends it to the AI ​​model.

[1298] Input: Latest game data

[1299] Output: Game data sent to the AI ​​model

[1300] Step 7:

[1301] The generative AI model generates new game content (e.g., stages and character dialogue) and sends that content back to the server.

[1302] Input: Game data

[1303] Output: Generated game content

[1304] Step 8:

[1305] The server integrates the generated new game content into the existing game database and automatically updates the game data.

[1306] Input: Generated game content

[1307] Output: Updated game database

[1308] Step 9:

[1309] The device sends the user's voice and text to an emotion recognition engine to analyze the user's emotions. Specifically, the device sends the voice and text to an emotion analysis service to obtain emotional information.

[1310] Input: User voice or text

[1311] Output: Parsed emotion information

[1312] Step 10:

[1313] The server adjusts the response based on the analyzed user's emotions. For example, if the emotion recognition engine detects "sadness," it changes the response to something comforting.

[1314] Input: Parsed emotion information

[1315] Output: Adjusted response content

[1316] Step 11:

[1317] The user interacts with the in-game character through the device, which then changes the character's behavior and facial expressions in real time based on the user's emotional information. Specifically, the device controls the character's behavior using the game engine's API.

[1318] Input: User's emotional information

[1319] Output: Modified character movements and expressions

[1320] Step 12:

[1321] The device activates a speech synthesis engine in response to user operations and converts text into voice data. Specifically, when the user presses the "speak" button, the device sends the text to the speech synthesis engine.

[1322] Input: User text input

[1323] Output: Generated audio data

[1324] Step 13:

[1325] The terminal plays the generated audio data to the user. Specifically, it plays the audio file in a streaming format and lets the user listen to it.

[1326] Input: Generated audio data

[1327] Output: The audio played to the user

[1328] The above is the specific processing flow of this system.

[1329] (Application example 2)

[1330] 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."

[1331] Conventional food delivery services have faced issues with server resource shortages during sudden user increases, resulting in service delays and outages. Furthermore, customer support has been handled manually, resulting in issues of delayed responses and inconsistent quality. Furthermore, personalized responses based on user sentiment are required, but the means to achieve this have been limited. Even with voice support, only text-based support was available, limiting the user experience.

[1332] 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 automatically adjusting resources in real time according to the number of cloud server users, means for automating user chat services, customer support, and other responses using a generative artificial intelligence model, means for automatically generating in-game content and updates using a generative artificial intelligence model, means for using an emotion engine to recognize user emotions and adjust responses, and means for generating and playing voice data using a generative artificial intelligence model in response to user operations as a voice response. This makes it possible for food delivery services to provide stable service even to a rapidly increasing number of users and to realize interactive and personalized responses that correspond to user emotions.

[1333] A "cloud server" is a collection of server resources provided over the Internet, and is a remote computing environment for storing and processing data.

[1334] "Automatic resource adjustment" is a function that dynamically changes the allocation of computer resources such as servers and storage according to current usage.

[1335] A "generative artificial intelligence model" is an AI model that has the ability to learn implicit rules and patterns and generate new data such as text, images, and audio based on given input.

[1336] "Chat service" refers to a means of communication for exchanging messages in real time, and is intended to enable users to exchange information with each other and between users and support staff.

[1337] "Customer support" refers to services that assist customers in resolving inquiries and problems.

[1338] "In-game content" refers to elements such as stages, characters, items, and dialogue that are provided for the enjoyment of game players.

[1339] An "emotion engine" is a system that determines emotions from a user's voice or text and adjusts the response accordingly.

[1340] "Voice support" is a function that enables interaction using voice data generated based on user operations.

[1341] An "instance" is a unit of computer resources that runs as a virtual machine or container in a cloud environment.

[1342] "Scaling" refers to the act of adding or removing resources to increase or decrease the performance or capacity of a system.

[1343] This invention is a system that provides an interactive and personalized experience in a food delivery service by automatically adjusting cloud server resources, automating customer support using a generative artificial intelligence model, and improving user response using an emotion engine.

[1344] Cloud Server Management

[1345] server

[1346] The server measures the current number of active users at regular intervals. For example, it measures the number of active users every hour and adjusts resources based on that number. For example, if the number of active users decreases at night, unnecessary instances are automatically deactivated to reduce costs.

[1347] The server calculates the amount of resources needed based on the number of active users. For example, if the number of active users increases, the server will launch new instances and instantly add the required CPU, memory, and storage.

[1348] Leveraging generative AI models

[1349] Terminal

[1350] The device receives requests from users and sends them to the generative AI model. For example, when a user sends a message to customer support, the content is forwarded to the generative AI model. The generative AI model then generates a response appropriate to the inquiry and sends it back to the device.

[1351] The device displays the generated response to the user. For example, the device displays the response from the generative AI model in a chat window, providing the user with a quick reply.

[1352] Utilizing the Emotion Engine

[1353] Terminal

[1354] The device recognizes emotions from the user's voice and text. For example, the device analyzes messages typed by the user in a chat interface or the content of voice calls to detect the user's emotions.

[1355] server

[1356] The server adjusts the content of responses from chat services and customer support based on the recognized emotions. For example, if the emotion engine detects "anger" or "sadness," it changes the response to be more polite and comforting. Conversely, if it detects "joy" or "excitement," it adjusts the response to a friendlier tone.

[1357] Voice support

[1358] Terminal

[1359] The device generates voice data based on the generative AI model in response to user actions. For example, if a user types "Please tell me the status of my order," the device sends the text to the generative AI model, which then converts the resulting text into speech.

[1360] server

[1361] The server generates voice data using a generative AI model. For example, the server uses a speech synthesis model to generate an audio file based on the text sent to it and sends it back to the device.

[1362] Terminal

[1363] The terminal plays the generated audio data to the user. In a specific example, the terminal plays the generated audio data so that the user can hear it.

[1364] Examples of concrete examples and prompts

[1365] As a concrete example, if a user sends the message "Please tell me the status of my order," the system will act as follows:

[1366] 1. The number of active users is checked and the required resources are adjusted.

[1367] 2. The emotion "excitement" is recognized from the user's text, and a positive response is generated: "Great! How can I assist you today?"

[1368] 3. The generated text is converted into speech and played back to the user.

[1369] Example prompt sentence:

[1370] User: "What's the status of my order?"

[1371] Sentiment analysis result: Positive

[1372] Response: "Great! How can I assist you today?"

[1373] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1374] Step 1:

[1375] The server measures the current number of active users at regular intervals. The measured number of active users becomes input data. Based on this data, the server adjusts resources. For example, if the number of active users decreases at night, it automatically deactivates unnecessary instances to reduce costs.

[1376] Step 2:

[1377] The server calculates the required resources based on the number of active users it measures. This calculation results in output data. If the number of active users increases, the server launches new instances, providing additional CPU, memory, and storage immediately.

[1378] Step 3:

[1379] The device receives requests from users and sends the contents of those requests to the generative AI model. The contents of those requests become input data. Specifically, when a user sends a message to customer support, the contents of that message are forwarded to the generative AI model.

[1380] Step 4:

[1381] The generative AI model generates an appropriate response based on the received request. The generated response becomes the output data. This response is sent back to the device. For example, in response to a request such as "Please tell me the status of my order," the generative AI model generates a response such as "Sorry for the wait. Your order is currently being delivered."

[1382] Step 5:

[1383] The device receives the response from the generative AI model and displays it to the user. This response message serves as input data. For example, the device displays this message in a chat window to provide the user with a prompt reply.

[1384] Step 6:

[1385] The device recognizes emotions from the user's voice and text. Input data is messages typed by the user in the chat interface or the contents of voice calls. The device sends this to the emotion engine, which analyzes the user's emotions.

[1386] Step 7:

[1387] The emotion engine analyzes input data and generates output data based on the recognized emotions. The server receives the results and adjusts the chat service or customer support response. For example, if the emotion engine detects "anger," it can change the response to be more polite and comforting.

[1388] Step 8:

[1389] The device generates voice data based on the generative AI model in response to user actions. The text sent by the user is the input data. This text is sent to the generative AI model to generate voice data.

[1390] Step 9:

[1391] The server generates voice data using a generative AI model. The text data is the input data, and the voice file is the output data. The generated voice file is sent back to the device.

[1392] Step 10:

[1393] The terminal plays the generated voice data to the user. The voice data is input data, and the voice is played back so that the user can hear it. As a specific example, in response to a user request such as "Please tell me the status of my order," the voice response played back is "Sorry to keep you waiting. Your order is currently being delivered."

[1394] 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.

[1395] 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.

[1396] 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.

[1397] [Fourth embodiment]

[1398] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1399] 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.

[1400] 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).

[1401] 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.

[1402] 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.

[1403] 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).

[1404] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1405] 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.

[1406] 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.

[1407] 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.

[1408] 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.

[1409] 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.

[1410] 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."

[1411] The system of the present invention includes automatic resource adjustment according to the number of cloud server users, automated chat service and customer support using generative artificial intelligence models, and means for automatically generating in-game content and updates in order to avoid the termination of online game services and to operate them automatically at low cost.

[1412] The operation of the system of the present invention will be specifically described below.

[1413] Cloud Server Management

[1414] server

[1415] The server measures the current number of active users at regular intervals.

[1416] Example: The server measures the number of active users every hour and adjusts resources based on that number. For example, if the number of active users decreases at night, unnecessary instances are automatically released to reduce costs.

[1417] The server calculates the amount of resources needed based on the number of active users.

[1418] Example: If the number of active users increases, the server will launch new instances and instantly add the required CPU, memory, and storage.

[1419] Leveraging generative AI models

[1420] Terminal

[1421] The device receives requests from users and sends them to the AI ​​model.

[1422] Example: When a user sends a message to customer support, the device forwards the message to the AI ​​model, which then generates a response appropriate to the inquiry and sends it back to the device.

[1423] The terminal displays the generated response to the user.

[1424] Example: The device displays responses from the AI ​​model in a chat window, providing the user with a quick response.

[1425] Automatic updates

[1426] server

[1427] The server periodically sends game data to the AI ​​model.

[1428] Example: Every weekend, the server collects game data and pushes it to an AI model, which uses this data to generate new stages and character dialogue.

[1429] The server reflects the generated content in the game.

[1430] Example: The server integrates new content returned by the AI ​​model into the existing game data and automatically applies updates.

[1431] Voice support

[1432] Terminal

[1433] The device will activate the AI ​​voice bot when triggered by user action.

[1434] Example: When a user interacts with a specific character, the device detects when the "speak" button is pressed and sends text to an AI voice bot.

[1435] The terminal provides the generated voice data to the user.

[1436] Example: The device receives audio files from an AI voice bot and plays them in the game, allowing users to enjoy natural voice interaction.

[1437] Based on the above process, all operational processes, including cloud server operation, user support, content generation, and voice response, are automated using AI, enabling continuous operation of online games, which also significantly reduces operational costs and eases the burden on human resources.

[1438] The processing flow will be explained below.

[1439] Cloud Server Management

[1440] Step 1: Measure active users

[1441] The server measures the current number of active users at regular intervals.

[1442] Specifically, the server checks the sessions of all users connected to each game instance and tally the total number of active sessions.

[1443] Step 2: Calculate resources

[1444] The server calculates the amount of resources needed based on the number of active users.

[1445] For example, the server dynamically calculates new amounts of CPU, memory, and storage when the number of active users exceeds a certain threshold.

[1446] Step 3: Performing scaling

[1447] The server uses auto-scaling to adjust resources.

[1448] The servers automatically launch new instances to accommodate increased user load, and release unneeded instances to reduce costs when the number of users decreases.

[1449] Leveraging generative AI models

[1450] Step 1: Get the user request

[1451] The terminal receives a request from the user.

[1452] The device collects user messages using an in-game chat interface and customer support.

[1453] Step 2: Send to AI model

[1454] The device sends the user request to the appropriate AI model.

[1455] The device sends the message received from the user in text format to the API endpoint of the AI ​​model.

[1456] Step 3: Generation by AI model

[1457] The server receives the response generated by the AI ​​model.

[1458] The server receives and stores the response messages sent by the AI ​​model.

[1459] Step 4: Deliver to users

[1460] The terminal returns the generated response to the user.

[1461] The device displays the response from the AI ​​model on the chat interface and provides it to the user instantly.

[1462] Automatic updates

[1463] Step 1: Collect data

[1464] The server periodically collects the latest game data.

[1465] The server collects game setting files, character data, stage information, and other information all at once.

[1466] Step 2: Prepare to send data

[1467] The server prepares to send the collected game data to the AI ​​model.

[1468] The server formats various data and prepares it in a form that can be processed by the AI ​​model.

[1469] Step 3: Generation by AI model

[1470] The server sends game data to the AI ​​model and requests it to generate new content.

[1471] The AI ​​model generates new stages and character lines based on the data sent and sends them back to the server.

[1472] Step 4: Reflecting content

[1473] The server reflects the generated new content in the game.

[1474] The server incorporates the data returned from the AI ​​model into the game data and provides it to the user as new content.

[1475] Voice support

[1476] Step 1: Detecting trigger words

[1477] The device detects whether the user has used a specific trigger word.

[1478] The device monitors messages entered by users in the chat interface and detects defined trigger words.

[1479] Step 2: Launch your AI voicebot

[1480] If the device detects a trigger word, it will activate an AI voice bot.

[1481] Based on the detected trigger word, the device prepares to send text to the speech synthesis API.

[1482] Step 3: Speech generation

[1483] The server generates voice data using an AI voice bot.

[1484] The server inputs the transmitted text data into a speech synthesis model and generates an audio file.

[1485] Step 4: Streaming audio data

[1486] The terminal provides the generated voice data to the user.

[1487] The terminal plays back the generated audio data and lets the user hear it.

[1488] Example 1

[1489] 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."

[1490] When operating an online game, it is important to avoid service termination and ensure continuous operation at low cost. However, managing resources to respond to fluctuations in user numbers, providing user support, automatically generating content, and providing voice dialogue manually is extremely labor-intensive and increases operational costs. For this reason, an efficient, automated system is needed.

[1491] 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.

[1492] In this invention, the server includes means for automatically adjusting resources in real time according to the number of cloud server users, means for automating user chat services and customer support using a generative artificial intelligence model, means for automatically generating in-game content and updates using the generative artificial intelligence model, and means for providing voice interaction functionality using the generative artificial intelligence model, thereby enabling efficient resource management, automated user support, continuous content updates, and the provision of natural voice interaction.

[1493] A "cloud server" is a server system that provides multiple distributed computing resources accessible via the Internet.

[1494] "Automatic resource adjustment" is the process of dynamically changing the allocation of computing resources (CPU, memory, storage, etc.) depending on the number of users and load.

[1495] A "generative artificial intelligence model" is a machine learning algorithm and its implementation that can generate new information and content based on given data and conditions.

[1496] "User Chat Service" is a collective term for the interface that allows users to have text-based interactions with the system and the system that operates behind the interface.

[1497] "Customer support" refers to a service that responds to inquiries and problems from users and provides solutions.

[1498] "In-game content" means all elements (stages, characters, items, etc.) that users can operate, view, or use within an online game.

[1499] "Voice interaction functions" refer to the functions of a system that interacts based on a user's voice input and the voice output that it generates.

[1500] "Real-time" means that the delay between data generation, processing, and notification is close to zero.

[1501] "Scaling" is the process of increasing or decreasing system resources according to certain conditions or criteria.

[1502] A "server instance" is an individual virtual machine or container running on a cloud service.

[1503] The system of the present invention aims to prevent service terminations of online games and automate their operation at low cost. The system includes automatic resource adjustment based on the number of cloud server users, automated chat service and customer support using generative AI models, and automatic generation of in-game content and updates. Furthermore, it provides voice interaction functionality to create a more interactive user experience.

[1504] Cloud Server Management

[1505] The server measures the current number of active users at regular intervals. For example, the server obtains the number of active users from the game's login data at 00 minutes past the hour. This measurement data is recorded in a database and used in the next step. Based on the obtained number of active users, the server calculates the required amount of resources. If one instance is required for 200 users, and the current number of active users is 400, it calculates that a total of two instances are required. Based on this calculation, the server automatically adds or releases the necessary resources. For example, if the number of active users drops to 100 overnight, it will run only one instance and release the unnecessary instances.

[1506] Leveraging generative AI models

[1507] The device receives requests from the user and sends them to the generative AI model. For example, when a user sends a message to customer support, the device forwards the content to the AI ​​model. An example of a prompt sentence is, "User inquiry: I can't log in to my account. Please suggest a solution." The AI ​​model generates a response appropriate to the inquiry and sends it back to the device. The device then displays the generated response to the user. For example, the response from the AI ​​model can be displayed in a chat window, allowing the user to receive a prompt reply.

[1508] Automatic updates

[1509] The server periodically sends game data to the generative AI model. For example, the server collects game data every weekend and pushes it to the AI ​​model. A specific example of a prompt might be, "Generate new stages and character dialogue based on last week's data." The AI ​​model then generates new content (stages and character dialogue) based on this data. The generated new content is integrated with the existing game data and automatically reflected in the game.

[1510] Voice support

[1511] The device triggers the AI ​​voice bot with user actions. For example, when a user interacts with a specific character, it detects that the "Speak" button has been pressed and sends text to the AI ​​voice bot. An example of a prompt to send is "The user is interacting with Character A. Please generate a greeting line in voice." The device then plays back the voice data received from the AI ​​voice bot. This allows the user to enjoy a conversation in a natural voice.

[1512] The above process enables efficient resource management of cloud servers, automated user support, automatic game updates, and voice interaction, ensuring continuous operation of online games, while significantly reducing operational costs and the burden on personnel resources.

[1513] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1514] Cloud Server Management

[1515] Step 1:

[1516] The server measures the current number of active users at regular intervals. Specifically, the server obtains the number of active users from the game's login data at 00 minutes past the hour. The information is recorded in a database. The input is the login data, and the output is the number of active users.

[1517] Step 2:

[1518] The server calculates the required amount of resources based on the measured number of active users. For example, if it calculates that one instance is required for 200 users, and the number of active users is 400, two instances are required. This calculation result is sent to the resource management system. The input is the number of active users, and the output is the required amount of resources.

[1519] Step 3:

[1520] The server automatically adds or releases resources based on the calculation results. For example, if the number of active users drops to 100 overnight, it will run only one instance and release unnecessary instances. The input is the amount of resources required, and the output is the adjusted number of instances.

[1521] Leveraging generative AI models

[1522] Step 1:

[1523] The terminal receives requests from the user, such as when a user sends a message to customer support. The input is the user message, and the output is the converted prompt.

[1524] Step 2:

[1525] The device sends the received message to the generative AI model. It uses a REST API to send a request to the AI ​​model, for example, using a prompt such as "User inquiry: I can't log in to my account. Please suggest a solution." The input is the converted prompt, and the output is the response from the AI ​​model.

[1526] Step 3:

[1527] The device displays the generated response to the user. For example, it displays the response from the AI ​​model in a chat window, providing a quick reply to the user. The input is the response from the AI ​​model, and the output is the response displayed to the user.

[1528] Automatic updates

[1529] Step 1:

[1530] The server periodically collects game data, for example, summarizing game activity data every weekend. The input is the game activity data, and the output is the collected data.

[1531] Step 2:

[1532] The server sends the collected data to the generative AI model via an API, using a prompt such as, "Generate a new stage and character dialogue based on last week's data." The input is the collected data and the prompt, and the output is the generated new content.

[1533] Step 3:

[1534] The server reflects the generated new content in the game. It integrates the generated stage data and character dialogue into the existing game database and automatically updates the online game. The input is the generated new content, and the output is the updated game data.

[1535] Voice support

[1536] Step 1:

[1537] The device activates the AI ​​voice bot as a trigger of user actions. For example, when a user interacts with a specific character, it detects when the "Speak" button is pressed. The input is the user's actions, and the output is the transmitted text.

[1538] Step 2:

[1539] The device sends the detected text to an AI voice bot. The text is sent to a generative AI model, and a prompt such as "The user will interact with Character A. Please generate a greeting line in voice." The input is the text to be sent and the prompt, and the output is the generated voice data.

[1540] Step 3:

[1541] The device receives and plays back the voice data generated by the AI ​​voice bot. The voice file is then loaded by the player and played in the game. The input is the generated voice data, and the output is the voice that is played.

[1542] (Application example 1)

[1543] 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."

[1544] In today's online services and e-commerce platforms, efficient management of server resources, user support, and content updates are chronically draining human resources. Furthermore, providing voice support and quickly generating new product descriptions and reviews to improve the user experience are also challenges. Systems that can efficiently automate these tasks are needed.

[1545] 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.

[1546] In this invention, the server includes means for automatically adjusting resources in real time according to the number of cloud server users, means for automating user chat services and customer support using a generative artificial intelligence model, means for automatically generating online content and updates using the generative artificial intelligence model, and means for generating voice data and providing voice dialogue using the generative artificial intelligence model, thereby enabling efficient operation of the server, provision of high-quality user services, and automated content updates.

[1547] A "cloud server" is a server with computing resources and storage provided via the Internet.

[1548] "Real-time" refers to the instantaneous processing of data and information, meaning that there is very little delay.

[1549] "Automatic resource adjustment" refers to dynamically increasing or decreasing resources such as CPU, memory, and storage depending on server usage.

[1550] A "generative artificial intelligence model" is an artificial intelligence algorithm that is trained to generate content such as text, audio, or images.

[1551] "Chat service" refers to a service that allows real-time communication via text messages.

[1552] "Customer support" refers to support services provided to resolve inquiries and problems regarding products and services.

[1553] "Online content" refers to various media content, such as text, images, audio, and video, that is distributed via the Internet.

[1554] "Auto-generation" refers to content being created anew by a system or algorithm without human intervention.

[1555] "Speech data" refers to digital recordings of speech, typically used for speech recognition and synthesis.

[1556] "Voice interaction" refers to an interface in which the user interacts with the system using voice.

[1557] A "product description" is text or media content that provides detailed explanations of a product's features, functions, specifications, etc.

[1558] A "review" is content that describes a user's evaluation or opinion of a product or service.

[1559] "Recommendation" refers to a system or function that recommends products or services based on a user's preferences and behavioral history.

[1560] System Overview

[1561] This invention relates to a system that efficiently manages cloud server resources and utilizes generative artificial intelligence models to provide chat services, customer support, voice dialogue, and automatic content generation for users. Specific embodiments of this system are described below.

[1562] Hardware and Software Used

[1563] Hardware:

[1564] Smartphone

[1565] Cloud infrastructure (e.g. AWS, GCP)

[1566] software:

[1567] Programming languages: Python, Java (server side), Swift / Kotlin (mobile apps)

[1568] Frameworks: TensorFlow (generative AI model), Flask / Django (server-side API)

[1569] Libraries: NLTK, Spacy (natural language processing)

[1570] API: Google Cloud Speech-to-Text, Google Cloud Text-to-Speech

[1571] Processing Overview

[1572] 1. Cloud server resource management

[1573] The server measures the number of people using the cloud server at regular intervals and calculates the required amount of resources based on the data. Before resources become overloaded, it automatically launches new instances and adds the necessary CPU, memory, and storage. It also reduces costs by automatically releasing unnecessary instances when usage decreases.

[1574] 2. AI chat support

[1575] When a user sends a message to customer support from their device, the message is forwarded to the AI ​​model, which generates a response appropriate to the inquiry and sends it back to the device. This response is then displayed in the chat window, allowing the user to receive a prompt reply.

[1576] Example prompt sentence:

[1577] User: I want to know more about this product

[1578] AI model response: We will provide you with detailed product information. The main features of this product are...

[1579] 3. Automated content generation

[1580] The server periodically sends new product data to the AI ​​model and receives the generated product descriptions and recommendations. The generated content is automatically updated in the device application, ensuring that the latest information is always provided.

[1581] Example prompt sentence:

[1582] Generate a testimonial for your new smartphone

[1583] AI model response:

[1584] This latest smartphone is packed with innovative features and beautiful design, most notably...

[1585] 4. Voice support

[1586] When a user taps the microphone icon to start voice input, the recorded voice is converted into text by Google Cloud Speech-to-Text. The generated text is sent to an AI model, which returns an appropriate response. Google Cloud Text-to-Speech then generates audio data and plays it back on the device, allowing users to enjoy natural voice interaction.

[1587] The combination of these measures enables efficient operation of cloud servers, fast customer support, automated content generation and voice interaction, significantly reducing the operating costs of online services and providing a high-quality user experience.

[1588] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1589] Step 1:

[1590] The server measures the number of people using the cloud server at regular intervals. The input is the current number of active users, and the output is the calculated amount of resources required. This measurement is based on server log data and real-time access data. Specifically, the current number of active users is obtained by analyzing the server's access log.

[1591] Step 2:

[1592] The server calculates the required amount of resources based on the number of active users measured, and automatically adjusts the server instances. The input is the number of active users data output from Step 1, and the output is information about the instances to be newly added or released. Specifically, AWS's Auto Scaling function is used to dynamically add or reduce the required CPU and memory.

[1593] Step 3:

[1594] The device receives customer support messages from users and sends them to the AI ​​model. The input is the message entered by the user into the device, and the output is a prompt for the generative artificial intelligence model. Specifically, when the user enters a message and presses the send button, the message is transferred to the AI ​​model via the server.

[1595] Step 4:

[1596] The server receives the response generated by the AI ​​model and sends it to the terminal. The input is the response data generated by the AI ​​model, and the output is data in the format displayed in the chat window. Specifically, the AI ​​model generates a response appropriate to the inquiry content and sends it to the terminal in JSON format.

[1597] Step 5:

[1598] The server periodically sends new product data to the AI ​​model and receives the generated product descriptions and recommendations. The input is product attribute data, and the output is the generated product descriptions and recommendation lists. Specifically, information from the product database is periodically pushed to the AI ​​model to generate new descriptions and recommendation lists.

[1599] Step 6:

[1600] The device displays product descriptions and recommendations received from the server. The input is the generated data transferred from the server, and the output is the content displayed on the device's UI. Specifically, the generated descriptions and recommended item lists are rendered in the display area within the app.

[1601] Step 7:

[1602] The user starts voice input, and the device converts the recorded voice into text using the Google Cloud Speech-to-Text API. The input is the user's voice data, and the output is text data. Specifically, voice recording begins when the microphone button is pressed, and the recorded data is sent to the cloud API and converted into text.

[1603] Step 8:

[1604] The user's speech, converted into text, is sent to an AI model to generate an appropriate voice response. The input is text data, and the output is the response text data. Specifically, the converted text is sent to the AI ​​model as a prompt, and an appropriate reply is generated.

[1605] Step 9:

[1606] The server uses the Google Cloud Text-to-Speech API to convert the generated text data into audio data and send it to the device. The input is the text data of the response content, and the output is audio data. Specifically, the generated response text is sent to the cloud API, which generates an audio file and sends it to the device.

[1607] Step 10:

[1608] The device plays back the received voice data and provides it to the user. The input is the voice data sent from the server, and the output is the user's auditory feedback. Specifically, the received voice file is provided to the user using the playback function, realizing natural voice interaction.

[1609] 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.

[1610] The system of the present invention provides a more interactive and personalized experience by combining automatic resource adjustment according to the number of cloud server users, automated user support using a generative artificial intelligence model, and automatic generation of in-game content with an emotion engine that recognizes user emotions.

[1611] The operation process of the system of the present invention will be specifically described below.

[1612] Cloud Server Management

[1613] server

[1614] The server measures the current number of active users at regular intervals.

[1615] Example: The server measures the number of active users every hour and adjusts resources based on that number. For example, if the number of active users decreases at night, unnecessary instances are automatically released to reduce costs.

[1616] The server calculates the amount of resources needed based on the number of active users.

[1617] Example: If the number of active users increases, the server will launch new instances and instantly add the required CPU, memory, and storage.

[1618] Leveraging generative AI models

[1619] Terminal

[1620] The device receives requests from users and sends them to the AI ​​model.

[1621] Example: When a user sends a message to customer support, the device forwards the message to the AI ​​model, which then generates a response appropriate to the inquiry and sends it back to the device.

[1622] The terminal displays the generated response to the user.

[1623] Example: The device displays responses from the AI ​​model in a chat window, providing the user with a quick response.

[1624] Automatic updates

[1625] server

[1626] The server periodically sends game data to the AI ​​model.

[1627] Example: Every weekend, the server collects game data and pushes it to an AI model, which uses this data to generate new stages and character dialogue.

[1628] The server reflects the generated content in the game.

[1629] Example: The server integrates new content returned by the AI ​​model into the existing game data and automatically applies updates.

[1630] Utilizing the Emotion Engine

[1631] Terminal

[1632] The device recognizes emotions from the user's voice and text.

[1633] Example: The device analyzes messages typed by the user in a chat interface and the content of voice calls to detect the user's emotions.

[1634] server

[1635] The server then tailors responses for chat services and customer support based on the perceived emotion.

[1636] For example: If the emotion engine detects "anger" or "sadness," the server may change the response to be more polite and comforting. Conversely, if it detects "joy" or "excitement," the server may adjust the response to a friendlier tone.

[1637] Terminal

[1638] The device changes the movements and expressions of the in-game characters in real time according to the user's emotions.

[1639] Example: If the device's emotion engine recognizes that the user is sad, it will change the in-game character to make comforting gestures and say comforting lines.

[1640] Voice support

[1641] Terminal

[1642] The device will activate the AI ​​voice bot when triggered by user action.

[1643] Example: When a user interacts with a specific character, the device detects when the "speak" button is pressed and sends text to an AI voice bot.

[1644] server

[1645] The server generates voice data using an AI voice bot.

[1646] Example: The server uses a speech synthesis model to generate an audio file based on the text sent and sends it back to the device.

[1647] Terminal

[1648] The terminal plays the generated audio data to the user.

[1649] Example: The device plays the generated audio data so that the user can hear it.

[1650] As a result, the system of the present invention achieves effective resource management of cloud servers, automated user response through generative AI models, and interactive and emotionally responsive experiences through an emotion engine, which significantly reduces operational costs and alleviates the burden on human resources.

[1651] The processing flow will be explained below.

[1652] Cloud Server Management

[1653] Step 1: Measure active users

[1654] The server measures the current number of active users at regular intervals.

[1655] Example: The server checks and aggregates the session information of active users every hour, thereby determining the real-time number of users.

[1656] Step 2: Calculate resources

[1657] The server calculates the amount of resources needed based on the number of active users.

[1658] Example: A server calculates how many additional resources (CPU, memory, storage) to add when the number of active users exceeds a certain threshold (e.g., 500 users).

[1659] Step 3: Performing scaling

[1660] The server uses auto-scaling to adjust resources.

[1661] Example: Servers launch new instances to add necessary resources as the number of users increases, while unnecessary instances are stopped to reduce costs when the number of users decreases.

[1662] Leveraging generative AI models

[1663] Step 1: Get the user request

[1664] The terminal receives a request from the user.

[1665] Example: When a user contacts customer support, the device receives the message.

[1666] Step 2: Send to AI model

[1667] The device sends the user request to the AI ​​model.

[1668] Example: The device sends the received message to the API endpoint of the AI ​​model, initiating processing to generate an appropriate response.

[1669] Step 3: Generation by AI model

[1670] The server receives the response generated by the AI ​​model.

[1671] Example: The server receives and stores the response message generated by the AI ​​model.

[1672] Step 4: Deliver to users

[1673] The terminal returns the generated response to the user.

[1674] Example: The device displays a reply message from the AI ​​model on the chat interface and provides it to the user.

[1675] Automatic updates

[1676] Step 1: Collect data

[1677] The server periodically collects the latest game data.

[1678] Example: Every weekend, the server collects game configuration files, character data, stage information, etc.

[1679] Step 2: Prepare data for transmission

[1680] The server prepares to send the collected game data to the AI ​​model.

[1681] Example: The server formats the data in a way that is easy for the AI ​​model to parse.

[1682] Step 3: Generation by AI model

[1683] The server sends game data to the AI ​​model and requests it to generate new content.

[1684] Example: An AI model generates new levels and character dialogue and sends it back to the server.

[1685] Step 4: Reflecting content

[1686] The server reflects the generated new content in the game.

[1687] Example: The server integrates new content returned by the AI ​​model into the existing game data and updates it so that the new content is immediately available to the user.

[1688] Utilizing the Emotion Engine

[1689] Step 1: Collecting emotion data

[1690] The device recognizes emotions from the user's voice and text.

[1691] Example: The device analyzes messages entered by the user in a chat interface to detect the user's emotions (happiness, sadness, anger, excitement).

[1692] Step 2: Generate an emotion-based response

[1693] The server adjusts the response content based on the user's emotions recognized by the emotion engine.

[1694] Example: If the server detects "anger," it might make its response polite and comforting, but if it detects "happiness," it might use a friendlier tone.

[1695] Step 3: Generate emotion-based content

[1696] The server dynamically generates content within the game according to the user's emotions.

[1697] Example: If the user is sad, an in-game character can automatically generate comforting lines and actions.

[1698] Voice support

[1699] Step 1: Detecting trigger words

[1700] The device detects whether the user has used a specific trigger word.

[1701] Example: The device monitors and detects trigger words such as "talk" in a chat interface.

[1702] Step 2: Launch your AI voicebot

[1703] The device will activate an AI voice bot if it detects a trigger word.

[1704] Example: The device sends the detected trigger word to an AI voice bot to start the voice synthesis process.

[1705] Step 3: Speech generation

[1706] The server generates voice data using an AI voice bot.

[1707] Example: The server inputs the submitted text data into a speech synthesis model and saves the generated audio file.

[1708] Step 4: Streaming audio data

[1709] The terminal provides the generated voice data to the user.

[1710] Example: The device plays the generated audio data so that the user can hear it.

[1711] Example 2

[1712] 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."

[1713] Conventional cloud server systems face challenges in efficient resource management, making it difficult to flexibly adjust and respond to user usage and emotions. They also lack the ability to automatically generate in-game content and provide interactive experiences based on user emotions. This has resulted in high system operating costs and limited user experience.

[1714] 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.

[1715] In this invention, the server includes means for automatically adjusting resources in real time according to the number of cloud server users, means for automating user chat services and customer support responses using a generative artificial intelligence model, means for automatically generating in-game content and updates using a generative artificial intelligence model, means for recognizing emotions from user voice and text using an emotion recognition engine and adjusting response content based on the emotions, and means for converting text into voice data based on user operations using a speech synthesis engine and playing the voice data back to the user. This enables efficient resource management and cost reduction, and makes it possible to provide users with a more interactive and personalized experience.

[1716] A "cloud server" is a computer server that provides remote computer resources accessible over the Internet.

[1717] "Real-time" is a term that refers to events and data processing occurring as soon as they occur.

[1718] "Resources" are the hardware and software capabilities that a computer system provides, such as computation, memory, and storage.

[1719] A "generative artificial intelligence model" is an algorithm and machine learning model that automatically generates data and information based on instructions given by humans.

[1720] "Chat service" is a communication service that allows sending and receiving text messages in real time.

[1721] "Customer Support" means services that provide assistance to customers with questions or problems.

[1722] An "emotion recognition engine" is an algorithm and system for analyzing and recognizing emotions from human voice and text.

[1723] A "speech synthesis engine" is a technology and program for converting text data into voice data.

[1724] "Scaling" is the process of increasing or decreasing a system's processing power or resources to adapt to load or demand.

[1725] An "instance" is an individual execution environment for virtual machines and computer resources that run on a cloud server.

[1726] The present invention is a system that utilizes a cloud server to efficiently manage resources based on the user's usage status and emotions, and combines a generative artificial intelligence model and an emotion recognition engine to provide an advanced user experience.

[1727] First, the server uses the cloud provider's monitoring tools (for example, a general cloud management service) to measure the current number of active users at regular intervals. Based on the measured number of active users, the server calculates the amount of resources required and automatically adjusts the resources. Specifically, this involves adding or removing virtual machine instances using a scaling policy.

[1728] Next, the device receives the user's request and sends it to a generative artificial intelligence model (e.g., a general-purpose generative AI model). When the user sends a message to customer support, the content is sent to the generative AI model, which generates an appropriate response. For example, if the user asks, "I'd like to return an item. What should I do?", the generative AI model will generate a response such as, "We will inform you of the return procedure. First, please fill out the return form."

[1729] Furthermore, the server periodically collects the latest game data and sends it to the generative AI model, which then generates new stages and character dialogue and integrates them with the existing game data, updating the game database and automatically distributing the updates to the server.

[1730] The device analyzes the user's voice and text and recognizes the user's emotions using an emotion recognition engine (e.g., a general emotion analysis service). This emotion information is sent to the server and used to adjust the response content and the in-game character's movements and facial expressions in real time. For example, if the user types "Today was a tough day," the emotion recognition engine recognizes this as "sadness," and the in-game character will say encouraging words like "Cheer up!"

[1731] Furthermore, the device activates a speech synthesis engine in response to a user operation, converts the text into voice data, and plays it back to the user. For example, when the user presses the "speak" button, the text is sent to the speech synthesis engine, and the generated voice data is played back.

[1732] This allows the system of the present invention to achieve efficient resource management, reduce costs, and provide users with an interactive and personalized experience.

[1733] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1734] Step 1:

[1735] The server uses the cloud provider's monitoring tool to measure the current number of active users at regular intervals. Specifically, it periodically retrieves metric data generated by the monitoring tool and analyzes the data with a Python script.

[1736] Input: Metric data from cloud provider monitoring tools

[1737] Output: Analysis result of current number of active users

[1738] Step 2:

[1739] The server calculates the required amount of resources based on the number of active users measured, and automatically adds or removes virtual machine instances using a scaling policy, specifically using an auto-scaling function such as AWS Lambda.

[1740] Input: Number of active users

[1741] Output: Instances added or removed due to resource throttling

[1742] Step 3:

[1743] The user sends a message to customer support through the device, which receives the user's request and sends it to the generative AI model.

[1744] Input: Customer support message from the user

[1745] Output: The request sent to the generative AI model

[1746] Step 4:

[1747] The generative AI model generates a response appropriate to the user's request and returns the response to the device. Specifically, the generative AI model uses natural language processing to generate text appropriate to the inquiry.

[1748] Input: Customer Support Request

[1749] Output: Generated customer support response text

[1750] Step 5:

[1751] The device displays the response returned by the generative AI model to the user, specifically, by displaying the generated response in a chat window.

[1752] Input: Response text from the generative AI model

[1753] Output: Response displayed in the chat window

[1754] Step 6:

[1755] The server periodically collects the latest game data and sends it to the generative AI model, which then converts the collected game data into JSON format and sends it to the AI ​​model.

[1756] Input: Latest game data

[1757] Output: Game data sent to the AI ​​model

[1758] Step 7:

[1759] The generative AI model generates new game content (e.g., stages and character dialogue) and sends that content back to the server.

[1760] Input: Game data

[1761] Output: Generated game content

[1762] Step 8:

[1763] The server integrates the generated new game content into the existing game database and automatically updates the game data.

[1764] Input: Generated game content

[1765] Output: Updated game database

[1766] Step 9:

[1767] The device sends the user's voice and text to an emotion recognition engine to analyze the user's emotions. Specifically, the device sends the voice and text to an emotion analysis service to obtain emotional information.

[1768] Input: User voice or text

[1769] Output: Parsed emotion information

[1770] Step 10:

[1771] The server adjusts the response based on the analyzed user's emotions. For example, if the emotion recognition engine detects "sadness," it changes the response to something comforting.

[1772] Input: Parsed emotion information

[1773] Output: Adjusted response content

[1774] Step 11:

[1775] The user interacts with the in-game character through the device, which then changes the character's behavior and facial expressions in real time based on the user's emotional information. Specifically, the device controls the character's behavior using the game engine's API.

[1776] Input: User's emotional information

[1777] Output: Modified character movements and expressions

[1778] Step 12:

[1779] The device activates a speech synthesis engine in response to user operations and converts text into voice data. Specifically, when the user presses the "speak" button, the device sends the text to the speech synthesis engine.

[1780] Input: User text input

[1781] Output: Generated audio data

[1782] Step 13:

[1783] The terminal plays the generated audio data to the user. Specifically, it plays the audio file in a streaming format and lets the user listen to it.

[1784] Input: Generated audio data

[1785] Output: The audio played to the user

[1786] The above is the specific processing flow of this system.

[1787] (Application example 2)

[1788] 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."

[1789] Conventional food delivery services have faced issues with server resource shortages during sudden user increases, resulting in service delays and outages. Furthermore, customer support has been handled manually, resulting in issues of delayed responses and inconsistent quality. Furthermore, personalized responses based on user sentiment are required, but the means to achieve this have been limited. Even with voice support, only text-based support was available, limiting the user experience.

[1790] 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 automatically adjusting resources in real time according to the number of cloud server users, means for automating user chat services, customer support, and other responses using a generative artificial intelligence model, means for automatically generating in-game content and updates using a generative artificial intelligence model, means for using an emotion engine to recognize user emotions and adjust responses, and means for generating and playing voice data using a generative artificial intelligence model in response to user operations as a voice response. This makes it possible for food delivery services to provide stable service even to a rapidly increasing number of users and to realize interactive and personalized responses that correspond to user emotions.

[1791] A "cloud server" is a collection of server resources provided over the Internet, and is a remote computing environment for storing and processing data.

[1792] "Automatic resource adjustment" is a function that dynamically changes the allocation of computer resources such as servers and storage according to current usage.

[1793] A "generative artificial intelligence model" is an AI model that has the ability to learn implicit rules and patterns and generate new data such as text, images, and audio based on given input.

[1794] "Chat service" refers to a means of communication for exchanging messages in real time, and is intended to enable users to exchange information with each other and between users and support staff.

[1795] "Customer support" refers to services that assist customers in resolving inquiries and problems.

[1796] "In-game content" refers to elements such as stages, characters, items, and dialogue that are provided for the enjoyment of game players.

[1797] An "emotion engine" is a system that determines emotions from a user's voice or text and adjusts the response accordingly.

[1798] "Voice support" is a function that enables interaction using voice data generated based on user operations.

[1799] An "instance" is a unit of computer resources that runs as a virtual machine or container in a cloud environment.

[1800] "Scaling" refers to the act of adding or removing resources to increase or decrease the performance or capacity of a system.

[1801] This invention is a system that provides an interactive and personalized experience in a food delivery service by automatically adjusting cloud server resources, automating customer support using a generative artificial intelligence model, and improving user response using an emotion engine.

[1802] Cloud Server Management

[1803] server

[1804] The server measures the current number of active users at regular intervals. For example, it measures the number of active users every hour and adjusts resources based on that number. For example, if the number of active users decreases at night, unnecessary instances are automatically deactivated to reduce costs.

[1805] The server calculates the amount of resources needed based on the number of active users. For example, if the number of active users increases, the server will launch new instances and instantly add the required CPU, memory, and storage.

[1806] Leveraging generative AI models

[1807] Terminal

[1808] The device receives requests from users and sends them to the generative AI model. For example, when a user sends a message to customer support, the content is forwarded to the generative AI model. The generative AI model then generates a response appropriate to the inquiry and sends it back to the device.

[1809] The device displays the generated response to the user. For example, the device displays the response from the generative AI model in a chat window, providing the user with a quick reply.

[1810] Utilizing the Emotion Engine

[1811] Terminal

[1812] The device recognizes emotions from the user's voice and text. For example, the device analyzes messages typed by the user in a chat interface or the content of voice calls to detect the user's emotions.

[1813] server

[1814] The server adjusts the content of responses from chat services and customer support based on the recognized emotions. For example, if the emotion engine detects "anger" or "sadness," it changes the response to be more polite and comforting. Conversely, if it detects "joy" or "excitement," it adjusts the response to a friendlier tone.

[1815] Voice support

[1816] Terminal

[1817] The device generates voice data based on the generative AI model in response to user actions. For example, if a user types "Please tell me the status of my order," the device sends the text to the generative AI model, which then converts the resulting text into speech.

[1818] server

[1819] The server generates voice data using a generative AI model. For example, the server uses a speech synthesis model to generate an audio file based on the text sent to it and sends it back to the device.

[1820] Terminal

[1821] The terminal plays the generated audio data to the user. In a specific example, the terminal plays the generated audio data so that the user can hear it.

[1822] Examples of concrete examples and prompts

[1823] As a concrete example, if a user sends the message "Please tell me the status of my order," the system will act as follows:

[1824] 1. The number of active users is checked and the required resources are adjusted.

[1825] 2. The emotion "excitement" is recognized from the user's text, and a positive response is generated: "Great! How can I assist you today?"

[1826] 3. The generated text is converted into speech and played back to the user.

[1827] Example prompt sentence:

[1828] User: "What's the status of my order?"

[1829] Sentiment analysis result: Positive

[1830] Response: "Great! How can I assist you today?"

[1831] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1832] Step 1:

[1833] The server measures the current number of active users at regular intervals. The measured number of active users becomes input data. Based on this data, the server adjusts resources. For example, if the number of active users decreases at night, it automatically deactivates unnecessary instances to reduce costs.

[1834] Step 2:

[1835] The server calculates the required resources based on the number of active users it measures. This calculation results in output data. If the number of active users increases, the server launches new instances, providing additional CPU, memory, and storage immediately.

[1836] Step 3:

[1837] The device receives requests from users and sends the contents of those requests to the generative AI model. The contents of those requests become input data. Specifically, when a user sends a message to customer support, the contents of that message are forwarded to the generative AI model.

[1838] Step 4:

[1839] The generative AI model generates an appropriate response based on the received request. The generated response becomes the output data. This response is sent back to the device. For example, in response to a request such as "Please tell me the status of my order," the generative AI model generates a response such as "Sorry for the wait. Your order is currently being delivered."

[1840] Step 5:

[1841] The device receives the response from the generative AI model and displays it to the user. This response message serves as input data. For example, the device displays this message in a chat window to provide the user with a prompt reply.

[1842] Step 6:

[1843] The device recognizes emotions from the user's voice and text. Input data is messages typed by the user in the chat interface or the contents of voice calls. The device sends this to the emotion engine, which analyzes the user's emotions.

[1844] Step 7:

[1845] The emotion engine analyzes input data and generates output data based on the recognized emotions. The server receives the results and adjusts the chat service or customer support response. For example, if the emotion engine detects "anger," it can change the response to be more polite and comforting.

[1846] Step 8:

[1847] The device generates voice data based on the generative AI model in response to user actions. The text sent by the user is the input data. This text is sent to the generative AI model to generate voice data.

[1848] Step 9:

[1849] The server generates voice data using a generative AI model. The text data is the input data, and the voice file is the output data. The generated voice file is sent back to the device.

[1850] Step 10:

[1851] The terminal plays the generated voice data to the user. The voice data is input data, and the voice is played back so that the user can hear it. As a specific example, in response to a user request such as "Please tell me the status of my order," the voice response played back is "Sorry to keep you waiting. Your order is currently being delivered."

[1852] 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.

[1853] 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.

[1854] 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.

[1855] 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.

[1856] 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.

[1857] 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.

[1858] 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).

[1859] 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.

[1860] 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."

[1861] 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.

[1862] 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).

[1863] 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.

[1864] 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.

[1865] 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.

[1866] 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.

[1867] 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.

[1868] 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.

[1869] 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.

[1870] 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.

[1871] 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.

[1872] 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.

[1873] The following is further disclosed regarding the above embodiment.

[1874] (Claim 1)

[1875] A means to automatically adjust resources in real time according to the number of cloud server users,

[1876] Using generative artificial intelligence models to automate user chat services and customer support,

[1877] A means for automatically generating in-game content and updates using generative artificial intelligence models; and

[1878] A system including:

[1879] (Claim 2)

[1880] A means for measuring resources and calculating the amount of resources based on the number of users of the cloud server;

[1881] 10. The system of claim 1, further comprising means for automatically adjusting the server instances based on scaling.

[1882] (Claim 3)

[1883] 2. The system according to claim 1, further comprising means for automatically generating new stages, characters and character dialogue using a generative artificial intelligence model.

[1884] (Claim 4)

[1885] 10. The system of claim 1, further comprising means for generating chat dialogues for customer support using a generative artificial intelligence model.

[1886] (Claim 5)

[1887] 10. The system of claim 1, further comprising means for activating a speech synthesis model in response to a specific trigger word to generate speech data.

[1888] "Example 1"

[1889] (Claim 1)

[1890] A means to automatically adjust resources in real time according to the number of cloud server users,

[1891] Using generative artificial intelligence models to automate user chat services and customer support,

[1892] A means for automatically generating in-game content and updates using generative artificial intelligence models; and

[1893] a means for providing voice interaction functionality using a generative artificial intelligence model;

[1894] A system including:

[1895] (Claim 2)

[1896] A means for measuring resources and calculating the amount of resources based on the number of users of the cloud server;

[1897] 10. The system of claim 1, further comprising means for automatically adjusting the server instances based on scaling.

[1898] (Claim 3)

[1899] 2. The system according to claim 1, further comprising means for automatically generating new stages, characters and character dialogue using a generative artificial intelligence model.

[1900] (Claim 4)

[1901] The system according to claim 1, further comprising: means for generating speech using a generative artificial intelligence model in response to a user's operation as a trigger; and means for providing the generated speech data to the user.

[1902] "Application Example 1"

[1903] (Claim 1)

[1904] A means to automatically adjust resources in real time according to the number of cloud server users,

[1905] Using generative artificial intelligence models to automate user chat services and customer support,

[1906] means for automatically generating online content and updates using generative artificial intelligence models;

[1907] means for generating voice data using a generative artificial intelligence model and providing a voice dialogue;

[1908] A system including:

[1909] (Claim 2)

[1910] A means for measuring resources and calculating the amount of resources based on the number of users of the cloud server;

[1911] 10. The system of claim 1, further comprising means for automatically adjusting the server instances based on scaling.

[1912] (Claim 3)

[1913] 10. The system of claim 1, further comprising means for automatically generating new product descriptions, reviews, and recommendations using a generative artificial intelligence model.

[1914] "Example 2: Combining Emotion Engines"

[1915] (Claim 1)

[1916] A means to automatically adjust resources in real time according to the number of cloud server users,

[1917] Using generative artificial intelligence models to automate user chat services and customer support,

[1918] A means for automatically generating in-game content and updates using generative artificial intelligence models; and

[1919] a means for using an emotion recognition engine to recognize emotions from a user's voice or text and tailoring responses based on the emotions;

[1920] a means for converting the text into speech data based on user actions using a speech synthesis engine and playing it back to the user;

[1921] A system including:

[1922] (Claim 2)

[1923] A means for measuring resources and calculating the amount of resources based on the number of users of the cloud server;

[1924] a means for automatically adjusting the server instances based on scaling;

[1925] a means for periodically collecting game data and transmitting it to the generative artificial intelligence model;

[1926] A means for integrating the generated in-game content into game data and reflecting it;

[1927] 10. The system of claim 1, comprising:

[1928] (Claim 3)

[1929] A means for automatically generating new stages, characters, and character lines using a generative artificial intelligence model;

[1930] A way to change the behavior and facial expressions of in-game characters in real time according to the user's emotions,

[1931] 10. The system of claim 1, comprising:

[1932] "Application example 2 when combining emotion engines"

[1933] (Claim 1)

[1934] A means to automatically adjust resources in real time according to the number of cloud server users,

[1935] Using generative artificial intelligence models to automate user chat services and customer support,

[1936] A means for automatically generating in-game content and updates using generative artificial intelligence models; and

[1937] using an emotion engine to recognize user emotions and adjust responses;

[1938] For voice support, a means for generating and playing voice data using a generative artificial intelligence model triggered by user operation;

[1939] A system including:

[1940] (Claim 2)

[1941] A means for measuring resources and calculating the amount of resources based on the number of users of the cloud server;

[1942] Includes a means to automatically adjust server instances based on scaling

[1943] 10. The system of claim 1.

[1944] (Claim 3)

[1945] Includes means for automatically generating new stages, characters, and character dialogue using a generative artificial intelligence model.

[1946] 10. The system of claim 1. [Explanation of symbols]

[1947] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means to automatically adjust resources in real time according to the number of cloud server users, Using generative artificial intelligence models to automate user chat services and customer support, A means for automatically generating in-game content and updates using generative artificial intelligence models; and A system including:

2. A means for measuring resources and calculating the amount of resources based on the number of users of the cloud server; The system of claim 1 further comprising means for automatically adjusting the server instances based on scaling.

3. 2. The system according to claim 1, further comprising means for automatically generating new stages, characters and character lines using a generative artificial intelligence model.

4. 10. The system of claim 1, further comprising means for generating chat dialogues for customer support using a generative artificial intelligence model.

5. 2. The system of claim 1, further comprising means for activating a speech synthesis model in response to a specific trigger word to generate speech data.

Images