system

Abstract

We provide the system. [Solution] A means of receiving a message, A means for analyzing the aforementioned message and extracting the request, A means for selecting the optimal generation AI service based on the aforementioned requirements, A means for sending a request to the aforementioned generation AI service, Means for receiving generation results from the aforementioned generation AI service, A means for returning the aforementioned generation result to the user, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Among a variety of generative AI services, users often have trouble choosing which service to use, and as a result, there are many cases where they do not reach specific service usage. Also, it is a problem that it takes time for users to operate multiple generative AI services individually. This hinders efficient content generation by generative AI. [[ID=三十七]]

Means for Solving the Problems

[0005] The present invention solves the above problems by providing a system that includes means for receiving messages, means for analyzing messages and extracting requests, means for selecting the optimal generation AI service based on the requests, means for sending requests to generation AI services, means for receiving generation results from generation AI services, and means for returning the generation results to the user. As a result, the user can access multiple generation AI services from a single point of contact, and the selection of appropriate services and the sending of requests are performed automatically, thus simplifying the use of generation AI. Furthermore, by including means for post-processing of the generation results, the final generation results will better suit the user's requirements.

[0006] A "message" is text information that a user sends to a system, containing content or requests that they wish to have generated.

[0007] "Means of receiving" refers to a part of a system that has the functionality to receive messages from users.

[0008] "Means of analysis" refers to a part of a system that has the function of analyzing received messages using natural language processing technology to understand their content and intent.

[0009] "Requests" refer to information extracted as a result of message analysis, indicating the purpose and content of a specific generative AI service that the user expects to use.

[0010] "Selection method" refers to a part of a system that has the function of selecting the most suitable one from among multiple generative AI services based on the analyzed requirements.

[0011] A "generative AI service" is an external service that provides artificial intelligence technology for generating specific content (such as videos, text, images, and audio).

[0012] A "request" is request information that includes instructions and data to request a specific generation process from the selected generation AI service.

[0013] "Generated results" refer to the output such as videos, text, images, and audio that the generation AI service creates in response to a user's request.

[0014] "Post-processing" refers to a function that performs additional processing on the generation results received from the generation AI service, such as format conversion or the addition of metadata. [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0018] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0019] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0023] [First Embodiment]

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

[0025] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0028] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0032] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0035] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0036] This invention provides a system that enables a user to utilize multiple generative AI services through a single interface. This system automatically performs a series of processes, including receiving and analyzing messages, selecting the optimal generative AI service, sending requests, receiving generation results, and returning them to the user.

[0037] A natural language explanation of the program's processing.

[0038] server

[0039] 1. Receive messages sent by the user from their device.

[0040] 2. The received message is analyzed using natural language processing (NLP) technology to extract the user's request.

[0041] 3. Based on the extracted requirements, select the optimal generation AI service. This selection will take into account the service's performance, past performance, and frequency of use.

[0042] 4. Create request data for the selected generative AI service and send the request.

[0043] 5. Receive the generated results (e.g., video, text, images, audio, etc.) from the generation AI service.

[0044] 6. If necessary, perform post-processing on the generated results (format conversion, metadata addition, etc.).

[0045] 7. The completed generation results are sent to the user's terminal and the user is notified.

[0046] terminal

[0047] 1. The user enters the content they want to generate and sends the message to the server.

[0048] 2. Receive notifications and generation results from the server and display them to the user.

[0049] User

[0050] 1. Enter the content you want to generate via your device.

[0051] 2. Check and use the generated results sent from the server.

[0052] Specific example

[0053] For example, suppose a user enters a message into their device saying, "I would like you to create a cute video of my cat," and sends it to the system.

[0054] The server receives the message and uses natural language processing technology to extract keywords such as "cat," "cute," and "video."

[0055] The server selects a generation AI service specifically designed for video generation. For example, video generation AI service A might be selected.

[0056] The server generates request data for creating a cute cat video and sends the request to AI generation service A.

[0057] AI generation service A generates a cute cat video in response to a request and sends the result back to the server.

[0058] The server receives the generated video, performs any necessary post-processing, and sends the final video to the user's device.

[0059] The device displays the received video to the user, allowing the user to view the generated cute cat video.

[0060] By implementing this invention, users can eliminate the need to individually manage each generation AI service and efficiently obtain their desired generation results from a single point of contact. This system significantly improves the convenience of generation AI technology.

[0061] The following describes the processing flow.

[0062] Step 1:

[0063] The user uses their device to enter a message containing the content they want generated. For example, they might enter, "I want a cute video of a cat."

[0064] Step 2:

[0065] The terminal receives the message entered by the user and sends that message data to the server.

[0066] Step 3:

[0067] The server receives the message sent from the terminal.

[0068] Step 4:

[0069] The server analyzes received messages using natural language processing (NLP) techniques. Specifically, it extracts keywords and context from messages to understand user requests. For example, it might extract keywords such as "cat," "cute," and "video."

[0070] Step 5:

[0071] The server selects the optimal generation AI service based on the analysis results. Selection criteria include service performance, past performance, and frequency of use. Example: Select generation AI service A, which specializes in video generation.

[0072] Step 6:

[0073] The server generates request data for the selected generation AI service. The request data includes details of the content the user wants generated (e.g., specific instructions for generating a cute cat video).

[0074] Step 7:

[0075] The server sends the generated request data to the selected generation AI service. Example: Send a request to generation AI service A.

[0076] Step 8:

[0077] The generation AI service performs generation processing based on the request and creates the generated result. Example: Generate a cute video of a cat.

[0078] Step 9:

[0079] The AI ​​generation service sends the generated results back to the server.

[0080] Step 10:

[0081] The server receives the generated results. Example: Receives a cute cat video from AI generation service A.

[0082] Step 11:

[0083] If necessary, the server performs post-processing on the generated results. For example, this may include format conversion or the addition of metadata.

[0084] Step 12:

[0085] The server sends the final generation result to the user's terminal.

[0086] Step 13:

[0087] The device receives the generated result sent from the server. Example: It receives a cute video of a cat.

[0088] Step 14:

[0089] The device displays the generated result to the user. The user can then view the generated video.

[0090] (Example 1)

[0091] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0092] Currently, for users to utilize multiple generative AI services, they need to access each service individually and configure and operate each platform separately. This is time-consuming and inefficient for users. Furthermore, understanding the performance and characteristics of each generative AI service and selecting the appropriate one is difficult, making it challenging to obtain optimal results.

[0093] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0094] In this invention, the server includes means for receiving messages, means for analyzing messages and extracting requests, means for selecting the optimal generative artificial intelligence service, means for sending requests to the generative artificial intelligence service, means for receiving generation results from the generative artificial intelligence service, means for performing post-processing on the generation results as necessary, and means for sending and notifying the user terminal of the generation results. This enables the user to efficiently utilize multiple generative AI services through a single interface and obtain the optimal generation result.

[0095] "Means for receiving messages" refers to a function that receives messages sent from a user terminal and processes their content.

[0096] "Means for analyzing messages and extracting requests" refers to a function that uses natural language processing technology to analyze received messages and clearly extract the user's requirements.

[0097] "Means for selecting the optimal generative artificial intelligence service" refers to a function that selects the optimal generative AI service based on extracted requirements, taking into account performance, past performance, frequency of use, etc.

[0098] "Means for sending requests to a generative artificial intelligence service" refers to a function for sending request data in accordance with the user's request to a selected generative AI service.

[0099] "Means for receiving generation results from a generation artificial intelligence service" refers to a function for receiving generation results sent from a generation AI service.

[0100] "Means for performing post-processing on the generated results as needed" refers to functions for performing post-processing on the received generated results, such as format conversion or the addition of metadata.

[0101] "Means for sending and notifying the user of the generation results" refers to a function for sending the post-processed generation results to the user's terminal and notifying the user.

[0102] This invention provides a system that enables users to efficiently utilize multiple generative AI services through a single interface. This system consists of a server, a terminal, and a user, and automatically performs a series of processes.

[0103] Hardware and software configuration

[0104] server

[0105] Message reception: The server receives messages sent by the user from their terminal.

[0106] Message analysis: Received messages are analyzed using natural language processing (NLP) techniques (e.g., SpaCy or NLTK library) to extract user requests.

[0107] Service Selection: Based on the extracted requirements, the optimal generative artificial intelligence service will be selected considering performance, track record, frequency of use, etc. Specifically, OpenAI® or similar services will be used for the generative AI model.

[0108] Request data creation: Create request data for the selected generative AI service and send the data, including the prompt message.

[0109] Result reception: Receives generated results from the generation AI service, including in formats such as video, text, images, and audio.

[0110] Post-processing: Perform post-processing as needed, such as format conversion or metadata addition. For example, use FFmpeg to convert the video format.

[0111] Notification / Sending: The completed generation results are sent to the user's terminal, and the user is notified that the results have been generated.

[0112] terminal

[0113] Message Input and Sending: The user inputs the content they want to generate via their terminal and sends the message to the server.

[0114] Result Reception and Display: Receives results and displays them to the user. For example, if the user enters "I want a cute video of a cat," the results will be displayed on the device.

[0115] User

[0116] Content Input: The user enters the content they want to generate into the terminal. Specifically, they enter prompt messages such as "Please create a cute video of a cat" or "Please generate a photo of a flower field."

[0117] Confirmation and Use of Generated Results: Users can confirm and use the generated results.

[0118] Specific example

[0119] For example, a user might type a message into their device saying, "I want you to create a cute video of my cat," and send it to the system.

[0120] The server receives the message and uses natural language processing technology to analyze and extract keywords such as "cat," "cute," and "video."

[0121] The server selects a generation AI service suitable for video generation, for example, a video generation AI, which is one of the generation AI models.

[0122] The server creates request data that includes the prompt "Please create a cute video of a cat" and sends it to the AI ​​generation service.

[0123] The AI ​​generation service generates cute cat videos in response to requests and sends the results back to the server.

[0124] The server receives the generated results, performs any necessary post-processing, and then sends the completed video to the user's device.

[0125] The device receives the results and displays the video to the user. The user can then watch the generated cute video of a cat.

[0126] This invention eliminates the need for users to individually manage each generation AI service, enabling them to efficiently obtain the desired generation results from a single interface. Furthermore, it significantly improves the convenience of generation AI technology.

[0127] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0128] Step 1: Receive message

[0129] The server receives messages sent from the terminal.

[0130] Input: The user sent a message saying, "I would like you to create a cute video of my cat."

[0131] Output: Received messages are saved on the server.

[0132] Step 2: Message analysis and request extraction

[0133] The server analyzes received messages using natural language processing (NLP) techniques. Specifically, it utilizes libraries such as SpaCy and NLTK.

[0134] Input: Received message: "I would like you to create a cute video of my cat."

[0135] Data processing: Extract keywords such as "cat," "cute," and "video" from the message.

[0136] Output: Extracted keywords: "cat", "cute", "video".

[0137] Step 3: Selecting a Generative AI Service

[0138] The server selects the optimal generation AI service based on the extracted keywords, taking into account factors such as performance, past performance, and frequency of use.

[0139] Input: Extracted keywords "cat", "cute", "video".

[0140] Data processing: Evaluate the characteristics of each generation AI service and select the optimal service.

[0141] Output: Selected generative AI service (e.g., video generation AI service).

[0142] Step 4: Create Request Data

[0143] The server creates request data for the selected generative AI service. It generates an appropriate request, including a prompt.

[0144] Input: User requirements and selected generation AI service.

[0145] Data processing: Generate request data that includes the prompt "Please create a cute video of a cat".

[0146] Output: Generated request data.

[0147] Step 5: Submit Request

[0148] The server sends the generated request data to the selected generation AI service.

[0149] Input: Generated request data.

[0150] Output: A request is sent to the generation AI service.

[0151] Step 6: Receive the generation result

[0152] The server receives the results generated from the AI ​​generation service.

[0153] Input: Generated results (e.g., video data) sent from a generation AI service.

[0154] Output: The received generation results are saved on the server.

[0155] Step 7: Post-processing

[0156] The server performs post-processing on the generated results as needed, such as format conversion or metadata addition. Specifically, it uses FFmpeg.

[0157] Input: Received generation result.

[0158] Data processing: Converting video formats and adding metadata.

[0159] Output: The generated result after post-processing is complete.

[0160] Step 8: Send Results and Notification

[0161] The server sends the post-processed results to the user's terminal and notifies the user that the results have been generated.

[0162] Input: The generated result after post-processing is complete.

[0163] Output: The generated result is sent to the user's terminal, and a notification is issued.

[0164] Step 9: Receive and display results

[0165] The terminal receives the generated results sent from the server and displays them to the user.

[0166] Input: The generated result sent from the server.

[0167] Output: The generated result will be displayed on the terminal.

[0168] Step 10: Confirm and use of generation results

[0169] The user checks the generated results displayed on the device and uses them.

[0170] Input: The generated result displayed on the terminal.

[0171] Output: The generated result is checked and used.

[0172] (Application Example 1)

[0173] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0174] Conventional generation AI services required users to individually select each service, submit requests, and receive results, resulting in a cumbersome operation. Furthermore, it was difficult for users to understand the characteristics and performance of each generation AI service, making it challenging to select the optimal service. Additionally, post-processing of the generation results required manual work, which was time-consuming and labor-intensive. This invention aims to solve these problems and provide a system that allows users to efficiently utilize generation AI services through a single interface.

[0175] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0176] In this invention, the server includes means for receiving messages, means for analyzing the messages and extracting requests, means for selecting the optimal generation AI service based on the requests, means for sending requests to the generation AI service, means for receiving generation results from the generation AI service, means for returning the generation results to the user, means for performing post-processing on the generation results, and means for performing product searches and suggestions on an e-commerce site. This enables users to efficiently utilize generation AI services from a single point of contact and effectively make use of the generation results.

[0177] A "message" is textual information sent by a user, including requests and instructions regarding the AI ​​generation service.

[0178] "Analysis" is the process of interpreting received messages based on natural language processing technology and extracting user requests.

[0179] A "request" refers to the actions or data that a user wants the AI ​​service to perform or generate.

[0180] A "generative AI service" is an external service or platform that uses AI technology to generate content such as text, images, audio, and video.

[0181] A "request" refers to data based on a request sent to a specific AI-generating service.

[0182] "Generation result" refers to the generated content information returned from the generation AI service.

[0183] "Return" refers to the process of returning the generated results received from the generation AI service back to the user.

[0184] "Post-processing" refers to the process of performing necessary format conversions and adding metadata to the generated results obtained from the generation AI service.

[0185] An "online shopping site" is an online platform where users can search for and purchase products via the internet.

[0186] "Product search" refers to the act of a user searching for a specific product or service on an e-commerce website.

[0187] "Recommendation" refers to the act of recommending appropriate products or services based on the user's needs and preferences.

[0188] This invention relates to a system that allows users to utilize multiple AI-generated services through a single interface. In particular, an example of its implementation as a smartphone application for product search and suggestions on an e-commerce site is provided.

[0189] System Configuration

[0190] The main components are a server and a terminal (smartphone). The server receives messages, analyzes their content, selects the optimal generation AI service, sends requests to the generation AI service, and receives the generation results. The terminal is responsible for receiving and displaying notifications and generation results from the server, as well as inputting the content the user wants to generate.

[0191] Hardware and software to be used

[0192] Server: Uses the Flask framework in Python to manage message reception and request sending.

[0193] Natural Language Processing (NLP) techniques: Message analysis is performed using spaCy in Python.

[0194] Generative AI services: External generative AI platforms (e.g., OpenAI's GPT-3®) can be used.

[0195] Smartphone applications: Developed using iOS or Android® development environments (Swift or Kotlin).

[0196] Data processing and calculation

[0197] The server processes the data in the following steps:

[0198] 1. Receive messages sent from the terminal and analyze them using NLP (Neuro-Linguistic Programming) technology. This analysis extracts the user's requests.

[0199] 2. Based on the extracted requirements, select the optimal generative AI service. Selection criteria include the performance and frequency of use of the generative AI service.

[0200] 3. Generate request data for the selected generative AI service and send the request.

[0201] 4. Receive the generation results from the generation AI service and perform post-processing on the results as needed. Post-processing includes data format conversion and metadata addition.

[0202] 5. Send the completed generation result to the terminal and notify the user.

[0203] Specific example

[0204] Let's say a user types "I'd like some suggestions for coordinating outfits for women's casual dresses" and sends it to the server.

[0205] The server receives the message and uses NLP technology to extract the keywords "women's casual dress" and "outfit."

[0206] The server selects a fashion-related AI service for generating data (e.g., a fashion suggestion AI service).

[0207] The server creates request data to generate a women's casual dress outfit and sends it to the generation AI service.

[0208] The generation AI service generates suggestions in response to requests and sends the results back to the server.

[0209] The server receives the generated list of suggestions, formats it into a specific format, and sends it to the user's terminal.

[0210] The device displays the list of suggestions received by the user, allowing the user to view the generated list and suggested coordinates.

[0211] Example of a prompt

[0212] User: Can you suggest some casual dress outfit ideas for women?

[0213] AI: I suggest the following three outfit combinations:...

[0214] In this way, users can easily utilize the generated AI service to efficiently perform tasks such as product searches and outfit suggestions on e-commerce sites.

[0215] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0216] Step 1:

[0217] The user enters the content they want to generate using their smartphone. In this case, the user enters "Please give me some ideas for coordinating casual dresses for women." The entered message is then sent to the server.

[0218] Step 2:

[0219] The server receives a message sent by a user. For example, it might receive the message, "Please give me some ideas for coordinating a casual dress for women." This message is then analyzed using natural language processing (NLP) techniques. Specifically, the Python library spaCy is used to extract keywords from the message. The input here is the user's message, and the output is the extracted keywords (e.g., "casual dress for women," "coordination").

[0220] Step 3:

[0221] The server selects the most suitable generative AI service based on the extracted keywords. For example, it might select a generative AI service specializing in fashion suggestions. Past performance and performance indicators are considered in the selection process. In this step, the input is the extracted keywords, and the output is the selected generative AI service (e.g., a fashion suggestion AI service).

[0222] Step 4:

[0223] The server generates request data for the selected AI service. This request data includes the user's request and other necessary metadata. The inputs here are the extracted keywords and the selected AI service, and the output is the generated request data.

[0224] Step 5:

[0225] The server sends the generated request data to the specified AI service. This is done by sending an HTTP request to the AI ​​service's API endpoint. The input here is the request data, and the output is the response from the AI ​​service (the generated suggestion result).

[0226] Step 6:

[0227] The system receives generation results (suggestions) from the generation AI service. The received generation results are temporarily stored on the server, and post-processing is performed as needed. Post-processing includes data format conversion and metadata addition. The input here is the generation result from the generation AI service, and the output is the post-processed generation result.

[0228] Step 7:

[0229] The server returns the post-processed generated results to the user's device. The final data is sent to the user's smartphone app in JSON format or similar. Here, the input is the post-processed generated results, and the output is the notification and display on the user's device.

[0230] Step 8:

[0231] The user checks the generated results displayed on the device. For example, they can see the generated "Women's Casual Dress Coordination Suggestions" on their smartphone screen. In this step, the input is the generated results received by the device, and the output is the user's confirmation action.

[0232] Through these steps, users can easily utilize the AI-generated service and efficiently obtain the necessary suggestions and information.

[0233] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0234] This invention relates to a generative AI service utilization system that incorporates an emotion engine for recognizing user emotions. This system enables users to utilize multiple generative AI services through a single interface and provides optimal generation results while taking user emotions into consideration.

[0235] A natural language explanation of the program's processing.

[0236] server

[0237] 1. Receive messages sent by the user from their device.

[0238] 2. An emotion engine is used to analyze the user's emotions from received messages. Specifically, it analyzes the vocabulary, expressions, and context within the text to identify emotions (such as joy, sadness, or anger).

[0239] 3. Analyze messages using natural language processing (NLP) techniques to extract user requests. Example: Extract keywords such as "cat," "cute," and "video."

[0240] 4. Based on the extracted requests and analyzed emotions, select the optimal generative AI service. This selection will consider factors such as the service's performance, past performance, and compatibility with the emotions. Example: Select generative AI service A, which specializes in video generation.

[0241] 5. Generate request data for the selected generative AI service. The request data includes details of the content the user wants generated (e.g., specific instructions for generating a cute cat video) and analyzed emotions.

[0242] 6. Send the generated request data to the selected generation AI service.

[0243] 7. The generation AI service performs the generation process based on the request and returns the generation result to the server.

[0244] 8. Post-processing is performed on the generated results as needed. Post-processing includes adjusting the content according to the emotion recognition results.

[0245] 9. Send the completed generation results to the user's device and notify the user.

[0246] terminal

[0247] 1. The user enters the content they want to generate and sends the message to the server.

[0248] 2. Receive notifications and generation results from the server and display them to the user.

[0249] User

[0250] 1. Enter the content you want to generate through your device. Example: Enter "I want a cute video of a cat."

[0251] 2. Review and use the generated results sent from the server. The generated results will be provided in an optimal form that reflects the user's emotions.

[0252] Specific example

[0253] For example, suppose a user types into their device, "I'd like you to create a cute video of my cat. I'm feeling a bit down today," and sends it to the system.

[0254] The server receives the message and uses an emotion engine to perform sentiment analysis on the message. Based on the analysis, it determines that the user is "depressed."

[0255] Using natural language processing techniques, the keywords "cat," "cute," and "video" are extracted from the message.

[0256] When selecting a video generation AI service, the server takes into account the user's emotions (feeling down) and selects service A, which can generate cheerful videos to lift the user's spirits.

[0257] The server generates request data to create a cute cat video and sends the request to AI service A. The request data also includes the user's "depressed" emotion.

[0258] AI generation service A generates a cute cat video in response to a request and sends the video back to the server.

[0259] The server receives the generated video, performs post-processing to reflect emotions if necessary, and sends the final video to the user's device.

[0260] The device displays the received video to the user, who then plays and reviews the generated cute cat video. The video is designed to brighten the user's mood.

[0261] By implementing this invention, users can efficiently utilize a generative AI service from a single point of contact and obtain generation results that reflect their own emotions. This improves the convenience of generative AI technology and the user experience.

[0262] The following describes the processing flow.

[0263] Step 1:

[0264] The user uses their device to enter a message containing the content they want generated. For example, they might enter, "I'd like a cute video of my cat. I'm feeling a bit down today."

[0265] Step 2:

[0266] The terminal receives the message entered by the user and sends that message data to the server.

[0267] Step 3:

[0268] The server receives the message sent from the terminal.

[0269] Step 4:

[0270] The server uses an emotion engine to analyze the messages it receives. Specifically, it analyzes the vocabulary, expressions, and context within the text to identify the user's emotions (for example, "feeling down").

[0271] Step 5:

[0272] The server uses natural language processing (NLP) techniques to analyze the message and extract the user's request. For example, it might extract keywords such as "cat," "cute," and "video."

[0273] Step 6:

[0274] The server selects the optimal generation AI service based on the analysis results. Selection criteria include service performance, past performance, frequency of use, and suitability for emotions. Example: Select generation AI service A, which specializes in video generation.

[0275] Step 7:

[0276] The server generates request data for the selected generation AI service. The request data includes details of the content the user wants generated (e.g., specific instructions to generate a cute cat video) and analyzed emotions.

[0277] Step 8:

[0278] The server sends the generated request data to the selected generation AI service. Example: Send a request to generation AI service A.

[0279] Step 9:

[0280] The AI ​​generation service A performs the generation process based on the request, generates a cute video of a cat, and sends the result back to the server.

[0281] Step 10:

[0282] The server receives the generated results. Example: Receives a cute cat video from AI generation service A.

[0283] Step 11:

[0284] The server performs post-processing on the generation result as needed. This post-processing also includes the adjustment of content according to the emotion recognition result.

[0285] Step 12:

[0286] The server sends the final generation result to the user's terminal.

[0287] Step 13:

[0288] The terminal receives the generation result sent from the server. Example: Receive a cute video of a cat.

[0289] Step 14:

[0290] The terminal displays the generation result to the user. The user can view the generated video. The video contains content that brightens the user's mood.

[0291] (Example 2)

[0292] Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart device 14 is referred to as the "terminal".

[0293] In the conventional generation AI service system, there was a problem that users had to use individual services separately, and it was difficult to provide an optimal generation result considering emotions. Also, message analysis and requirement extraction were insufficient, and it was difficult to obtain a generation result that appropriately reflected the user's requirements.

[0294] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0295] In this invention, the server includes means for receiving messages, means for analyzing messages and recognizing emotions, means for analyzing messages and extracting requests, means for selecting the optimal generative AI service based on the extracted requests and recognized emotions, means for generating and sending request data to the generative AI service, means for receiving generation results from the generative AI service, means for performing necessary post-processing on the generation results, and means for returning the generation results to the user. This enables the user to efficiently utilize the generative AI service and obtain optimal generation results that reflect emotions.

[0296] A "message" refers to text information entered by the user, including requests and emotions directed at the AI-generated service.

[0297] "Means" refers to a device, module, or method for performing a specific function or operation.

[0298] "Means of recognizing emotions" refers to systems and algorithms that analyze and identify a user's emotions based on the vocabulary, expressions, and context within a message.

[0299] "Means of extracting requirements" refers to systems and methods for identifying keywords and phrases related to the user's purpose and desires from a message, and extracting the necessary information.

[0300] "Generative AI services" refer to services that use artificial intelligence technology to generate content and data based on user requests.

[0301] "Request data" refers to data sent to the generating AI service, including the user's requests and analyzed sentiment.

[0302] "Post-processing" refers to operations that perform additional processing on the generated results to optimize or adjust them.

[0303] The "means for returning to the user" refers to communication means or systems for delivering the generated results to the user.

[0304] The present invention is a generation AI service utilization system incorporating an emotion engine that recognizes the emotions of users. This system enables users to utilize multiple generation AI services through a single interface and provides optimal generation results considering the emotions of the users. How to implement this system will be detailed below.

[0305] Server

[0306] The server receives the message sent by the user from the terminal.

[0307] The server analyzes the user's emotions from the received message using the emotion engine. Specifically, it analyzes the vocabulary, expressions, and context within the text to identify emotions (such as joy, sadness, anger, etc.). This emotion engine is implemented in a programming language such as Python and uses natural language processing libraries (e.g., NLTK, spaCy).

[0308] The server analyzes the message using natural language processing (NLP) technology and extracts the user's request. For example, it extracts keywords such as "cat", "cute", and "video". This process is also executed in Python and an NLP library is used.

[0309] The server selects the optimal generation AI service based on the extracted request and the analyzed emotions. In this selection, factors such as the performance of the service, past performance, and compatibility with emotions are considered. As an example, generation AI service A specialized in video generation is selected.

[0310] The server generates request data for the selected generation AI service. The request data includes details of the generated content requested by the user (e.g., specific instructions for generating a cute video of a cat) and the analyzed emotions.

[0311] The server sends the generated request data to the selected generation AI service.

[0312] The generation AI service performs the generation process based on the request and sends the generation result (e.g., the generated video) back to the server.

[0313] The server receives the generated results and performs post-processing as needed. Post-processing includes adjusting the content based on the emotion recognition results (e.g., adjusting video brightness or selecting music).

[0314] The server sends the completed generation results to the user's terminal and notifies the user.

[0315] terminal

[0316] It provides an interface for users to input the content they want to generate.

[0317] The terminal receives user input and sends that message to the server.

[0318] The terminal receives notifications and generated results from the server and displays them to the user.

[0319] User

[0320] The user enters the content they want to generate via their device and sends the message to the server. For example, they might enter, "I'd like a cute video of my cat. I'm feeling a bit down today."

[0321] The user reviews and uses the generated results sent from the server. The generated results are provided in an optimal form that reflects the user's emotions.

[0322] Specific example

[0323] For example, suppose a user types into their device, "I'd like you to create a cute video of my cat. I'm feeling a bit down today," and sends it to the system.

[0324] The server receives the message and uses an emotion engine to perform sentiment analysis on the message. Based on the analysis, it determines that the user is "depressed."

[0325] Using natural language processing techniques, the keywords "cat," "cute," and "video" are extracted from the message.

[0326] When selecting a video generation AI service, the server takes into account the user's emotions (feeling down) and selects service A, which can generate cheerful videos to lift the user's spirits.

[0327] The server generates request data to create a cute cat video and sends the request to AI service A. The request data also includes the user's "depressed" emotion.

[0328] AI generation service A generates a cute cat video in response to a request and sends the video back to the server.

[0329] The server receives the generated video, performs post-processing to reflect emotions if necessary, and sends the final video to the user's device.

[0330] The device displays the received video to the user, who then plays and reviews the generated cute cat video. The video is designed to brighten the user's mood.

[0331] In this way, the present invention allows users to efficiently utilize the generation AI service from a single point of contact and obtain optimal generation results that reflect their own emotions. This improves the convenience of generation AI technology and the user experience.

[0332] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0333] Step 1:

[0334] The user enters the content they want to generate into the terminal interface and sends a message to the server. The input may include text such as, "I'd like a cute video of my cat. I'm feeling a bit down today." This sends a message to the server expressing the user's request and feelings.

[0335] Step 2:

[0336] The server receives messages sent from the terminal. The received messages are stored in the server's database in text format.

[0337] Input: Received message (text)

[0338] Output: Text saved in the database

[0339] Step 3:

[0340] The server uses an emotion engine to recognize emotions from received messages. The emotion engine analyzes the vocabulary, expressions, and context within the text to identify emotions such as joy, sadness, and anger.

[0341] Input: Saved text

[0342] Data processing: Analyzing emotions using natural language processing techniques.

[0343] Output: Identified emotion (e.g., depressed)

[0344] Step 4:

[0345] The server uses natural language processing (NLP) techniques to analyze the message content and extract the user's request. For example, it might identify keywords such as "cat," "cute," and "video" from the message.

[0346] Input: Saved text

[0347] Data processing: Analyze requirements using a keyword extraction algorithm.

[0348] Output: Extracted keywords (e.g., cat, cute, video)

[0349] Step 5:

[0350] The server selects the optimal generative AI service based on the extracted requests and analyzed emotions. This selection considers factors such as service performance, past performance, and compatibility with the emotions. For example, it might select service A, which can generate videos that uplift the user.

[0351] Input: Extracted keywords, identified emotions

[0352] Data processing: Evaluation and selection of multiple generative AI services.

[0353] Output: Selected generative AI service (e.g., Service A)

[0354] Step 6:

[0355] The server generates request data for the selected generative AI service. This request data includes details of the generated content requested by the user and an analyzed sentiment.

[0356] Input: Extracted keywords, identified sentiment, selected generative AI service

[0357] Data processing: Generating request data

[0358] Output: Generated request data

[0359] Step 7:

[0360] The server sends the generated request data to the selected generation AI service. This transmission is performed using a communication protocol.

[0361] Input: Generated request data

[0362] Output: Request data sent to the AI ​​generation service

[0363] Step 8:

[0364] The AI ​​generation service processes content generation based on the request and returns the generated result (e.g., the generated video) to the server.

[0365] Input: Request data (generation instructions and sentiment information)

[0366] Output: Generated content (e.g., a cute video of a cat)

[0367] Step 9:

[0368] The server receives the generated results and performs post-processing as needed. Post-processing includes adjusting the content based on the emotion recognition results (e.g., adjusting video brightness or selecting music).

[0369] Input: Generated content

[0370] Data processing: Optimization based on emotion recognition results

[0371] Output: Post-processed generated content

[0372] Step 10:

[0373] The server sends the completed generation results to the user's terminal and notifies the user.

[0374] Input: Post-processed generated content

[0375] Output: Generated content sent to the user's terminal

[0376] Step 11:

[0377] Users view and use the generated results (e.g., cute cat videos) on their devices. The videos displayed on the device are optimized to reflect the user's emotions.

[0378] Input: Generated content sent from the server

[0379] Output: Generated content that users view and use (e.g., cute cat videos)

[0380] (Application Example 2)

[0381] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0382] In modern content delivery services, it is difficult for users to automatically and efficiently find the most suitable content based on their emotional state. Furthermore, the lack of a system that allows users to enjoy content that reflects their own emotions can lead to a diminished user experience. Therefore, a new system is needed that considers user emotions and recommends the most suitable content based on those emotions.

[0383] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0384] In this invention, the server includes means for receiving messages, means for analyzing the messages to recognize emotions and extract requests, and means for selecting the optimal generative AI service based on the emotions and requests. This makes it possible to automatically recommend the most suitable content according to the user's emotional state.

[0385] A "means of receiving messages" is an interface for electronically receiving user input and initiating processing.

[0386] "A means of analyzing messages to recognize emotions and extract requests" refers to a function that analyzes received messages using natural language processing technology and extracts the user's emotional state and specific requests from them.

[0387] "Emotions" refer to the mental states of users extracted from their input, including feelings such as joy, sadness, and anger.

[0388] A "request" refers to a specific request or need that a user makes to the system, such as asking for actions like recommending specific content or generating specific information.

[0389] "Means for selecting the optimal generative AI service" refers to algorithms and methods for selecting the most suitable service from among multiple existing generative AI services based on emotions and requests.

[0390] "Means for sending requests to a generation AI service" refers to a means of communication for requesting a selected generation AI service to perform processing according to the user's requirements.

[0391] "Means for receiving generation results from the generation AI service" refers to a function for receiving data when the generation AI service completes processing and sends the results back to the server.

[0392] "Means for returning the generation results to the user" refers to an interface for sending the received generation results to the user's terminal and providing them to the user.

[0393] "Natural language processing technology" refers to a set of techniques that enable computers to understand, interpret, and respond to human language, and is used for text analysis, sentiment recognition, request extraction, and more.

[0394] "Post-processing including emotion-based adjustments" refers to the process of further fine-tuning the generated results received from the generation AI service to match the user's emotions, with the aim of improving the user experience.

[0395] A specific system for carrying out this invention includes the following steps:

[0396] The server receives input messages from the user. Text format is preferred for these messages. A network communication module is used to receive messages entered from user terminals such as smartphones.

[0397] Next, the server analyzes the received message using natural language processing techniques to recognize the user's emotions and extract requests from the message content. This process utilizes natural language processing libraries such as TextBlob. For example, if a user enters "I'm very tired today," the server recognizes the emotion of "tired" from this message and extracts the request "I would like recommendations for content suitable for rest."

[0398] After emotions and requests are extracted, the server selects the most suitable generative AI service based on this information. This selection takes into account past performance and compatibility with the user's emotions. The generative AI service may utilize the latest deep learning models, among others.

[0399] A request is sent to the selected generative AI service, tailored to the user's needs. The request data includes information about the user's emotions. The generative AI service then provides the most suitable generation result based on this request. For example, a streaming music service might provide relaxing music.

[0400] Once the generation AI service returns the generated results, the server performs further emotion-based post-processing as needed. This adjusts the content to better reflect the user's emotions.

[0401] Finally, the generated results are sent to the user's device and the user is notified. The user can then access the generated content through their device. This entire process allows the user to easily obtain content optimized for their own emotions.

[0402] For example, if a user types "I'm very tired today" into their smartphone, the system will recommend a relaxing movie that matches that feeling. This improves the user experience.

[0403] Examples of prompt messages include the following:

[0404] "Please tell me how you're feeling right now: I'm very tired today."

[0405] "I recommend this to you: Guardians of the Galaxy (movie)"

[0406] This allows users to easily find content that suits their emotions, resulting in a highly satisfying experience.

[0407] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0408] Step 1:

[0409] The user uses a terminal to type a message containing emotions and requests. For example, they might type, "I'm very tired today." Input: The user's text message. Output: The message sent from the terminal to the server.

[0410] Step 2:

[0411] The server receives messages sent from the terminal. The received data is stored in text format. Input: Message sent from the terminal. Output: Received message data.

[0412] Step 3:

[0413] The server analyzes received messages using natural language processing techniques to recognize the user's emotions and extract requests. Specifically, it uses libraries such as TextBlob to identify emotions (positive, negative, neutral) and pinpoint the emotion "tired." Input: Received message data. Output: Analyzed emotions and extracted requests.

[0414] Step 4:

[0415] The server selects the optimal generative AI service based on the analyzed emotions and requests. From the available generative AI services, it chooses the one best suited to the user's emotions. Input: Analyzed emotion and request data. Output: Selected generative AI service.

[0416] Step 5:

[0417] The server sends a request to the selected generative AI service. The request data includes the user's sentiment information and specific request details. Input: Selected generative AI service, request data, sentiment data. Output: Request data sent to the generative AI service.

[0418] Step 6:

[0419] The AI ​​generation service processes requests from the server and returns the generated content to the server. For example, it could recommend relaxing movies. Input: Request data from the server. Output: Generated content data.

[0420] Step 7:

[0421] The server receives content data returned from the AI ​​generation service and performs post-processing as needed. It makes emotion-based adjustments and determines the final content. Input: Generated content data. Output: Post-processed final content data.

[0422] Step 8:

[0423] The server sends the post-processed final content data to the user's terminal and notifies them. Input: Final content data. Output: Content data sent to the user's terminal.

[0424] Step 9:

[0425] Users view and use content received through their devices. For example, they might watch a recommended movie. Input: Content data received from the server. Output: Displayed content.

[0426] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0427] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0428] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0429] [Second Embodiment]

[0430] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0431] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0432] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0433] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0434] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0435] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0436] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0437] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0438] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0439] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0440] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0441] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0442] This invention provides a system that enables a user to utilize multiple generative AI services through a single interface. This system automatically performs a series of processes, including receiving and analyzing messages, selecting the optimal generative AI service, sending requests, receiving generation results, and returning them to the user.

[0443] A natural language explanation of the program's processing.

[0444] server

[0445] 1. Receive messages sent by the user from their device.

[0446] 2. The received message is analyzed using natural language processing (NLP) technology to extract the user's request.

[0447] 3. Based on the extracted requirements, select the optimal generation AI service. This selection will take into account the service's performance, past performance, and frequency of use.

[0448] 4. Create request data for the selected generative AI service and send the request.

[0449] 5. Receive the generated results (e.g., video, text, images, audio, etc.) from the generation AI service.

[0450] 6. If necessary, perform post-processing on the generated results (format conversion, metadata addition, etc.).

[0451] 7. The completed generation results are sent to the user's terminal and the user is notified.

[0452] terminal

[0453] 1. The user enters the content they want to generate and sends the message to the server.

[0454] 2. Receive notifications and generation results from the server and display them to the user.

[0455] User

[0456] 1. Enter the content you want to generate via your device.

[0457] 2. Check and use the generated results sent from the server.

[0458] Specific example

[0459] For example, suppose a user enters a message into their device saying, "I would like you to create a cute video of my cat," and sends it to the system.

[0460] The server receives the message and uses natural language processing technology to extract keywords such as "cat," "cute," and "video."

[0461] The server selects a generation AI service specifically designed for video generation. For example, video generation AI service A might be selected.

[0462] The server generates request data for creating a cute cat video and sends the request to AI generation service A.

[0463] AI generation service A generates a cute cat video in response to a request and sends the result back to the server.

[0464] The server receives the generated video, performs any necessary post-processing, and sends the final video to the user's device.

[0465] The device displays the received video to the user, allowing the user to view the generated cute cat video.

[0466] By implementing this invention, users can eliminate the need to individually manage each generation AI service and efficiently obtain their desired generation results from a single point of contact. This system significantly improves the convenience of generation AI technology.

[0467] The following describes the processing flow.

[0468] Step 1:

[0469] The user uses their device to enter a message containing the content they want generated. For example, they might enter, "I want a cute video of a cat."

[0470] Step 2:

[0471] The terminal receives the message entered by the user and sends that message data to the server.

[0472] Step 3:

[0473] The server receives the message sent from the terminal.

[0474] Step 4:

[0475] The server analyzes received messages using natural language processing (NLP) techniques. Specifically, it extracts keywords and context from messages to understand user requests. For example, it might extract keywords such as "cat," "cute," and "video."

[0476] Step 5:

[0477] The server selects the optimal generation AI service based on the analysis results. Selection criteria include service performance, past performance, and frequency of use. Example: Select generation AI service A, which specializes in video generation.

[0478] Step 6:

[0479] The server generates request data for the selected generation AI service. The request data includes details of the content the user wants generated (e.g., specific instructions for generating a cute cat video).

[0480] Step 7:

[0481] The server sends the generated request data to the selected generation AI service. Example: Send a request to generation AI service A.

[0482] Step 8:

[0483] The generation AI service performs generation processing based on the request and creates the generated result. Example: Generate a cute video of a cat.

[0484] Step 9:

[0485] The AI ​​generation service sends the generated results back to the server.

[0486] Step 10:

[0487] The server receives the generated results. Example: Receives a cute cat video from AI generation service A.

[0488] Step 11:

[0489] If necessary, the server performs post-processing on the generated results. For example, this may include format conversion or the addition of metadata.

[0490] Step 12:

[0491] The server sends the final generation result to the user's terminal.

[0492] Step 13:

[0493] The device receives the generated result sent from the server. Example: It receives a cute video of a cat.

[0494] Step 14:

[0495] The device displays the generated result to the user. The user can then view the generated video.

[0496] (Example 1)

[0497] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0498] Currently, for users to utilize multiple generative AI services, they need to access each service individually and configure and operate each platform separately. This is time-consuming and inefficient for users. Furthermore, understanding the performance and characteristics of each generative AI service and selecting the appropriate one is difficult, making it challenging to obtain optimal results.

[0499] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0500] In this invention, the server includes means for receiving messages, means for analyzing messages and extracting requests, means for selecting the optimal generative artificial intelligence service, means for sending requests to the generative artificial intelligence service, means for receiving generation results from the generative artificial intelligence service, means for performing post-processing on the generation results as necessary, and means for sending and notifying the user terminal of the generation results. This enables the user to efficiently utilize multiple generative AI services through a single interface and obtain the optimal generation result.

[0501] "Means for receiving messages" refers to a function that receives messages sent from a user terminal and processes their content.

[0502] "Means for analyzing messages and extracting requests" refers to a function that uses natural language processing technology to analyze received messages and clearly extract the user's requirements.

[0503] "Means for selecting the optimal generative artificial intelligence service" refers to a function that selects the optimal generative AI service based on extracted requirements, taking into account performance, past performance, frequency of use, etc.

[0504] "Means for sending requests to a generative artificial intelligence service" refers to a function for sending request data in accordance with the user's request to a selected generative AI service.

[0505] "Means for receiving generation results from a generation artificial intelligence service" refers to a function for receiving generation results sent from a generation AI service.

[0506] "Means for performing post-processing on the generated results as needed" refers to functions for performing post-processing on the received generated results, such as format conversion or the addition of metadata.

[0507] "Means for sending and notifying the user of the generation results" refers to a function for sending the post-processed generation results to the user's terminal and notifying the user.

[0508] This invention provides a system that enables users to efficiently utilize multiple generative AI services through a single interface. This system consists of a server, a terminal, and a user, and automatically performs a series of processes.

[0509] Hardware and software configuration

[0510] server

[0511] Message reception: The server receives messages sent by the user from their terminal.

[0512] Message analysis: Received messages are analyzed using natural language processing (NLP) techniques (e.g., SpaCy or NLTK library) to extract user requests.

[0513] Service Selection: Based on the extracted requirements, the optimal generative artificial intelligence service will be selected considering performance, track record, frequency of use, etc. For example, OpenAI or similar services will be used for the generative AI model.

[0514] Request data creation: Create request data for the selected generative AI service and send the data, including the prompt message.

[0515] Result reception: Receives generated results from the generation AI service, including in formats such as video, text, images, and audio.

[0516] Post-processing: Perform post-processing as needed, such as format conversion or metadata addition. For example, use FFmpeg to convert the video format.

[0517] Notification / Sending: The completed generation results are sent to the user's terminal, and the user is notified that the results have been generated.

[0518] terminal

[0519] Message Input and Sending: The user inputs the content they want to generate via their terminal and sends the message to the server.

[0520] Result Reception and Display: Receives results and displays them to the user. For example, if the user enters "I want a cute video of a cat," the results will be displayed on the device.

[0521] User

[0522] Content Input: The user enters the content they want to generate into the terminal. Specifically, they enter prompt messages such as "Please create a cute video of a cat" or "Please generate a photo of a flower field."

[0523] Confirmation and Use of Generated Results: Users can confirm and use the generated results.

[0524] Specific example

[0525] For example, a user might type a message into their device saying, "I want you to create a cute video of my cat," and send it to the system.

[0526] The server receives the message and uses natural language processing technology to analyze and extract keywords such as "cat," "cute," and "video."

[0527] The server selects a generation AI service suitable for video generation, for example, a video generation AI, which is one of the generation AI models.

[0528] The server creates request data that includes the prompt "Please create a cute video of a cat" and sends it to the AI ​​generation service.

[0529] The AI ​​generation service generates cute cat videos in response to requests and sends the results back to the server.

[0530] The server receives the generated results, performs any necessary post-processing, and then sends the completed video to the user's device.

[0531] The device receives the results and displays the video to the user. The user can then watch the generated cute video of a cat.

[0532] This invention eliminates the need for users to individually manage each generation AI service, enabling them to efficiently obtain the desired generation results from a single interface. Furthermore, it significantly improves the convenience of generation AI technology.

[0533] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0534] Step 1: Receive message

[0535] The server receives messages sent from the terminal.

[0536] Input: The user sent a message saying, "I would like you to create a cute video of my cat."

[0537] Output: Received messages are saved on the server.

[0538] Step 2: Message analysis and request extraction

[0539] The server analyzes received messages using natural language processing (NLP) techniques. Specifically, it utilizes libraries such as SpaCy and NLTK.

[0540] Input: Received message: "I would like you to create a cute video of my cat."

[0541] Data processing: Extract keywords such as "cat," "cute," and "video" from the message.

[0542] Output: Extracted keywords: "cat", "cute", "video".

[0543] Step 3: Selecting a Generative AI Service

[0544] The server selects the optimal generation AI service based on the extracted keywords, taking into account factors such as performance, past performance, and frequency of use.

[0545] Input: Extracted keywords "cat", "cute", "video".

[0546] Data processing: Evaluate the characteristics of each generation AI service and select the optimal service.

[0547] Output: Selected generative AI service (e.g., video generation AI service).

[0548] Step 4: Create Request Data

[0549] The server creates request data for the selected generative AI service. It generates an appropriate request, including a prompt.

[0550] Input: User requirements and selected generation AI service.

[0551] Data processing: Generate request data that includes the prompt "Please create a cute video of a cat".

[0552] Output: Generated request data.

[0553] Step 5: Submit Request

[0554] The server sends the generated request data to the selected generation AI service.

[0555] Input: Generated request data.

[0556] Output: A request is sent to the generation AI service.

[0557] Step 6: Receive the generation result

[0558] The server receives the results generated from the AI ​​generation service.

[0559] Input: Generated results (e.g., video data) sent from a generation AI service.

[0560] Output: The received generation results are saved on the server.

[0561] Step 7: Post-processing

[0562] The server performs post-processing on the generated results as needed, such as format conversion or metadata addition. Specifically, it uses FFmpeg.

[0563] Input: Received generation result.

[0564] Data processing: Converting video formats and adding metadata.

[0565] Output: The generated result after post-processing is complete.

[0566] Step 8: Send Results and Notification

[0567] The server sends the post-processed results to the user's terminal and notifies the user that the results have been generated.

[0568] Input: The generated result after post-processing is complete.

[0569] Output: The generated result is sent to the user's terminal, and a notification is issued.

[0570] Step 9: Receive and display results

[0571] The terminal receives the generated results sent from the server and displays them to the user.

[0572] Input: The generated result sent from the server.

[0573] Output: The generated result will be displayed on the terminal.

[0574] Step 10: Confirm and use of generation results

[0575] The user checks the generated results displayed on the device and uses them.

[0576] Input: The generated result displayed on the terminal.

[0577] Output: The generated result is checked and used.

[0578] (Application Example 1)

[0579] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0580] Conventional generation AI services required users to individually select each service, submit requests, and receive results, resulting in a cumbersome operation. Furthermore, it was difficult for users to understand the characteristics and performance of each generation AI service, making it challenging to select the optimal service. Additionally, post-processing of the generation results required manual work, which was time-consuming and labor-intensive. This invention aims to solve these problems and provide a system that allows users to efficiently utilize generation AI services through a single interface.

[0581] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0582] In this invention, the server includes means for receiving messages, means for analyzing the messages and extracting requests, means for selecting the optimal generation AI service based on the requests, means for sending requests to the generation AI service, means for receiving generation results from the generation AI service, means for returning the generation results to the user, means for performing post-processing on the generation results, and means for performing product searches and suggestions on an e-commerce site. This enables users to efficiently utilize generation AI services from a single point of contact and effectively make use of the generation results.

[0583] A "message" is textual information sent by a user, including requests and instructions regarding the AI ​​generation service.

[0584] "Analysis" is the process of interpreting received messages based on natural language processing technology and extracting user requests.

[0585] A "request" refers to the actions or data that a user wants the AI ​​service to perform or generate.

[0586] A "generative AI service" is an external service or platform that uses AI technology to generate content such as text, images, audio, and video.

[0587] A "request" refers to data based on a request sent to a specific AI-generating service.

[0588] "Generation result" refers to the generated content information returned from the generation AI service.

[0589] "Return" refers to the process of returning the generated results received from the generation AI service back to the user.

[0590] "Post-processing" refers to the process of performing necessary format conversions and adding metadata to the generated results obtained from the generation AI service.

[0591] An "online shopping site" is an online platform where users can search for and purchase products via the internet.

[0592] "Product search" refers to the act of a user searching for a specific product or service on an e-commerce website.

[0593] "Recommendation" refers to the act of recommending appropriate products or services based on the user's needs and preferences.

[0594] This invention relates to a system that allows users to utilize multiple AI-generated services through a single interface. In particular, an example of its implementation as a smartphone application for product search and suggestions on an e-commerce site is provided.

[0595] System Configuration

[0596] The main components are a server and a terminal (smartphone). The server receives messages, analyzes their content, selects the optimal generation AI service, sends requests to the generation AI service, and receives the generation results. The terminal is responsible for receiving and displaying notifications and generation results from the server, as well as inputting the content the user wants to generate.

[0597] Hardware and software to be used

[0598] Server: Uses the Flask framework in Python to manage message reception and request sending.

[0599] Natural Language Processing (NLP) techniques: Message analysis is performed using spaCy in Python.

[0600] Generative AI services: External generative AI platforms (e.g., OpenAI's GPT-3) can be used.

[0601] Smartphone applications: Developed using iOS or Android development environments (Swift or Kotlin).

[0602] Data processing and calculation

[0603] The server processes the data in the following steps:

[0604] 1. Receive messages sent from the terminal and analyze them using NLP (Neuro-Linguistic Programming) technology. This analysis extracts the user's requests.

[0605] 2. Based on the extracted requirements, select the optimal generative AI service. Selection criteria include the performance and frequency of use of the generative AI service.

[0606] 3. Generate request data for the selected generative AI service and send the request.

[0607] 4. Receive the generation results from the generation AI service and perform post-processing on the results as needed. Post-processing includes data format conversion and metadata addition.

[0608] 5. Send the completed generation result to the terminal and notify the user.

[0609] Specific example

[0610] Let's say a user types "I'd like some suggestions for coordinating outfits for women's casual dresses" and sends it to the server.

[0611] The server receives the message and uses NLP technology to extract the keywords "women's casual dress" and "outfit."

[0612] The server selects a fashion-related AI service for generating data (e.g., a fashion suggestion AI service).

[0613] The server creates request data to generate a women's casual dress outfit and sends it to the generation AI service.

[0614] The generation AI service generates suggestions in response to requests and sends the results back to the server.

[0615] The server receives the generated list of suggestions, formats it into a specific format, and sends it to the user's terminal.

[0616] The device displays the list of suggestions received by the user, allowing the user to view the generated list and suggested coordinates.

[0617] Example of a prompt

[0618] User: Can you suggest some casual dress outfit ideas for women?

[0619] AI: I suggest the following three outfit combinations:...

[0620] In this way, users can easily utilize the generated AI service to efficiently perform tasks such as product searches and outfit suggestions on e-commerce sites.

[0621] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0622] Step 1:

[0623] The user enters the content they want to generate using their smartphone. In this case, the user enters "Please give me some ideas for coordinating casual dresses for women." The entered message is then sent to the server.

[0624] Step 2:

[0625] The server receives a message sent by a user. For example, it might receive the message, "Please give me some ideas for coordinating a casual dress for women." This message is then analyzed using natural language processing (NLP) techniques. Specifically, the Python library spaCy is used to extract keywords from the message. The input here is the user's message, and the output is the extracted keywords (e.g., "casual dress for women," "coordination").

[0626] Step 3:

[0627] The server selects the most suitable generative AI service based on the extracted keywords. For example, it might select a generative AI service specializing in fashion suggestions. Past performance and performance indicators are considered in the selection process. In this step, the input is the extracted keywords, and the output is the selected generative AI service (e.g., a fashion suggestion AI service).

[0628] Step 4:

[0629] The server generates request data for the selected AI service. This request data includes the user's request and other necessary metadata. The inputs here are the extracted keywords and the selected AI service, and the output is the generated request data.

[0630] Step 5:

[0631] The server sends the generated request data to the specified AI service. This is done by sending an HTTP request to the AI ​​service's API endpoint. The input here is the request data, and the output is the response from the AI ​​service (the generated suggestion result).

[0632] Step 6:

[0633] The system receives generation results (suggestions) from the generation AI service. The received generation results are temporarily stored on the server, and post-processing is performed as needed. Post-processing includes data format conversion and metadata addition. The input here is the generation result from the generation AI service, and the output is the post-processed generation result.

[0634] Step 7:

[0635] The server returns the post-processed generated results to the user's device. The final data is sent to the user's smartphone app in JSON format or similar. Here, the input is the post-processed generated results, and the output is the notification and display on the user's device.

[0636] Step 8:

[0637] The user checks the generated results displayed on the device. For example, they can see the generated "Women's Casual Dress Coordination Suggestions" on their smartphone screen. In this step, the input is the generated results received by the device, and the output is the user's confirmation action.

[0638] Through these steps, users can easily utilize the AI-generated service and efficiently obtain the necessary suggestions and information.

[0639] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0640] This invention relates to a generative AI service utilization system that incorporates an emotion engine for recognizing user emotions. This system enables users to utilize multiple generative AI services through a single interface and provides optimal generation results while taking user emotions into consideration.

[0641] A natural language explanation of the program's processing.

[0642] server

[0643] 1. Receive messages sent by the user from their device.

[0644] 2. An emotion engine is used to analyze the user's emotions from received messages. Specifically, it analyzes the vocabulary, expressions, and context within the text to identify emotions (such as joy, sadness, or anger).

[0645] 3. Analyze messages using natural language processing (NLP) techniques to extract user requests. Example: Extract keywords such as "cat," "cute," and "video."

[0646] 4. Based on the extracted requests and analyzed emotions, select the optimal generative AI service. This selection will consider factors such as the service's performance, past performance, and compatibility with the emotions. Example: Select generative AI service A, which specializes in video generation.

[0647] 5. Generate request data for the selected generative AI service. The request data includes details of the content the user wants generated (e.g., specific instructions for generating a cute cat video) and analyzed emotions.

[0648] 6. Send the generated request data to the selected generation AI service.

[0649] 7. The generation AI service performs the generation process based on the request and returns the generation result to the server.

[0650] 8. Post-processing is performed on the generated results as needed. Post-processing includes adjusting the content according to the emotion recognition results.

[0651] 9. Send the completed generation results to the user's device and notify the user.

[0652] terminal

[0653] 1. The user enters the content they want to generate and sends the message to the server.

[0654] 2. Receive notifications and generation results from the server and display them to the user.

[0655] User

[0656] 1. Enter the content you want to generate through your device. Example: Enter "I want a cute video of a cat."

[0657] 2. Review and use the generated results sent from the server. The generated results will be provided in an optimal form that reflects the user's emotions.

[0658] Specific example

[0659] For example, suppose a user types into their device, "I'd like you to create a cute video of my cat. I'm feeling a bit down today," and sends it to the system.

[0660] The server receives the message and uses an emotion engine to perform sentiment analysis on the message. Based on the analysis, it determines that the user is "depressed."

[0661] Using natural language processing techniques, the keywords "cat," "cute," and "video" are extracted from the message.

[0662] When selecting a video generation AI service, the server takes into account the user's emotions (feeling down) and selects service A, which can generate cheerful videos to lift the user's spirits.

[0663] The server generates request data to create a cute cat video and sends the request to AI service A. The request data also includes the user's "depressed" emotion.

[0664] AI generation service A generates a cute cat video in response to a request and sends the video back to the server.

[0665] The server receives the generated video, performs post-processing to reflect emotions if necessary, and sends the final video to the user's device.

[0666] The device displays the received video to the user, who then plays and reviews the generated cute cat video. The video is designed to brighten the user's mood.

[0667] By implementing this invention, users can efficiently utilize a generative AI service from a single point of contact and obtain generation results that reflect their own emotions. This improves the convenience of generative AI technology and the user experience.

[0668] The following describes the processing flow.

[0669] Step 1:

[0670] The user uses their device to enter a message containing the content they want generated. For example, they might enter, "I'd like a cute video of my cat. I'm feeling a bit down today."

[0671] Step 2:

[0672] The terminal receives the message entered by the user and sends that message data to the server.

[0673] Step 3:

[0674] The server receives the message sent from the terminal.

[0675] Step 4:

[0676] The server uses an emotion engine to analyze the messages it receives. Specifically, it analyzes the vocabulary, expressions, and context within the text to identify the user's emotions (for example, "feeling down").

[0677] Step 5:

[0678] The server uses natural language processing (NLP) techniques to analyze the message and extract the user's request. For example, it might extract keywords such as "cat," "cute," and "video."

[0679] Step 6:

[0680] The server selects the optimal generation AI service based on the analysis results. Selection criteria include service performance, past performance, frequency of use, and suitability for emotions. Example: Select generation AI service A, which specializes in video generation.

[0681] Step 7:

[0682] The server generates request data for the selected generation AI service. The request data includes details of the content the user wants generated (e.g., specific instructions to generate a cute cat video) and analyzed emotions.

[0683] Step 8:

[0684] The server sends the generated request data to the selected generation AI service. Example: Send a request to generation AI service A.

[0685] Step 9:

[0686] The AI ​​generation service A performs the generation process based on the request, generates a cute video of a cat, and sends the result back to the server.

[0687] Step 10:

[0688] The server receives the generated results. Example: Receives a cute cat video from AI generation service A.

[0689] Step 11:

[0690] The server performs post-processing on the generated results as needed. This post-processing includes adjusting the content based on the emotion recognition results.

[0691] Step 12:

[0692] The server sends the final generation result to the user's terminal.

[0693] Step 13:

[0694] The device receives the generated result sent from the server. Example: It receives a cute video of a cat.

[0695] Step 14:

[0696] The device displays the generated result to the user. The user can view the generated video. The video contains content that will uplift the user's mood.

[0697] (Example 2)

[0698] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0699] Conventional AI-generated service systems faced challenges in providing optimal generated results that took emotions into account, as users had to utilize each service separately. Furthermore, insufficient message analysis and request extraction made it difficult to obtain generated results that adequately reflected user needs.

[0700] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0701] In this invention, the server includes means for receiving messages, means for analyzing messages and recognizing emotions, means for analyzing messages and extracting requests, means for selecting the optimal generative AI service based on the extracted requests and recognized emotions, means for generating and sending request data to the generative AI service, means for receiving generation results from the generative AI service, means for performing necessary post-processing on the generation results, and means for returning the generation results to the user. This enables the user to efficiently utilize the generative AI service and obtain optimal generation results that reflect emotions.

[0702] A "message" refers to text information entered by the user, including requests and emotions directed at the AI-generated service.

[0703] "Means" refers to a device, module, or method for performing a specific function or operation.

[0704] "Means of recognizing emotions" refers to systems and algorithms that analyze and identify a user's emotions based on the vocabulary, expressions, and context within a message.

[0705] "Means of extracting requirements" refers to systems and methods for identifying keywords and phrases related to the user's purpose and desires from a message, and extracting the necessary information.

[0706] "Generative AI services" refer to services that use artificial intelligence technology to generate content and data based on user requests.

[0707] "Request data" refers to data sent to the generating AI service, including the user's requests and analyzed sentiment.

[0708] "Post-processing" refers to operations that perform additional processing on the generated results to optimize or adjust them.

[0709] "Means of returning to the user" refers to communication methods and systems used to deliver the generated results to the user.

[0710] This invention relates to a generative AI service utilization system that incorporates an emotion engine for recognizing user emotions. This system allows users to utilize multiple generative AI services through a single interface and provides optimal generation results while considering the user's emotions. The implementation of this system is described in detail below.

[0711] server

[0712] The server receives messages sent by the user from their terminal.

[0713] The server uses an emotion engine to analyze the user's emotions from received messages. Specifically, it analyzes the vocabulary, expressions, and context within the text to identify emotions (such as joy, sadness, or anger). This emotion engine is implemented in a programming language such as Python and uses natural language processing libraries (e.g., NLTK, spaCy).

[0714] The server uses natural language processing (NLP) techniques to analyze messages and extract user requests. For example, it might extract keywords like "cat," "cute," and "video." This process is also run in Python, using NLP libraries.

[0715] The server selects the optimal generative AI service based on the extracted requests and analyzed emotions. This selection considers factors such as service performance, past performance, and compatibility with the emotions. For example, generative AI service A, which specializes in video generation, is selected.

[0716] The server generates request data for the selected generative AI service. The request data includes details of the content the user wants generated (e.g., specific instructions for generating a cute cat video) and analyzed emotions.

[0717] The server sends the generated request data to the selected generation AI service.

[0718] The generation AI service performs the generation process based on the request and sends the generation result (e.g., the generated video) back to the server.

[0719] The server receives the generated results and performs post-processing as needed. Post-processing includes adjusting the content based on the emotion recognition results (e.g., adjusting video brightness or selecting music).

[0720] The server sends the completed generation results to the user's terminal and notifies the user.

[0721] terminal

[0722] It provides an interface for users to input the content they want to generate.

[0723] The terminal receives user input and sends that message to the server.

[0724] The terminal receives notifications and generated results from the server and displays them to the user.

[0725] User

[0726] The user enters the content they want to generate via their device and sends the message to the server. For example, they might enter, "I'd like a cute video of my cat. I'm feeling a bit down today."

[0727] The user reviews and uses the generated results sent from the server. The generated results are provided in an optimal form that reflects the user's emotions.

[0728] Specific example

[0729] For example, suppose a user types into their device, "I'd like you to create a cute video of my cat. I'm feeling a bit down today," and sends it to the system.

[0730] The server receives the message and uses an emotion engine to perform sentiment analysis on the message. Based on the analysis, it determines that the user is "depressed."

[0731] Using natural language processing techniques, the keywords "cat," "cute," and "video" are extracted from the message.

[0732] When selecting a video generation AI service, the server takes into account the user's emotions (feeling down) and selects service A, which can generate cheerful videos to lift the user's spirits.

[0733] The server generates request data to create a cute cat video and sends the request to AI service A. The request data also includes the user's "depressed" emotion.

[0734] AI generation service A generates a cute cat video in response to a request and sends the video back to the server.

[0735] The server receives the generated video, performs post-processing to reflect emotions if necessary, and sends the final video to the user's device.

[0736] The device displays the received video to the user, who then plays and reviews the generated cute cat video. The video is designed to brighten the user's mood.

[0737] In this way, the present invention allows users to efficiently utilize the generation AI service from a single point of contact and obtain optimal generation results that reflect their own emotions. This improves the convenience of generation AI technology and the user experience.

[0738] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0739] Step 1:

[0740] The user enters the content they want to generate into the terminal interface and sends a message to the server. The input may include text such as, "I'd like a cute video of my cat. I'm feeling a bit down today." This sends a message to the server expressing the user's request and feelings.

[0741] Step 2:

[0742] The server receives messages sent from the terminal. The received messages are stored in the server's database in text format.

[0743] Input: Received message (text)

[0744] Output: Text saved in the database

[0745] Step 3:

[0746] The server uses an emotion engine to recognize emotions from received messages. The emotion engine analyzes the vocabulary, expressions, and context within the text to identify emotions such as joy, sadness, and anger.

[0747] Input: Saved text

[0748] Data processing: Analyzing emotions using natural language processing techniques.

[0749] Output: Identified emotion (e.g., depressed)

[0750] Step 4:

[0751] The server uses natural language processing (NLP) techniques to analyze the message content and extract the user's request. For example, it might identify keywords such as "cat," "cute," and "video" from the message.

[0752] Input: Saved text

[0753] Data processing: Analyze requirements using a keyword extraction algorithm.

[0754] Output: Extracted keywords (e.g., cat, cute, video)

[0755] Step 5:

[0756] The server selects the optimal generative AI service based on the extracted requests and analyzed emotions. This selection considers factors such as service performance, past performance, and compatibility with the emotions. For example, it might select service A, which can generate videos that uplift the user.

[0757] Input: Extracted keywords, identified emotions

[0758] Data processing: Evaluation and selection of multiple generative AI services.

[0759] Output: Selected generative AI service (e.g., Service A)

[0760] Step 6:

[0761] The server generates request data for the selected generative AI service. This request data includes details of the generated content requested by the user and an analyzed sentiment.

[0762] Input: Extracted keywords, identified sentiment, selected generative AI service

[0763] Data processing: Generating request data

[0764] Output: Generated request data

[0765] Step 7:

[0766] The server sends the generated request data to the selected generation AI service. This transmission is performed using a communication protocol.

[0767] Input: Generated request data

[0768] Output: Request data sent to the AI ​​generation service

[0769] Step 8:

[0770] The AI ​​generation service processes content generation based on the request and returns the generated result (e.g., the generated video) to the server.

[0771] Input: Request data (generation instructions and sentiment information)

[0772] Output: Generated content (e.g., a cute video of a cat)

[0773] Step 9:

[0774] The server receives the generated results and performs post-processing as needed. Post-processing includes adjusting the content based on the emotion recognition results (e.g., adjusting video brightness or selecting music).

[0775] Input: Generated content

[0776] Data processing: Optimization based on emotion recognition results

[0777] Output: Post-processed generated content

[0778] Step 10:

[0779] The server sends the completed generation results to the user's terminal and notifies the user.

[0780] Input: Post-processed generated content

[0781] Output: Generated content sent to the user's terminal

[0782] Step 11:

[0783] Users view and use the generated results (e.g., cute cat videos) on their devices. The videos displayed on the device are optimized to reflect the user's emotions.

[0784] Input: Generated content sent from the server

[0785] Output: Generated content that users view and use (e.g., cute cat videos)

[0786] (Application Example 2)

[0787] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0788] In modern content delivery services, it is difficult for users to automatically and efficiently find the most suitable content based on their emotional state. Furthermore, the lack of a system that allows users to enjoy content that reflects their own emotions can lead to a diminished user experience. Therefore, a new system is needed that considers user emotions and recommends the most suitable content based on those emotions.

[0789] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0790] In this invention, the server includes means for receiving messages, means for analyzing the messages to recognize emotions and extract requests, and means for selecting the optimal generative AI service based on the emotions and requests. This makes it possible to automatically recommend the most suitable content according to the user's emotional state.

[0791] A "means of receiving messages" is an interface for electronically receiving user input and initiating processing.

[0792] "A means of analyzing messages to recognize emotions and extract requests" refers to a function that analyzes received messages using natural language processing technology and extracts the user's emotional state and specific requests from them.

[0793] "Emotions" refer to the mental states of users extracted from their input, including feelings such as joy, sadness, and anger.

[0794] A "request" refers to a specific request or need that a user makes to the system, such as asking for actions like recommending specific content or generating specific information.

[0795] "Means for selecting the optimal generative AI service" refers to algorithms and methods for selecting the most suitable service from among multiple existing generative AI services based on emotions and requests.

[0796] "Means for sending requests to a generation AI service" refers to a means of communication for requesting a selected generation AI service to perform processing according to the user's requirements.

[0797] "Means for receiving generation results from the generation AI service" refers to a function for receiving data when the generation AI service completes processing and sends the results back to the server.

[0798] "Means for returning the generation results to the user" refers to an interface for sending the received generation results to the user's terminal and providing them to the user.

[0799] "Natural language processing technology" refers to a set of techniques that enable computers to understand, interpret, and respond to human language, and is used for text analysis, sentiment recognition, request extraction, and more.

[0800] "Post-processing including emotion-based adjustments" refers to the process of further fine-tuning the generated results received from the generation AI service to match the user's emotions, with the aim of improving the user experience.

[0801] A specific system for carrying out this invention includes the following steps:

[0802] The server receives input messages from the user. Text format is preferred for these messages. A network communication module is used to receive messages entered from user terminals such as smartphones.

[0803] Next, the server analyzes the received message using natural language processing techniques to recognize the user's emotions and extract requests from the message content. This process utilizes natural language processing libraries such as TextBlob. For example, if a user enters "I'm very tired today," the server recognizes the emotion of "tired" from this message and extracts the request "I would like recommendations for content suitable for rest."

[0804] After emotions and requests are extracted, the server selects the most suitable generative AI service based on this information. This selection takes into account past performance and compatibility with the user's emotions. The generative AI service may utilize the latest deep learning models, among others.

[0805] A request is sent to the selected generative AI service, tailored to the user's needs. The request data includes information about the user's emotions. The generative AI service then provides the most suitable generation result based on this request. For example, a streaming music service might provide relaxing music.

[0806] Once the generation AI service returns the generated results, the server performs further emotion-based post-processing as needed. This adjusts the content to better reflect the user's emotions.

[0807] Finally, the generated results are sent to the user's device and the user is notified. The user can then access the generated content through their device. This entire process allows the user to easily obtain content optimized for their own emotions.

[0808] For example, if a user types "I'm very tired today" into their smartphone, the system will recommend a relaxing movie that matches that feeling. This improves the user experience.

[0809] Examples of prompt messages include the following:

[0810] "Please tell me how you're feeling right now: I'm very tired today."

[0811] "I recommend this to you: Guardians of the Galaxy (movie)"

[0812] This allows users to easily find content that suits their emotions, resulting in a highly satisfying experience.

[0813] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0814] Step 1:

[0815] The user uses a terminal to type a message containing emotions and requests. For example, they might type, "I'm very tired today." Input: The user's text message. Output: The message sent from the terminal to the server.

[0816] Step 2:

[0817] The server receives messages sent from the terminal. The received data is stored in text format. Input: Message sent from the terminal. Output: Received message data.

[0818] Step 3:

[0819] The server analyzes received messages using natural language processing techniques to recognize the user's emotions and extract requests. Specifically, it uses libraries such as TextBlob to identify emotions (positive, negative, neutral) and pinpoint the emotion "tired." Input: Received message data. Output: Analyzed emotions and extracted requests.

[0820] Step 4:

[0821] The server selects the optimal generative AI service based on the analyzed emotions and requests. From the available generative AI services, it chooses the one best suited to the user's emotions. Input: Analyzed emotion and request data. Output: Selected generative AI service.

[0822] Step 5:

[0823] The server sends a request to the selected generative AI service. The request data includes the user's sentiment information and specific request details. Input: Selected generative AI service, request data, sentiment data. Output: Request data sent to the generative AI service.

[0824] Step 6:

[0825] The AI ​​generation service processes requests from the server and returns the generated content to the server. For example, it could recommend relaxing movies. Input: Request data from the server. Output: Generated content data.

[0826] Step 7:

[0827] The server receives content data returned from the AI ​​generation service and performs post-processing as needed. It makes emotion-based adjustments and determines the final content. Input: Generated content data. Output: Post-processed final content data.

[0828] Step 8:

[0829] The server sends the post-processed final content data to the user's terminal and notifies them. Input: Final content data. Output: Content data sent to the user's terminal.

[0830] Step 9:

[0831] Users view and use content received through their devices. For example, they might watch a recommended movie. Input: Content data received from the server. Output: Displayed content.

[0832] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0833] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0834] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0835] [Third Embodiment]

[0836] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0837] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0838] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0839] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0840] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0841] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0842] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0843] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0844] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0845] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0846] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0847] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0848] This invention provides a system that enables a user to utilize multiple generative AI services through a single interface. This system automatically performs a series of processes, including receiving and analyzing messages, selecting the optimal generative AI service, sending requests, receiving generation results, and returning them to the user.

[0849] A natural language explanation of the program's processing.

[0850] server

[0851] 1. Receive messages sent by the user from their device.

[0852] 2. The received message is analyzed using natural language processing (NLP) technology to extract the user's request.

[0853] 3. Based on the extracted requirements, select the optimal generation AI service. This selection will take into account the service's performance, past performance, and frequency of use.

[0854] 4. Create request data for the selected generative AI service and send the request.

[0855] 5. Receive the generated results (e.g., video, text, images, audio, etc.) from the generation AI service.

[0856] 6. If necessary, perform post-processing on the generated results (format conversion, metadata addition, etc.).

[0857] 7. The completed generation results are sent to the user's terminal and the user is notified.

[0858] terminal

[0859] 1. The user enters the content they want to generate and sends the message to the server.

[0860] 2. Receive notifications and generation results from the server and display them to the user.

[0861] User

[0862] 1. Enter the content you want to generate via your device.

[0863] 2. Check and use the generated results sent from the server.

[0864] Specific example

[0865] For example, suppose a user enters a message into their device saying, "I would like you to create a cute video of my cat," and sends it to the system.

[0866] The server receives the message and uses natural language processing technology to extract keywords such as "cat," "cute," and "video."

[0867] The server selects a generation AI service specifically designed for video generation. For example, video generation AI service A might be selected.

[0868] The server generates request data for creating a cute cat video and sends the request to AI generation service A.

[0869] AI generation service A generates a cute cat video in response to a request and sends the result back to the server.

[0870] The server receives the generated video, performs any necessary post-processing, and sends the final video to the user's device.

[0871] The device displays the received video to the user, allowing the user to view the generated cute cat video.

[0872] By implementing this invention, users can eliminate the need to individually manage each generation AI service and efficiently obtain their desired generation results from a single point of contact. This system significantly improves the convenience of generation AI technology.

[0873] The following describes the processing flow.

[0874] Step 1:

[0875] The user uses their device to enter a message containing the content they want generated. For example, they might enter, "I want a cute video of a cat."

[0876] Step 2:

[0877] The terminal receives the message entered by the user and sends that message data to the server.

[0878] Step 3:

[0879] The server receives the message sent from the terminal.

[0880] Step 4:

[0881] The server analyzes received messages using natural language processing (NLP) techniques. Specifically, it extracts keywords and context from messages to understand user requests. For example, it might extract keywords such as "cat," "cute," and "video."

[0882] Step 5:

[0883] The server selects the optimal generation AI service based on the analysis results. Selection criteria include service performance, past performance, and frequency of use. Example: Select generation AI service A, which specializes in video generation.

[0884] Step 6:

[0885] The server generates request data for the selected generation AI service. The request data includes details of the content the user wants generated (e.g., specific instructions for generating a cute cat video).

[0886] Step 7:

[0887] The server sends the generated request data to the selected generation AI service. Example: Send a request to generation AI service A.

[0888] Step 8:

[0889] The generation AI service performs generation processing based on the request and creates the generated result. Example: Generate a cute video of a cat.

[0890] Step 9:

[0891] The AI ​​generation service sends the generated results back to the server.

[0892] Step 10:

[0893] The server receives the generated results. Example: Receives a cute cat video from AI generation service A.

[0894] Step 11:

[0895] If necessary, the server performs post-processing on the generated results. For example, this may include format conversion or the addition of metadata.

[0896] Step 12:

[0897] The server sends the final generation result to the user's terminal.

[0898] Step 13:

[0899] The device receives the generated result sent from the server. Example: It receives a cute video of a cat.

[0900] Step 14:

[0901] The device displays the generated result to the user. The user can then view the generated video.

[0902] (Example 1)

[0903] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0904] Currently, for users to utilize multiple generative AI services, they need to access each service individually and configure and operate each platform separately. This is time-consuming and inefficient for users. Furthermore, understanding the performance and characteristics of each generative AI service and selecting the appropriate one is difficult, making it challenging to obtain optimal results.

[0905] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0906] In this invention, the server includes means for receiving messages, means for analyzing messages and extracting requests, means for selecting the optimal generative artificial intelligence service, means for sending requests to the generative artificial intelligence service, means for receiving generation results from the generative artificial intelligence service, means for performing post-processing on the generation results as necessary, and means for sending and notifying the user terminal of the generation results. This enables the user to efficiently utilize multiple generative AI services through a single interface and obtain the optimal generation result.

[0907] "Means for receiving messages" refers to a function that receives messages sent from a user terminal and processes their content.

[0908] "Means for analyzing messages and extracting requests" refers to a function that uses natural language processing technology to analyze received messages and clearly extract the user's requirements.

[0909] "Means for selecting the optimal generative artificial intelligence service" refers to a function that selects the optimal generative AI service based on extracted requirements, taking into account performance, past performance, frequency of use, etc.

[0910] "Means for sending requests to a generative artificial intelligence service" refers to a function for sending request data in accordance with the user's request to a selected generative AI service.

[0911] "Means for receiving generation results from a generation artificial intelligence service" refers to a function for receiving generation results sent from a generation AI service.

[0912] "Means for performing post-processing on the generated results as needed" refers to functions for performing post-processing on the received generated results, such as format conversion or the addition of metadata.

[0913] "Means for sending and notifying the user of the generation results" refers to a function for sending the post-processed generation results to the user's terminal and notifying the user.

[0914] This invention provides a system that enables users to efficiently utilize multiple generative AI services through a single interface. This system consists of a server, a terminal, and a user, and automatically performs a series of processes.

[0915] Hardware and software configuration

[0916] server

[0917] Message reception: The server receives messages sent by the user from their terminal.

[0918] Message analysis: Received messages are analyzed using natural language processing (NLP) techniques (e.g., SpaCy or NLTK library) to extract user requests.

[0919] Service Selection: Based on the extracted requirements, the optimal generative artificial intelligence service will be selected considering performance, track record, frequency of use, etc. For example, OpenAI or similar services will be used for the generative AI model.

[0920] Request data creation: Create request data for the selected generative AI service and send the data, including the prompt message.

[0921] Result reception: Receives generated results from the generation AI service, including in formats such as video, text, images, and audio.

[0922] Post-processing: Perform post-processing as needed, such as format conversion or metadata addition. For example, use FFmpeg to convert the video format.

[0923] Notification / Sending: The completed generation results are sent to the user's terminal, and the user is notified that the results have been generated.

[0924] terminal

[0925] Message Input and Sending: The user inputs the content they want to generate via their terminal and sends the message to the server.

[0926] Result Reception and Display: Receives results and displays them to the user. For example, if the user enters "I want a cute video of a cat," the results will be displayed on the device.

[0927] User

[0928] Content Input: The user enters the content they want to generate into the terminal. Specifically, they enter prompt messages such as "Please create a cute video of a cat" or "Please generate a photo of a flower field."

[0929] Confirmation and Use of Generated Results: Users can confirm and use the generated results.

[0930] Specific example

[0931] For example, a user might type a message into their device saying, "I want you to create a cute video of my cat," and send it to the system.

[0932] The server receives the message and uses natural language processing technology to analyze and extract keywords such as "cat," "cute," and "video."

[0933] The server selects a generation AI service suitable for video generation, for example, a video generation AI, which is one of the generation AI models.

[0934] The server creates request data that includes the prompt "Please create a cute video of a cat" and sends it to the AI ​​generation service.

[0935] The AI ​​generation service generates cute cat videos in response to requests and sends the results back to the server.

[0936] The server receives the generated results, performs any necessary post-processing, and then sends the completed video to the user's device.

[0937] The device receives the results and displays the video to the user. The user can then watch the generated cute video of a cat.

[0938] This invention eliminates the need for users to individually manage each generation AI service, enabling them to efficiently obtain the desired generation results from a single interface. Furthermore, it significantly improves the convenience of generation AI technology.

[0939] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0940] Step 1: Receive message

[0941] The server receives messages sent from the terminal.

[0942] Input: The user sent a message saying, "I would like you to create a cute video of my cat."

[0943] Output: Received messages are saved on the server.

[0944] Step 2: Message analysis and request extraction

[0945] The server analyzes received messages using natural language processing (NLP) techniques. Specifically, it utilizes libraries such as SpaCy and NLTK.

[0946] Input: Received message: "I would like you to create a cute video of my cat."

[0947] Data processing: Extract keywords such as "cat," "cute," and "video" from the message.

[0948] Output: Extracted keywords: "cat", "cute", "video".

[0949] Step 3: Selecting a Generative AI Service

[0950] The server selects the optimal generation AI service based on the extracted keywords, taking into account factors such as performance, past performance, and frequency of use.

[0951] Input: Extracted keywords "cat", "cute", "video".

[0952] Data processing: Evaluate the characteristics of each generation AI service and select the optimal service.

[0953] Output: Selected generative AI service (e.g., video generation AI service).

[0954] Step 4: Create Request Data

[0955] The server creates request data for the selected generative AI service. It generates an appropriate request, including a prompt.

[0956] Input: User requirements and selected generation AI service.

[0957] Data processing: Generate request data that includes the prompt "Please create a cute video of a cat".

[0958] Output: Generated request data.

[0959] Step 5: Submit Request

[0960] The server sends the generated request data to the selected generation AI service.

[0961] Input: Generated request data.

[0962] Output: A request is sent to the generation AI service.

[0963] Step 6: Receive the generation result

[0964] The server receives the results generated from the AI ​​generation service.

[0965] Input: Generated results (e.g., video data) sent from a generation AI service.

[0966] Output: The received generation results are saved on the server.

[0967] Step 7: Post-processing

[0968] The server performs post-processing on the generated results as needed, such as format conversion or metadata addition. Specifically, it uses FFmpeg.

[0969] Input: Received generation result.

[0970] Data processing: Converting video formats and adding metadata.

[0971] Output: The generated result after post-processing is complete.

[0972] Step 8: Send Results and Notification

[0973] The server sends the post-processed results to the user's terminal and notifies the user that the results have been generated.

[0974] Input: The generated result after post-processing is complete.

[0975] Output: The generated result is sent to the user's terminal, and a notification is issued.

[0976] Step 9: Receive and display results

[0977] The terminal receives the generated results sent from the server and displays them to the user.

[0978] Input: The generated result sent from the server.

[0979] Output: The generated result will be displayed on the terminal.

[0980] Step 10: Confirm and use of generation results

[0981] The user checks the generated results displayed on the device and uses them.

[0982] Input: The generated result displayed on the terminal.

[0983] Output: The generated result is checked and used.

[0984] (Application Example 1)

[0985] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0986] Conventional generation AI services required users to individually select each service, submit requests, and receive results, resulting in a cumbersome operation. Furthermore, it was difficult for users to understand the characteristics and performance of each generation AI service, making it challenging to select the optimal service. Additionally, post-processing of the generation results required manual work, which was time-consuming and labor-intensive. This invention aims to solve these problems and provide a system that allows users to efficiently utilize generation AI services through a single interface.

[0987] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0988] In this invention, the server includes means for receiving messages, means for analyzing the messages and extracting requests, means for selecting the optimal generation AI service based on the requests, means for sending requests to the generation AI service, means for receiving generation results from the generation AI service, means for returning the generation results to the user, means for performing post-processing on the generation results, and means for performing product searches and suggestions on an e-commerce site. This enables users to efficiently utilize generation AI services from a single point of contact and effectively make use of the generation results.

[0989] A "message" is textual information sent by a user, including requests and instructions regarding the AI ​​generation service.

[0990] "Analysis" is the process of interpreting received messages based on natural language processing technology and extracting user requests.

[0991] A "request" refers to the actions or data that a user wants the AI ​​service to perform or generate.

[0992] A "generative AI service" is an external service or platform that uses AI technology to generate content such as text, images, audio, and video.

[0993] A "request" refers to data based on a request sent to a specific AI-generating service.

[0994] "Generation result" refers to the generated content information returned from the generation AI service.

[0995] "Return" refers to the process of returning the generated results received from the generation AI service back to the user.

[0996] "Post-processing" refers to the process of performing necessary format conversions and adding metadata to the generated results obtained from the generation AI service.

[0997] An "online shopping site" is an online platform where users can search for and purchase products via the internet.

[0998] "Product search" refers to the act of a user searching for a specific product or service on an e-commerce website.

[0999] "Recommendation" refers to the act of recommending appropriate products or services based on the user's needs and preferences.

[1000] This invention relates to a system that allows users to utilize multiple AI-generated services through a single interface. In particular, an example of its implementation as a smartphone application for product search and suggestions on an e-commerce site is provided.

[1001] System Configuration

[1002] The main components are a server and a terminal (smartphone). The server receives messages, analyzes their content, selects the optimal generation AI service, sends requests to the generation AI service, and receives the generation results. The terminal is responsible for receiving and displaying notifications and generation results from the server, as well as inputting the content the user wants to generate.

[1003] Hardware and software to be used

[1004] Server: Uses the Flask framework in Python to manage message reception and request sending.

[1005] Natural Language Processing (NLP) techniques: Message analysis is performed using spaCy in Python.

[1006] Generative AI services: External generative AI platforms (e.g., OpenAI's GPT-3) can be used.

[1007] Smartphone applications: Developed using iOS or Android development environments (Swift or Kotlin).

[1008] Data processing and calculation

[1009] The server processes the data in the following steps:

[1010] 1. Receive messages sent from the terminal and analyze them using NLP (Neuro-Linguistic Programming) technology. This analysis extracts the user's requests.

[1011] 2. Based on the extracted requirements, select the optimal generative AI service. Selection criteria include the performance and frequency of use of the generative AI service.

[1012] 3. Generate request data for the selected generative AI service and send the request.

[1013] 4. Receive the generation results from the generation AI service and perform post-processing on the results as needed. Post-processing includes data format conversion and metadata addition.

[1014] 5. Send the completed generation result to the terminal and notify the user.

[1015] Specific example

[1016] Let's say a user types "I'd like some suggestions for coordinating outfits for women's casual dresses" and sends it to the server.

[1017] The server receives the message and uses NLP technology to extract the keywords "women's casual dress" and "outfit."

[1018] The server selects a fashion-related AI service for generating data (e.g., a fashion suggestion AI service).

[1019] The server creates request data to generate a women's casual dress outfit and sends it to the generation AI service.

[1020] The generation AI service generates suggestions in response to requests and sends the results back to the server.

[1021] The server receives the generated list of suggestions, formats it into a specific format, and sends it to the user's terminal.

[1022] The device displays the list of suggestions received by the user, allowing the user to view the generated list and suggested coordinates.

[1023] Example of a prompt

[1024] User: Can you suggest some casual dress outfit ideas for women?

[1025] AI: I suggest the following three outfit combinations:...

[1026] In this way, users can easily utilize the generated AI service to efficiently perform tasks such as product searches and outfit suggestions on e-commerce sites.

[1027] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1028] Step 1:

[1029] The user enters the content they want to generate using their smartphone. In this case, the user enters "Please give me some ideas for coordinating casual dresses for women." The entered message is then sent to the server.

[1030] Step 2:

[1031] The server receives a message sent by a user. For example, it might receive the message, "Please give me some ideas for coordinating a casual dress for women." This message is then analyzed using natural language processing (NLP) techniques. Specifically, the Python library spaCy is used to extract keywords from the message. The input here is the user's message, and the output is the extracted keywords (e.g., "casual dress for women," "coordination").

[1032] Step 3:

[1033] The server selects the most suitable generative AI service based on the extracted keywords. For example, it might select a generative AI service specializing in fashion suggestions. Past performance and performance indicators are considered in the selection process. In this step, the input is the extracted keywords, and the output is the selected generative AI service (e.g., a fashion suggestion AI service).

[1034] Step 4:

[1035] The server generates request data for the selected AI service. This request data includes the user's request and other necessary metadata. The inputs here are the extracted keywords and the selected AI service, and the output is the generated request data.

[1036] Step 5:

[1037] The server sends the generated request data to the specified AI service. This is done by sending an HTTP request to the AI ​​service's API endpoint. The input here is the request data, and the output is the response from the AI ​​service (the generated suggestion result).

[1038] Step 6:

[1039] The system receives generation results (suggestions) from the generation AI service. The received generation results are temporarily stored on the server, and post-processing is performed as needed. Post-processing includes data format conversion and metadata addition. The input here is the generation result from the generation AI service, and the output is the post-processed generation result.

[1040] Step 7:

[1041] The server returns the post-processed generated results to the user's device. The final data is sent to the user's smartphone app in JSON format or similar. Here, the input is the post-processed generated results, and the output is the notification and display on the user's device.

[1042] Step 8:

[1043] The user checks the generated results displayed on the device. For example, they can see the generated "Women's Casual Dress Coordination Suggestions" on their smartphone screen. In this step, the input is the generated results received by the device, and the output is the user's confirmation action.

[1044] Through these steps, users can easily utilize the AI-generated service and efficiently obtain the necessary suggestions and information.

[1045] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1046] This invention relates to a generative AI service utilization system that incorporates an emotion engine for recognizing user emotions. This system enables users to utilize multiple generative AI services through a single interface and provides optimal generation results while taking user emotions into consideration.

[1047] A natural language explanation of the program's processing.

[1048] server

[1049] 1. Receive messages sent by the user from their device.

[1050] 2. An emotion engine is used to analyze the user's emotions from received messages. Specifically, it analyzes the vocabulary, expressions, and context within the text to identify emotions (such as joy, sadness, or anger).

[1051] 3. Analyze messages using natural language processing (NLP) techniques to extract user requests. Example: Extract keywords such as "cat," "cute," and "video."

[1052] 4. Based on the extracted requests and analyzed emotions, select the optimal generative AI service. This selection will consider factors such as the service's performance, past performance, and compatibility with the emotions. Example: Select generative AI service A, which specializes in video generation.

[1053] 5. Generate request data for the selected generative AI service. The request data includes details of the content the user wants generated (e.g., specific instructions for generating a cute cat video) and analyzed emotions.

[1054] 6. Send the generated request data to the selected generation AI service.

[1055] 7. The generation AI service performs the generation process based on the request and returns the generation result to the server.

[1056] 8. Post-processing is performed on the generated results as needed. Post-processing includes adjusting the content according to the emotion recognition results.

[1057] 9. Send the completed generation results to the user's device and notify the user.

[1058] terminal

[1059] 1. The user enters the content they want to generate and sends the message to the server.

[1060] 2. Receive notifications and generation results from the server and display them to the user.

[1061] User

[1062] 1. Enter the content you want to generate through your device. Example: Enter "I want a cute video of a cat."

[1063] 2. Review and use the generated results sent from the server. The generated results will be provided in an optimal form that reflects the user's emotions.

[1064] Specific example

[1065] For example, suppose a user types into their device, "I'd like you to create a cute video of my cat. I'm feeling a bit down today," and sends it to the system.

[1066] The server receives the message and uses an emotion engine to perform sentiment analysis on the message. Based on the analysis, it determines that the user is "depressed."

[1067] Using natural language processing techniques, the keywords "cat," "cute," and "video" are extracted from the message.

[1068] When selecting a video generation AI service, the server takes into account the user's emotions (feeling down) and selects service A, which can generate cheerful videos to lift the user's spirits.

[1069] The server generates request data to create a cute cat video and sends the request to AI service A. The request data also includes the user's "depressed" emotion.

[1070] AI generation service A generates a cute cat video in response to a request and sends the video back to the server.

[1071] The server receives the generated video, performs post-processing to reflect emotions if necessary, and sends the final video to the user's device.

[1072] The device displays the received video to the user, who then plays and reviews the generated cute cat video. The video is designed to brighten the user's mood.

[1073] By implementing this invention, users can efficiently utilize a generative AI service from a single point of contact and obtain generation results that reflect their own emotions. This improves the convenience of generative AI technology and the user experience.

[1074] The following describes the processing flow.

[1075] Step 1:

[1076] The user uses their device to enter a message containing the content they want generated. For example, they might enter, "I'd like a cute video of my cat. I'm feeling a bit down today."

[1077] Step 2:

[1078] The terminal receives the message entered by the user and sends that message data to the server.

[1079] Step 3:

[1080] The server receives the message sent from the terminal.

[1081] Step 4:

[1082] The server uses an emotion engine to analyze the messages it receives. Specifically, it analyzes the vocabulary, expressions, and context within the text to identify the user's emotions (for example, "feeling down").

[1083] Step 5:

[1084] The server uses natural language processing (NLP) techniques to analyze the message and extract the user's request. For example, it might extract keywords such as "cat," "cute," and "video."

[1085] Step 6:

[1086] The server selects the optimal generation AI service based on the analysis results. Selection criteria include service performance, past performance, frequency of use, and suitability for emotions. Example: Select generation AI service A, which specializes in video generation.

[1087] Step 7:

[1088] The server generates request data for the selected generation AI service. The request data includes details of the content the user wants generated (e.g., specific instructions to generate a cute cat video) and analyzed emotions.

[1089] Step 8:

[1090] The server sends the generated request data to the selected generation AI service. Example: Send a request to generation AI service A.

[1091] Step 9:

[1092] The AI ​​generation service A performs the generation process based on the request, generates a cute video of a cat, and sends the result back to the server.

[1093] Step 10:

[1094] The server receives the generated results. Example: Receives a cute cat video from AI generation service A.

[1095] Step 11:

[1096] The server performs post-processing on the generated results as needed. This post-processing includes adjusting the content based on the emotion recognition results.

[1097] Step 12:

[1098] The server sends the final generation result to the user's terminal.

[1099] Step 13:

[1100] The device receives the generated result sent from the server. Example: It receives a cute video of a cat.

[1101] Step 14:

[1102] The device displays the generated result to the user. The user can view the generated video. The video contains content that will uplift the user's mood.

[1103] (Example 2)

[1104] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1105] Conventional AI-generated service systems faced challenges in providing optimal generated results that took emotions into account, as users had to utilize each service separately. Furthermore, insufficient message analysis and request extraction made it difficult to obtain generated results that adequately reflected user needs.

[1106] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1107] In this invention, the server includes means for receiving messages, means for analyzing messages and recognizing emotions, means for analyzing messages and extracting requests, means for selecting the optimal generative AI service based on the extracted requests and recognized emotions, means for generating and sending request data to the generative AI service, means for receiving generation results from the generative AI service, means for performing necessary post-processing on the generation results, and means for returning the generation results to the user. This enables the user to efficiently utilize the generative AI service and obtain optimal generation results that reflect emotions.

[1108] A "message" refers to text information entered by the user, including requests and emotions directed at the AI-generated service.

[1109] "Means" refers to a device, module, or method for performing a specific function or operation.

[1110] "Means of recognizing emotions" refers to systems and algorithms that analyze and identify a user's emotions based on the vocabulary, expressions, and context within a message.

[1111] "Means of extracting requirements" refers to systems and methods for identifying keywords and phrases related to the user's purpose and desires from a message, and extracting the necessary information.

[1112] "Generative AI services" refer to services that use artificial intelligence technology to generate content and data based on user requests.

[1113] "Request data" refers to data sent to the generating AI service, including the user's requests and analyzed sentiment.

[1114] "Post-processing" refers to operations that perform additional processing on the generated results to optimize or adjust them.

[1115] "Means of returning to the user" refers to communication methods and systems used to deliver the generated results to the user.

[1116] This invention relates to a generative AI service utilization system that incorporates an emotion engine for recognizing user emotions. This system allows users to utilize multiple generative AI services through a single interface and provides optimal generation results while considering the user's emotions. The implementation of this system is described in detail below.

[1117] server

[1118] The server receives messages sent by the user from their terminal.

[1119] The server uses an emotion engine to analyze the user's emotions from received messages. Specifically, it analyzes the vocabulary, expressions, and context within the text to identify emotions (such as joy, sadness, or anger). This emotion engine is implemented in a programming language such as Python and uses natural language processing libraries (e.g., NLTK, spaCy).

[1120] The server uses natural language processing (NLP) techniques to analyze messages and extract user requests. For example, it might extract keywords like "cat," "cute," and "video." This process is also run in Python, using NLP libraries.

[1121] The server selects the optimal generative AI service based on the extracted requests and analyzed emotions. This selection considers factors such as service performance, past performance, and compatibility with the emotions. For example, generative AI service A, which specializes in video generation, is selected.

[1122] The server generates request data for the selected generative AI service. The request data includes details of the content the user wants generated (e.g., specific instructions for generating a cute cat video) and analyzed emotions.

[1123] The server sends the generated request data to the selected generation AI service.

[1124] The generation AI service performs the generation process based on the request and sends the generation result (e.g., the generated video) back to the server.

[1125] The server receives the generated results and performs post-processing as needed. Post-processing includes adjusting the content based on the emotion recognition results (e.g., adjusting video brightness or selecting music).

[1126] The server sends the completed generation results to the user's terminal and notifies the user.

[1127] terminal

[1128] It provides an interface for users to input the content they want to generate.

[1129] The terminal receives user input and sends that message to the server.

[1130] The terminal receives notifications and generated results from the server and displays them to the user.

[1131] User

[1132] The user enters the content they want to generate via their device and sends the message to the server. For example, they might enter, "I'd like a cute video of my cat. I'm feeling a bit down today."

[1133] The user reviews and uses the generated results sent from the server. The generated results are provided in an optimal form that reflects the user's emotions.

[1134] Specific example

[1135] For example, suppose a user types into their device, "I'd like you to create a cute video of my cat. I'm feeling a bit down today," and sends it to the system.

[1136] The server receives the message and uses an emotion engine to perform sentiment analysis on the message. Based on the analysis, it determines that the user is "depressed."

[1137] Using natural language processing techniques, the keywords "cat," "cute," and "video" are extracted from the message.

[1138] When selecting a video generation AI service, the server takes into account the user's emotions (feeling down) and selects service A, which can generate cheerful videos to lift the user's spirits.

[1139] The server generates request data to create a cute cat video and sends the request to AI service A. The request data also includes the user's "depressed" emotion.

[1140] AI generation service A generates a cute cat video in response to a request and sends the video back to the server.

[1141] The server receives the generated video, performs post-processing to reflect emotions if necessary, and sends the final video to the user's device.

[1142] The device displays the received video to the user, who then plays and reviews the generated cute cat video. The video is designed to brighten the user's mood.

[1143] In this way, the present invention allows users to efficiently utilize the generation AI service from a single point of contact and obtain optimal generation results that reflect their own emotions. This improves the convenience of generation AI technology and the user experience.

[1144] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1145] Step 1:

[1146] The user enters the content they want to generate into the terminal interface and sends a message to the server. The input may include text such as, "I'd like a cute video of my cat. I'm feeling a bit down today." This sends a message to the server expressing the user's request and feelings.

[1147] Step 2:

[1148] The server receives messages sent from the terminal. The received messages are stored in the server's database in text format.

[1149] Input: Received message (text)

[1150] Output: Text saved in the database

[1151] Step 3:

[1152] The server uses an emotion engine to recognize emotions from received messages. The emotion engine analyzes the vocabulary, expressions, and context within the text to identify emotions such as joy, sadness, and anger.

[1153] Input: Saved text

[1154] Data processing: Analyzing emotions using natural language processing techniques.

[1155] Output: Identified emotion (e.g., depressed)

[1156] Step 4:

[1157] The server uses natural language processing (NLP) techniques to analyze the message content and extract the user's request. For example, it might identify keywords such as "cat," "cute," and "video" from the message.

[1158] Input: Saved text

[1159] Data processing: Analyze requirements using a keyword extraction algorithm.

[1160] Output: Extracted keywords (e.g., cat, cute, video)

[1161] Step 5:

[1162] The server selects the optimal generative AI service based on the extracted requests and analyzed emotions. This selection considers factors such as service performance, past performance, and compatibility with the emotions. For example, it might select service A, which can generate videos that uplift the user.

[1163] Input: Extracted keywords, identified emotions

[1164] Data processing: Evaluation and selection of multiple generative AI services.

[1165] Output: Selected generative AI service (e.g., Service A)

[1166] Step 6:

[1167] The server generates request data for the selected generative AI service. This request data includes details of the generated content requested by the user and an analyzed sentiment.

[1168] Input: Extracted keywords, identified sentiment, selected generative AI service

[1169] Data processing: Generating request data

[1170] Output: Generated request data

[1171] Step 7:

[1172] The server sends the generated request data to the selected generation AI service. This transmission is performed using a communication protocol.

[1173] Input: Generated request data

[1174] Output: Request data sent to the AI ​​generation service

[1175] Step 8:

[1176] The AI ​​generation service processes content generation based on the request and returns the generated result (e.g., the generated video) to the server.

[1177] Input: Request data (generation instructions and sentiment information)

[1178] Output: Generated content (e.g., a cute video of a cat)

[1179] Step 9:

[1180] The server receives the generated results and performs post-processing as needed. Post-processing includes adjusting the content based on the emotion recognition results (e.g., adjusting video brightness or selecting music).

[1181] Input: Generated content

[1182] Data processing: Optimization based on emotion recognition results

[1183] Output: Post-processed generated content

[1184] Step 10:

[1185] The server sends the completed generation results to the user's terminal and notifies the user.

[1186] Input: Post-processed generated content

[1187] Output: Generated content sent to the user's terminal

[1188] Step 11:

[1189] Users view and use the generated results (e.g., cute cat videos) on their devices. The videos displayed on the device are optimized to reflect the user's emotions.

[1190] Input: Generated content sent from the server

[1191] Output: Generated content that users view and use (e.g., cute cat videos)

[1192] (Application Example 2)

[1193] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1194] In modern content delivery services, it is difficult for users to automatically and efficiently find the most suitable content based on their emotional state. Furthermore, the lack of a system that allows users to enjoy content that reflects their own emotions can lead to a diminished user experience. Therefore, a new system is needed that considers user emotions and recommends the most suitable content based on those emotions.

[1195] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1196] In this invention, the server includes means for receiving messages, means for analyzing the messages to recognize emotions and extract requests, and means for selecting the optimal generative AI service based on the emotions and requests. This makes it possible to automatically recommend the most suitable content according to the user's emotional state.

[1197] A "means of receiving messages" is an interface for electronically receiving user input and initiating processing.

[1198] "A means of analyzing messages to recognize emotions and extract requests" refers to a function that analyzes received messages using natural language processing technology and extracts the user's emotional state and specific requests from them.

[1199] "Emotions" refer to the mental states of users extracted from their input, including feelings such as joy, sadness, and anger.

[1200] A "request" refers to a specific request or need that a user makes to the system, such as asking for actions like recommending specific content or generating specific information.

[1201] "Means for selecting the optimal generative AI service" refers to algorithms and methods for selecting the most suitable service from among multiple existing generative AI services based on emotions and requests.

[1202] "Means for sending requests to a generation AI service" refers to a means of communication for requesting a selected generation AI service to perform processing according to the user's requirements.

[1203] "Means for receiving generation results from the generation AI service" refers to a function for receiving data when the generation AI service completes processing and sends the results back to the server.

[1204] "Means for returning the generation results to the user" refers to an interface for sending the received generation results to the user's terminal and providing them to the user.

[1205] "Natural language processing technology" refers to a set of techniques that enable computers to understand, interpret, and respond to human language, and is used for text analysis, sentiment recognition, request extraction, and more.

[1206] "Post-processing including emotion-based adjustments" refers to the process of further fine-tuning the generated results received from the generation AI service to match the user's emotions, with the aim of improving the user experience.

[1207] A specific system for carrying out this invention includes the following steps:

[1208] The server receives input messages from the user. Text format is preferred for these messages. A network communication module is used to receive messages entered from user terminals such as smartphones.

[1209] Next, the server analyzes the received message using natural language processing techniques to recognize the user's emotions and extract requests from the message content. This process utilizes natural language processing libraries such as TextBlob. For example, if a user enters "I'm very tired today," the server recognizes the emotion of "tired" from this message and extracts the request "I would like recommendations for content suitable for rest."

[1210] After emotions and requests are extracted, the server selects the most suitable generative AI service based on this information. This selection takes into account past performance and compatibility with the user's emotions. The generative AI service may utilize the latest deep learning models, among others.

[1211] A request is sent to the selected generative AI service, tailored to the user's needs. The request data includes information about the user's emotions. The generative AI service then provides the most suitable generation result based on this request. For example, a streaming music service might provide relaxing music.

[1212] Once the generation AI service returns the generated results, the server performs further emotion-based post-processing as needed. This adjusts the content to better reflect the user's emotions.

[1213] Finally, the generated results are sent to the user's device and the user is notified. The user can then access the generated content through their device. This entire process allows the user to easily obtain content optimized for their own emotions.

[1214] For example, if a user types "I'm very tired today" into their smartphone, the system will recommend a relaxing movie that matches that feeling. This improves the user experience.

[1215] Examples of prompt messages include the following:

[1216] "Please tell me how you're feeling right now: I'm very tired today."

[1217] "I recommend this to you: Guardians of the Galaxy (movie)"

[1218] This allows users to easily find content that suits their emotions, resulting in a highly satisfying experience.

[1219] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1220] Step 1:

[1221] The user uses a terminal to type a message containing emotions and requests. For example, they might type, "I'm very tired today." Input: The user's text message. Output: The message sent from the terminal to the server.

[1222] Step 2:

[1223] The server receives messages sent from the terminal. The received data is stored in text format. Input: Message sent from the terminal. Output: Received message data.

[1224] Step 3:

[1225] The server analyzes received messages using natural language processing techniques to recognize the user's emotions and extract requests. Specifically, it uses libraries such as TextBlob to identify emotions (positive, negative, neutral) and pinpoint the emotion "tired." Input: Received message data. Output: Analyzed emotions and extracted requests.

[1226] Step 4:

[1227] The server selects the optimal generative AI service based on the analyzed emotions and requests. From the available generative AI services, it chooses the one best suited to the user's emotions. Input: Analyzed emotion and request data. Output: Selected generative AI service.

[1228] Step 5:

[1229] The server sends a request to the selected generative AI service. The request data includes the user's sentiment information and specific request details. Input: Selected generative AI service, request data, sentiment data. Output: Request data sent to the generative AI service.

[1230] Step 6:

[1231] The AI ​​generation service processes requests from the server and returns the generated content to the server. For example, it could recommend relaxing movies. Input: Request data from the server. Output: Generated content data.

[1232] Step 7:

[1233] The server receives content data returned from the AI ​​generation service and performs post-processing as needed. It makes emotion-based adjustments and determines the final content. Input: Generated content data. Output: Post-processed final content data.

[1234] Step 8:

[1235] The server sends the post-processed final content data to the user's terminal and notifies them. Input: Final content data. Output: Content data sent to the user's terminal.

[1236] Step 9:

[1237] Users view and use content received through their devices. For example, they might watch a recommended movie. Input: Content data received from the server. Output: Displayed content.

[1238] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1239] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1240] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1241] [Fourth Embodiment]

[1242] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1243] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1244] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1245] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1246] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1247] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1248] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1249] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1250] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1251] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1252] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1253] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1254] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1255] This invention provides a system that enables a user to utilize multiple generative AI services through a single interface. This system automatically performs a series of processes, including receiving and analyzing messages, selecting the optimal generative AI service, sending requests, receiving generation results, and returning them to the user.

[1256] A natural language explanation of the program's processing.

[1257] server

[1258] 1. Receive messages sent by the user from their device.

[1259] 2. The received message is analyzed using natural language processing (NLP) technology to extract the user's request.

[1260] 3. Based on the extracted requirements, select the optimal generation AI service. This selection will take into account the service's performance, past performance, and frequency of use.

[1261] 4. Create request data for the selected generative AI service and send the request.

[1262] 5. Receive the generated results (e.g., video, text, images, audio, etc.) from the generation AI service.

[1263] 6. If necessary, perform post-processing on the generated results (format conversion, metadata addition, etc.).

[1264] 7. The completed generation results are sent to the user's terminal and the user is notified.

[1265] terminal

[1266] 1. The user enters the content they want to generate and sends the message to the server.

[1267] 2. Receive notifications and generation results from the server and display them to the user.

[1268] User

[1269] 1. Enter the content you want to generate via your device.

[1270] 2. Check and use the generated results sent from the server.

[1271] Specific example

[1272] For example, suppose a user enters a message into their device saying, "I would like you to create a cute video of my cat," and sends it to the system.

[1273] The server receives the message and uses natural language processing technology to extract keywords such as "cat," "cute," and "video."

[1274] The server selects a generation AI service specifically designed for video generation. For example, video generation AI service A might be selected.

[1275] The server generates request data for creating a cute cat video and sends the request to AI generation service A.

[1276] AI generation service A generates a cute cat video in response to a request and sends the result back to the server.

[1277] The server receives the generated video, performs any necessary post-processing, and sends the final video to the user's device.

[1278] The device displays the received video to the user, allowing the user to view the generated cute cat video.

[1279] By implementing this invention, users can eliminate the need to individually manage each generation AI service and efficiently obtain their desired generation results from a single point of contact. This system significantly improves the convenience of generation AI technology.

[1280] The following describes the processing flow.

[1281] Step 1:

[1282] The user uses their device to enter a message containing the content they want generated. For example, they might enter, "I want a cute video of a cat."

[1283] Step 2:

[1284] The terminal receives the message entered by the user and sends that message data to the server.

[1285] Step 3:

[1286] The server receives the message sent from the terminal.

[1287] Step 4:

[1288] The server analyzes received messages using natural language processing (NLP) techniques. Specifically, it extracts keywords and context from messages to understand user requests. For example, it might extract keywords such as "cat," "cute," and "video."

[1289] Step 5:

[1290] The server selects the optimal generation AI service based on the analysis results. Selection criteria include service performance, past performance, and frequency of use. Example: Select generation AI service A, which specializes in video generation.

[1291] Step 6:

[1292] The server generates request data for the selected generation AI service. The request data includes details of the content the user wants generated (e.g., specific instructions for generating a cute cat video).

[1293] Step 7:

[1294] The server sends the generated request data to the selected generation AI service. Example: Send a request to generation AI service A.

[1295] Step 8:

[1296] The generation AI service performs generation processing based on the request and creates the generated result. Example: Generate a cute video of a cat.

[1297] Step 9:

[1298] The AI ​​generation service sends the generated results back to the server.

[1299] Step 10:

[1300] The server receives the generated results. Example: Receives a cute cat video from AI generation service A.

[1301] Step 11:

[1302] If necessary, the server performs post-processing on the generated results. For example, this may include format conversion or the addition of metadata.

[1303] Step 12:

[1304] The server sends the final generation result to the user's terminal.

[1305] Step 13:

[1306] The device receives the generated result sent from the server. Example: It receives a cute video of a cat.

[1307] Step 14:

[1308] The device displays the generated result to the user. The user can then view the generated video.

[1309] (Example 1)

[1310] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1311] Currently, for users to utilize multiple generative AI services, they need to access each service individually and configure and operate each platform separately. This is time-consuming and inefficient for users. Furthermore, understanding the performance and characteristics of each generative AI service and selecting the appropriate one is difficult, making it challenging to obtain optimal results.

[1312] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1313] In this invention, the server includes means for receiving messages, means for analyzing messages and extracting requests, means for selecting the optimal generative artificial intelligence service, means for sending requests to the generative artificial intelligence service, means for receiving generation results from the generative artificial intelligence service, means for performing post-processing on the generation results as necessary, and means for sending and notifying the user terminal of the generation results. This enables the user to efficiently utilize multiple generative AI services through a single interface and obtain the optimal generation result.

[1314] "Means for receiving messages" refers to a function that receives messages sent from a user terminal and processes their content.

[1315] "Means for analyzing messages and extracting requests" refers to a function that uses natural language processing technology to analyze received messages and clearly extract the user's requirements.

[1316] "Means for selecting the optimal generative artificial intelligence service" refers to a function that selects the optimal generative AI service based on extracted requirements, taking into account performance, past performance, frequency of use, etc.

[1317] "Means for sending requests to a generative artificial intelligence service" refers to a function for sending request data in accordance with the user's request to a selected generative AI service.

[1318] "Means for receiving generation results from a generation artificial intelligence service" refers to a function for receiving generation results sent from a generation AI service.

[1319] "Means for performing post-processing on the generated results as needed" refers to functions for performing post-processing on the received generated results, such as format conversion or the addition of metadata.

[1320] "Means for sending and notifying the user of the generation results" refers to a function for sending the post-processed generation results to the user's terminal and notifying the user.

[1321] This invention provides a system that enables users to efficiently utilize multiple generative AI services through a single interface. This system consists of a server, a terminal, and a user, and automatically performs a series of processes.

[1322] Hardware and software configuration

[1323] server

[1324] Message reception: The server receives messages sent by the user from their terminal.

[1325] Message analysis: Received messages are analyzed using natural language processing (NLP) techniques (e.g., SpaCy or NLTK library) to extract user requests.

[1326] Service Selection: Based on the extracted requirements, the optimal generative artificial intelligence service will be selected considering performance, track record, frequency of use, etc. For example, OpenAI or similar services will be used for the generative AI model.

[1327] Request data creation: Create request data for the selected generative AI service and send the data, including the prompt message.

[1328] Result reception: Receives generated results from the generation AI service, including in formats such as video, text, images, and audio.

[1329] Post-processing: Perform post-processing as needed, such as format conversion or metadata addition. For example, use FFmpeg to convert the video format.

[1330] Notification / Sending: The completed generation results are sent to the user's terminal, and the user is notified that the results have been generated.

[1331] terminal

[1332] Message Input and Sending: The user inputs the content they want to generate via their terminal and sends the message to the server.

[1333] Result Reception and Display: Receives results and displays them to the user. For example, if the user enters "I want a cute video of a cat," the results will be displayed on the device.

[1334] User

[1335] Content Input: The user enters the content they want to generate into the terminal. Specifically, they enter prompt messages such as "Please create a cute video of a cat" or "Please generate a photo of a flower field."

[1336] Confirmation and Use of Generated Results: Users can confirm and use the generated results.

[1337] Specific example

[1338] For example, a user might type a message into their device saying, "I want you to create a cute video of my cat," and send it to the system.

[1339] The server receives the message and uses natural language processing technology to analyze and extract keywords such as "cat," "cute," and "video."

[1340] The server selects a generation AI service suitable for video generation, for example, a video generation AI, which is one of the generation AI models.

[1341] The server creates request data that includes the prompt "Please create a cute video of a cat" and sends it to the AI ​​generation service.

[1342] The AI ​​generation service generates cute cat videos in response to requests and sends the results back to the server.

[1343] The server receives the generated results, performs any necessary post-processing, and then sends the completed video to the user's device.

[1344] The device receives the results and displays the video to the user. The user can then watch the generated cute video of a cat.

[1345] This invention eliminates the need for users to individually manage each generation AI service, enabling them to efficiently obtain the desired generation results from a single interface. Furthermore, it significantly improves the convenience of generation AI technology.

[1346] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1347] Step 1: Receive message

[1348] The server receives messages sent from the terminal.

[1349] Input: The user sent a message saying, "I would like you to create a cute video of my cat."

[1350] Output: Received messages are saved on the server.

[1351] Step 2: Message analysis and request extraction

[1352] The server analyzes received messages using natural language processing (NLP) techniques. Specifically, it utilizes libraries such as SpaCy and NLTK.

[1353] Input: Received message: "I would like you to create a cute video of my cat."

[1354] Data processing: Extract keywords such as "cat," "cute," and "video" from the message.

[1355] Output: Extracted keywords: "cat", "cute", "video".

[1356] Step 3: Selecting a Generative AI Service

[1357] The server selects the optimal generation AI service based on the extracted keywords, taking into account factors such as performance, past performance, and frequency of use.

[1358] Input: Extracted keywords "cat", "cute", "video".

[1359] Data processing: Evaluate the characteristics of each generation AI service and select the optimal service.

[1360] Output: Selected generative AI service (e.g., video generation AI service).

[1361] Step 4: Create Request Data

[1362] The server creates request data for the selected generative AI service. It generates an appropriate request, including a prompt.

[1363] Input: User requirements and selected generation AI service.

[1364] Data processing: Generate request data that includes the prompt "Please create a cute video of a cat".

[1365] Output: Generated request data.

[1366] Step 5: Submit Request

[1367] The server sends the generated request data to the selected generation AI service.

[1368] Input: Generated request data.

[1369] Output: A request is sent to the generation AI service.

[1370] Step 6: Receive the generation result

[1371] The server receives the results generated from the AI ​​generation service.

[1372] Input: Generated results (e.g., video data) sent from a generation AI service.

[1373] Output: The received generation results are saved on the server.

[1374] Step 7: Post-processing

[1375] The server performs post-processing on the generated results as needed, such as format conversion or metadata addition. Specifically, it uses FFmpeg.

[1376] Input: Received generation result.

[1377] Data processing: Converting video formats and adding metadata.

[1378] Output: The generated result after post-processing is complete.

[1379] Step 8: Send Results and Notification

[1380] The server sends the post-processed results to the user's terminal and notifies the user that the results have been generated.

[1381] Input: The generated result after post-processing is complete.

[1382] Output: The generated result is sent to the user's terminal, and a notification is issued.

[1383] Step 9: Receive and display results

[1384] The terminal receives the generated results sent from the server and displays them to the user.

[1385] Input: The generated result sent from the server.

[1386] Output: The generated result will be displayed on the terminal.

[1387] Step 10: Confirm and use of generation results

[1388] The user checks the generated results displayed on the device and uses them.

[1389] Input: The generated result displayed on the terminal.

[1390] Output: The generated result is checked and used.

[1391] (Application Example 1)

[1392] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1393] Conventional generation AI services required users to individually select each service, submit requests, and receive results, resulting in a cumbersome operation. Furthermore, it was difficult for users to understand the characteristics and performance of each generation AI service, making it challenging to select the optimal service. Additionally, post-processing of the generation results required manual work, which was time-consuming and labor-intensive. This invention aims to solve these problems and provide a system that allows users to efficiently utilize generation AI services through a single interface.

[1394] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1395] In this invention, the server includes means for receiving messages, means for analyzing the messages and extracting requests, means for selecting the optimal generation AI service based on the requests, means for sending requests to the generation AI service, means for receiving generation results from the generation AI service, means for returning the generation results to the user, means for performing post-processing on the generation results, and means for performing product searches and suggestions on an e-commerce site. This enables users to efficiently utilize generation AI services from a single point of contact and effectively make use of the generation results.

[1396] A "message" is textual information sent by a user, including requests and instructions regarding the AI ​​generation service.

[1397] "Analysis" is the process of interpreting received messages based on natural language processing technology and extracting user requests.

[1398] A "request" refers to the actions or data that a user wants the AI ​​service to perform or generate.

[1399] A "generative AI service" is an external service or platform that uses AI technology to generate content such as text, images, audio, and video.

[1400] A "request" refers to data based on a request sent to a specific AI-generating service.

[1401] "Generation result" refers to the generated content information returned from the generation AI service.

[1402] "Return" refers to the process of returning the generated results received from the generation AI service back to the user.

[1403] "Post-processing" refers to the process of performing necessary format conversions and adding metadata to the generated results obtained from the generation AI service.

[1404] An "online shopping site" is an online platform where users can search for and purchase products via the internet.

[1405] "Product search" refers to the act of a user searching for a specific product or service on an e-commerce website.

[1406] "Recommendation" refers to the act of recommending appropriate products or services based on the user's needs and preferences.

[1407] This invention relates to a system that allows users to utilize multiple AI-generated services through a single interface. In particular, an example of its implementation as a smartphone application for product search and suggestions on an e-commerce site is provided.

[1408] System Configuration

[1409] The main components are a server and a terminal (smartphone). The server receives messages, analyzes their content, selects the optimal generation AI service, sends requests to the generation AI service, and receives the generation results. The terminal is responsible for receiving and displaying notifications and generation results from the server, as well as inputting the content the user wants to generate.

[1410] Hardware and software to be used

[1411] Server: Uses the Flask framework in Python to manage message reception and request sending.

[1412] Natural Language Processing (NLP) techniques: Message analysis is performed using spaCy in Python.

[1413] Generative AI services: External generative AI platforms (e.g., OpenAI's GPT-3) can be used.

[1414] Smartphone applications: Developed using iOS or Android development environments (Swift or Kotlin).

[1415] Data processing and calculation

[1416] The server processes the data in the following steps:

[1417] 1. Receive messages sent from the terminal and analyze them using NLP (Neuro-Linguistic Programming) technology. This analysis extracts the user's requests.

[1418] 2. Based on the extracted requirements, select the optimal generative AI service. Selection criteria include the performance and frequency of use of the generative AI service.

[1419] 3. Generate request data for the selected generative AI service and send the request.

[1420] 4. Receive the generation results from the generation AI service and perform post-processing on the results as needed. Post-processing includes data format conversion and metadata addition.

[1421] 5. Send the completed generation result to the terminal and notify the user.

[1422] Specific example

[1423] Let's say a user types "I'd like some suggestions for coordinating outfits for women's casual dresses" and sends it to the server.

[1424] The server receives the message and uses NLP technology to extract the keywords "women's casual dress" and "outfit."

[1425] The server selects a fashion-related AI service for generating data (e.g., a fashion suggestion AI service).

[1426] The server creates request data to generate a women's casual dress outfit and sends it to the generation AI service.

[1427] The generation AI service generates suggestions in response to requests and sends the results back to the server.

[1428] The server receives the generated list of suggestions, formats it into a specific format, and sends it to the user's terminal.

[1429] The device displays the list of suggestions received by the user, allowing the user to view the generated list and suggested coordinates.

[1430] Example of a prompt

[1431] User: Can you suggest some casual dress outfit ideas for women?

[1432] AI: I suggest the following three outfit combinations:...

[1433] In this way, users can easily utilize the generated AI service to efficiently perform tasks such as product searches and outfit suggestions on e-commerce sites.

[1434] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1435] Step 1:

[1436] The user enters the content they want to generate using their smartphone. In this case, the user enters "Please give me some ideas for coordinating casual dresses for women." The entered message is then sent to the server.

[1437] Step 2:

[1438] The server receives a message sent by a user. For example, it might receive the message, "Please give me some ideas for coordinating a casual dress for women." This message is then analyzed using natural language processing (NLP) techniques. Specifically, the Python library spaCy is used to extract keywords from the message. The input here is the user's message, and the output is the extracted keywords (e.g., "casual dress for women," "coordination").

[1439] Step 3:

[1440] The server selects the most suitable generative AI service based on the extracted keywords. For example, it might select a generative AI service specializing in fashion suggestions. Past performance and performance indicators are considered in the selection process. In this step, the input is the extracted keywords, and the output is the selected generative AI service (e.g., a fashion suggestion AI service).

[1441] Step 4:

[1442] The server generates request data for the selected AI service. This request data includes the user's request and other necessary metadata. The inputs here are the extracted keywords and the selected AI service, and the output is the generated request data.

[1443] Step 5:

[1444] The server sends the generated request data to the specified AI service. This is done by sending an HTTP request to the AI ​​service's API endpoint. The input here is the request data, and the output is the response from the AI ​​service (the generated suggestion result).

[1445] Step 6:

[1446] The system receives generation results (suggestions) from the generation AI service. The received generation results are temporarily stored on the server, and post-processing is performed as needed. Post-processing includes data format conversion and metadata addition. The input here is the generation result from the generation AI service, and the output is the post-processed generation result.

[1447] Step 7:

[1448] The server returns the post-processed generated results to the user's device. The final data is sent to the user's smartphone app in JSON format or similar. Here, the input is the post-processed generated results, and the output is the notification and display on the user's device.

[1449] Step 8:

[1450] The user checks the generated results displayed on the device. For example, they can see the generated "Women's Casual Dress Coordination Suggestions" on their smartphone screen. In this step, the input is the generated results received by the device, and the output is the user's confirmation action.

[1451] Through these steps, users can easily utilize the AI-generated service and efficiently obtain the necessary suggestions and information.

[1452] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1453] This invention relates to a generative AI service utilization system that incorporates an emotion engine for recognizing user emotions. This system enables users to utilize multiple generative AI services through a single interface and provides optimal generation results while taking user emotions into consideration.

[1454] A natural language explanation of the program's processing.

[1455] server

[1456] 1. Receive messages sent by the user from their device.

[1457] 2. An emotion engine is used to analyze the user's emotions from received messages. Specifically, it analyzes the vocabulary, expressions, and context within the text to identify emotions (such as joy, sadness, or anger).

[1458] 3. Analyze messages using natural language processing (NLP) techniques to extract user requests. Example: Extract keywords such as "cat," "cute," and "video."

[1459] 4. Based on the extracted requests and analyzed emotions, select the optimal generative AI service. This selection will consider factors such as the service's performance, past performance, and compatibility with the emotions. Example: Select generative AI service A, which specializes in video generation.

[1460] 5. Generate request data for the selected generative AI service. The request data includes details of the content the user wants generated (e.g., specific instructions for generating a cute cat video) and analyzed emotions.

[1461] 6. Send the generated request data to the selected generation AI service.

[1462] 7. The generation AI service performs the generation process based on the request and returns the generation result to the server.

[1463] 8. Post-processing is performed on the generated results as needed. Post-processing includes adjusting the content according to the emotion recognition results.

[1464] 9. Send the completed generation results to the user's device and notify the user.

[1465] terminal

[1466] 1. The user enters the content they want to generate and sends the message to the server.

[1467] 2. Receive notifications and generation results from the server and display them to the user.

[1468] User

[1469] 1. Enter the content you want to generate through your device. Example: Enter "I want a cute video of a cat."

[1470] 2. Review and use the generated results sent from the server. The generated results will be provided in an optimal form that reflects the user's emotions.

[1471] Specific example

[1472] For example, suppose a user types into their device, "I'd like you to create a cute video of my cat. I'm feeling a bit down today," and sends it to the system.

[1473] The server receives the message and uses an emotion engine to perform sentiment analysis on the message. Based on the analysis, it determines that the user is "depressed."

[1474] Using natural language processing techniques, the keywords "cat," "cute," and "video" are extracted from the message.

[1475] When selecting a video generation AI service, the server takes into account the user's emotions (feeling down) and selects service A, which can generate cheerful videos to lift the user's spirits.

[1476] The server generates request data to create a cute cat video and sends the request to AI service A. The request data also includes the user's "depressed" emotion.

[1477] AI generation service A generates a cute cat video in response to a request and sends the video back to the server.

[1478] The server receives the generated video, performs post-processing to reflect emotions if necessary, and sends the final video to the user's device.

[1479] The device displays the received video to the user, who then plays and reviews the generated cute cat video. The video is designed to brighten the user's mood.

[1480] By implementing this invention, users can efficiently utilize a generative AI service from a single point of contact and obtain generation results that reflect their own emotions. This improves the convenience of generative AI technology and the user experience.

[1481] The following describes the processing flow.

[1482] Step 1:

[1483] The user uses their device to enter a message containing the content they want generated. For example, they might enter, "I'd like a cute video of my cat. I'm feeling a bit down today."

[1484] Step 2:

[1485] The terminal receives the message entered by the user and sends that message data to the server.

[1486] Step 3:

[1487] The server receives the message sent from the terminal.

[1488] Step 4:

[1489] The server uses an emotion engine to analyze the messages it receives. Specifically, it analyzes the vocabulary, expressions, and context within the text to identify the user's emotions (for example, "feeling down").

[1490] Step 5:

[1491] The server uses natural language processing (NLP) techniques to analyze the message and extract the user's request. For example, it might extract keywords such as "cat," "cute," and "video."

[1492] Step 6:

[1493] The server selects the optimal generation AI service based on the analysis results. Selection criteria include service performance, past performance, frequency of use, and suitability for emotions. Example: Select generation AI service A, which specializes in video generation.

[1494] Step 7:

[1495] The server generates request data for the selected generation AI service. The request data includes details of the content the user wants generated (e.g., specific instructions to generate a cute cat video) and analyzed emotions.

[1496] Step 8:

[1497] The server sends the generated request data to the selected generation AI service. Example: Send a request to generation AI service A.

[1498] Step 9:

[1499] The AI ​​generation service A performs the generation process based on the request, generates a cute video of a cat, and sends the result back to the server.

[1500] Step 10:

[1501] The server receives the generated results. Example: Receives a cute cat video from AI generation service A.

[1502] Step 11:

[1503] The server performs post-processing on the generated results as needed. This post-processing includes adjusting the content based on the emotion recognition results.

[1504] Step 12:

[1505] The server sends the final generation result to the user's terminal.

[1506] Step 13:

[1507] The device receives the generated result sent from the server. Example: It receives a cute video of a cat.

[1508] Step 14:

[1509] The device displays the generated result to the user. The user can view the generated video. The video contains content that will uplift the user's mood.

[1510] (Example 2)

[1511] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1512] Conventional AI-generated service systems faced challenges in providing optimal generated results that took emotions into account, as users had to utilize each service separately. Furthermore, insufficient message analysis and request extraction made it difficult to obtain generated results that adequately reflected user needs.

[1513] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1514] In this invention, the server includes means for receiving messages, means for analyzing messages and recognizing emotions, means for analyzing messages and extracting requests, means for selecting the optimal generative AI service based on the extracted requests and recognized emotions, means for generating and sending request data to the generative AI service, means for receiving generation results from the generative AI service, means for performing necessary post-processing on the generation results, and means for returning the generation results to the user. This enables the user to efficiently utilize the generative AI service and obtain optimal generation results that reflect emotions.

[1515] A "message" refers to text information entered by the user, including requests and emotions directed at the AI-generated service.

[1516] "Means" refers to a device, module, or method for performing a specific function or operation.

[1517] "Means of recognizing emotions" refers to systems and algorithms that analyze and identify a user's emotions based on the vocabulary, expressions, and context within a message.

[1518] "Means of extracting requirements" refers to systems and methods for identifying keywords and phrases related to the user's purpose and desires from a message, and extracting the necessary information.

[1519] "Generative AI services" refer to services that use artificial intelligence technology to generate content and data based on user requests.

[1520] "Request data" refers to data sent to the generating AI service, including the user's requests and analyzed sentiment.

[1521] "Post-processing" refers to operations that perform additional processing on the generated results to optimize or adjust them.

[1522] "Means of returning to the user" refers to communication methods and systems used to deliver the generated results to the user.

[1523] This invention relates to a generative AI service utilization system that incorporates an emotion engine for recognizing user emotions. This system allows users to utilize multiple generative AI services through a single interface and provides optimal generation results while considering the user's emotions. The implementation of this system is described in detail below.

[1524] server

[1525] The server receives messages sent by the user from their terminal.

[1526] The server uses an emotion engine to analyze the user's emotions from received messages. Specifically, it analyzes the vocabulary, expressions, and context within the text to identify emotions (such as joy, sadness, or anger). This emotion engine is implemented in a programming language such as Python and uses natural language processing libraries (e.g., NLTK, spaCy).

[1527] The server uses natural language processing (NLP) techniques to analyze messages and extract user requests. For example, it might extract keywords like "cat," "cute," and "video." This process is also run in Python, using NLP libraries.

[1528] The server selects the optimal generative AI service based on the extracted requests and analyzed emotions. This selection considers factors such as service performance, past performance, and compatibility with the emotions. For example, generative AI service A, which specializes in video generation, is selected.

[1529] The server generates request data for the selected generative AI service. The request data includes details of the content the user wants generated (e.g., specific instructions for generating a cute cat video) and analyzed emotions.

[1530] The server sends the generated request data to the selected generation AI service.

[1531] The generation AI service performs the generation process based on the request and sends the generation result (e.g., the generated video) back to the server.

[1532] The server receives the generated results and performs post-processing as needed. Post-processing includes adjusting the content based on the emotion recognition results (e.g., adjusting video brightness or selecting music).

[1533] The server sends the completed generation results to the user's terminal and notifies the user.

[1534] terminal

[1535] It provides an interface for users to input the content they want to generate.

[1536] The terminal receives user input and sends that message to the server.

[1537] The terminal receives notifications and generated results from the server and displays them to the user.

[1538] User

[1539] The user enters the content they want to generate via their device and sends the message to the server. For example, they might enter, "I'd like a cute video of my cat. I'm feeling a bit down today."

[1540] The user reviews and uses the generated results sent from the server. The generated results are provided in an optimal form that reflects the user's emotions.

[1541] Specific example

[1542] For example, suppose a user types into their device, "I'd like you to create a cute video of my cat. I'm feeling a bit down today," and sends it to the system.

[1543] The server receives the message and uses an emotion engine to perform sentiment analysis on the message. Based on the analysis, it determines that the user is "depressed."

[1544] Using natural language processing techniques, the keywords "cat," "cute," and "video" are extracted from the message.

[1545] When selecting a video generation AI service, the server takes into account the user's emotions (feeling down) and selects service A, which can generate cheerful videos to lift the user's spirits.

[1546] The server generates request data to create a cute cat video and sends the request to AI service A. The request data also includes the user's "depressed" emotion.

[1547] AI generation service A generates a cute cat video in response to a request and sends the video back to the server.

[1548] The server receives the generated video, performs post-processing to reflect emotions if necessary, and sends the final video to the user's device.

[1549] The device displays the received video to the user, who then plays and reviews the generated cute cat video. The video is designed to brighten the user's mood.

[1550] In this way, the present invention allows users to efficiently utilize the generation AI service from a single point of contact and obtain optimal generation results that reflect their own emotions. This improves the convenience of generation AI technology and the user experience.

[1551] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1552] Step 1:

[1553] The user enters the content they want to generate into the terminal interface and sends a message to the server. The input may include text such as, "I'd like a cute video of my cat. I'm feeling a bit down today." This sends a message to the server expressing the user's request and feelings.

[1554] Step 2:

[1555] The server receives messages sent from the terminal. The received messages are stored in the server's database in text format.

[1556] Input: Received message (text)

[1557] Output: Text saved in the database

[1558] Step 3:

[1559] The server uses an emotion engine to recognize emotions from received messages. The emotion engine analyzes the vocabulary, expressions, and context within the text to identify emotions such as joy, sadness, and anger.

[1560] Input: Saved text

[1561] Data processing: Analyzing emotions using natural language processing techniques.

[1562] Output: Identified emotion (e.g., depressed)

[1563] Step 4:

[1564] The server uses natural language processing (NLP) techniques to analyze the message content and extract the user's request. For example, it might identify keywords such as "cat," "cute," and "video" from the message.

[1565] Input: Saved text

[1566] Data processing: Analyze requirements using a keyword extraction algorithm.

[1567] Output: Extracted keywords (e.g., cat, cute, video)

[1568] Step 5:

[1569] The server selects the optimal generative AI service based on the extracted requests and analyzed emotions. This selection considers factors such as service performance, past performance, and compatibility with the emotions. For example, it might select service A, which can generate videos that uplift the user.

[1570] Input: Extracted keywords, identified emotions

[1571] Data processing: Evaluation and selection of multiple generative AI services.

[1572] Output: Selected generative AI service (e.g., Service A)

[1573] Step 6:

[1574] The server generates request data for the selected generative AI service. This request data includes details of the generated content requested by the user and an analyzed sentiment.

[1575] Input: Extracted keywords, identified sentiment, selected generative AI service

[1576] Data processing: Generating request data

[1577] Output: Generated request data

[1578] Step 7:

[1579] The server sends the generated request data to the selected generation AI service. This transmission is performed using a communication protocol.

[1580] Input: Generated request data

[1581] Output: Request data sent to the AI ​​generation service

[1582] Step 8:

[1583] The AI ​​generation service processes content generation based on the request and returns the generated result (e.g., the generated video) to the server.

[1584] Input: Request data (generation instructions and sentiment information)

[1585] Output: Generated content (e.g., a cute video of a cat)

[1586] Step 9:

[1587] The server receives the generated results and performs post-processing as needed. Post-processing includes adjusting the content based on the emotion recognition results (e.g., adjusting video brightness or selecting music).

[1588] Input: Generated content

[1589] Data processing: Optimization based on emotion recognition results

[1590] Output: Post-processed generated content

[1591] Step 10:

[1592] The server sends the completed generation results to the user's terminal and notifies the user.

[1593] Input: Post-processed generated content

[1594] Output: Generated content sent to the user's terminal

[1595] Step 11:

[1596] Users view and use the generated results (e.g., cute cat videos) on their devices. The videos displayed on the device are optimized to reflect the user's emotions.

[1597] Input: Generated content sent from the server

[1598] Output: Generated content that users view and use (e.g., cute cat videos)

[1599] (Application Example 2)

[1600] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1601] In modern content delivery services, it is difficult for users to automatically and efficiently find the most suitable content based on their emotional state. Furthermore, the lack of a system that allows users to enjoy content that reflects their own emotions can lead to a diminished user experience. Therefore, a new system is needed that considers user emotions and recommends the most suitable content based on those emotions.

[1602] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1603] In this invention, the server includes means for receiving messages, means for analyzing the messages to recognize emotions and extract requests, and means for selecting the optimal generative AI service based on the emotions and requests. This makes it possible to automatically recommend the most suitable content according to the user's emotional state.

[1604] A "means of receiving messages" is an interface for electronically receiving user input and initiating processing.

[1605] "A means of analyzing messages to recognize emotions and extract requests" refers to a function that analyzes received messages using natural language processing technology and extracts the user's emotional state and specific requests from them.

[1606] "Emotions" refer to the mental states of users extracted from their input, including feelings such as joy, sadness, and anger.

[1607] A "request" refers to a specific request or need that a user makes to the system, such as asking for actions like recommending specific content or generating specific information.

[1608] "Means for selecting the optimal generative AI service" refers to algorithms and methods for selecting the most suitable service from among multiple existing generative AI services based on emotions and requests.

[1609] "Means for sending requests to a generation AI service" refers to a means of communication for requesting a selected generation AI service to perform processing according to the user's requirements.

[1610] "Means for receiving generation results from the generation AI service" refers to a function for receiving data when the generation AI service completes processing and sends the results back to the server.

[1611] "Means for returning the generation results to the user" refers to an interface for sending the received generation results to the user's terminal and providing them to the user.

[1612] "Natural language processing technology" refers to a set of techniques that enable computers to understand, interpret, and respond to human language, and is used for text analysis, sentiment recognition, request extraction, and more.

[1613] "Post-processing including emotion-based adjustments" refers to the process of further fine-tuning the generated results received from the generation AI service to match the user's emotions, with the aim of improving the user experience.

[1614] A specific system for carrying out this invention includes the following steps:

[1615] The server receives input messages from the user. Text format is preferred for these messages. A network communication module is used to receive messages entered from user terminals such as smartphones.

[1616] Next, the server analyzes the received message using natural language processing techniques to recognize the user's emotions and extract requests from the message content. This process utilizes natural language processing libraries such as TextBlob. For example, if a user enters "I'm very tired today," the server recognizes the emotion of "tired" from this message and extracts the request "I would like recommendations for content suitable for rest."

[1617] After emotions and requests are extracted, the server selects the most suitable generative AI service based on this information. This selection takes into account past performance and compatibility with the user's emotions. The generative AI service may utilize the latest deep learning models, among others.

[1618] A request is sent to the selected generative AI service, tailored to the user's needs. The request data includes information about the user's emotions. The generative AI service then provides the most suitable generation result based on this request. For example, a streaming music service might provide relaxing music.

[1619] Once the generation AI service returns the generated results, the server performs further emotion-based post-processing as needed. This adjusts the content to better reflect the user's emotions.

[1620] Finally, the generated results are sent to the user's device and the user is notified. The user can then access the generated content through their device. This entire process allows the user to easily obtain content optimized for their own emotions.

[1621] For example, if a user types "I'm very tired today" into their smartphone, the system will recommend a relaxing movie that matches that feeling. This improves the user experience.

[1622] Examples of prompt messages include the following:

[1623] "Please tell me how you're feeling right now: I'm very tired today."

[1624] "I recommend this to you: Guardians of the Galaxy (movie)"

[1625] This allows users to easily find content that suits their emotions, resulting in a highly satisfying experience.

[1626] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1627] Step 1:

[1628] The user uses a terminal to type a message containing emotions and requests. For example, they might type, "I'm very tired today." Input: The user's text message. Output: The message sent from the terminal to the server.

[1629] Step 2:

[1630] The server receives messages sent from the terminal. The received data is stored in text format. Input: Message sent from the terminal. Output: Received message data.

[1631] Step 3:

[1632] The server analyzes received messages using natural language processing techniques to recognize the user's emotions and extract requests. Specifically, it uses libraries such as TextBlob to identify emotions (positive, negative, neutral) and pinpoint the emotion "tired." Input: Received message data. Output: Analyzed emotions and extracted requests.

[1633] Step 4:

[1634] The server selects the optimal generative AI service based on the analyzed emotions and requests. From the available generative AI services, it chooses the one best suited to the user's emotions. Input: Analyzed emotion and request data. Output: Selected generative AI service.

[1635] Step 5:

[1636] The server sends a request to the selected generative AI service. The request data includes the user's sentiment information and specific request details. Input: Selected generative AI service, request data, sentiment data. Output: Request data sent to the generative AI service.

[1637] Step 6:

[1638] The AI ​​generation service processes requests from the server and returns the generated content to the server. For example, it could recommend relaxing movies. Input: Request data from the server. Output: Generated content data.

[1639] Step 7:

[1640] The server receives content data returned from the AI ​​generation service and performs post-processing as needed. It makes emotion-based adjustments and determines the final content. Input: Generated content data. Output: Post-processed final content data.

[1641] Step 8:

[1642] The server sends the post-processed final content data to the user's terminal and notifies them. Input: Final content data. Output: Content data sent to the user's terminal.

[1643] Step 9:

[1644] Users view and use content received through their devices. For example, they might watch a recommended movie. Input: Content data received from the server. Output: Displayed content.

[1645] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1646] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1647] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1648] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1649] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1650] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1651] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1652] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1653] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1654] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1655] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1656] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1657] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1658] 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.

[1659] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1660] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1661] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1662] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1663] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1664] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1665] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[1666] The following is further disclosed regarding the embodiments described above.

[1667] (Claim 1)

[1668] A means of receiving a message,

[1669] A means for analyzing the aforementioned message and extracting the request,

[1670] A means for selecting the optimal generation AI service based on the aforementioned requirements,

[1671] A means for sending a request to the aforementioned generation AI service,

[1672] Means for receiving generation results from the aforementioned generation AI service,

[1673] A means for returning the aforementioned generation result to the user,

[1674] A system that includes this.

[1675] (Claim 2)

[1676] The system according to claim 1, characterized in that natural language processing techniques are used for analyzing the aforementioned message.

[1677] (Claim 3)

[1678] The system according to claim 1, further comprising means for performing post-processing on the generation result.

[1679] "Example 1"

[1680] (Claim 1)

[1681] A means of receiving a message,

[1682] A means for analyzing the aforementioned message and extracting the request,

[1683] A means for selecting the optimal generative artificial intelligence service based on the above requirements,

[1684] Means for sending a request to the aforementioned artificial intelligence service for generation,

[1685] Means for receiving generation results from the aforementioned artificial intelligence generation service,

[1686] Means for performing post-processing on the generated results as needed,

[1687] A means for transmitting the aforementioned generation result to the user terminal and notifying the user,

[1688] A system that includes this.

[1689] (Claim 2)

[1690] The system according to claim 1, characterized in that natural language processing techniques are used for analyzing the aforementioned message.

[1691] (Claim 3)

[1692] The system according to claim 1, further comprising means for performing post-processing on the generation result, such as format conversion or addition of metadata.

[1693] "Application Example 1"

[1694] (Claim 1)

[1695] A means of receiving a message,

[1696] A means for analyzing the aforementioned message and extracting the request,

[1697] A means for selecting the optimal generation AI service based on the aforementioned requirements,

[1698] A means for sending a request to the aforementioned generation AI service,

[1699] Means for receiving generation results from the aforementioned generation AI service,

[1700] A means for returning the aforementioned generation result to the user,

[1701] Means for performing post-processing on the aforementioned generation result,

[1702] Methods for searching for and suggesting products on e-commerce sites,

[1703] A system that includes this.

[1704] (Claim 2)

[1705] The system according to claim 1, characterized in that natural language processing techniques are used for analyzing the aforementioned message.

[1706] (Claim 3)

[1707] The system according to claim 1, further comprising means for performing post-processing on the generated result and formatting it into a specific format.

[1708] "Example 2 of combining an emotion engine"

[1709] (Claim 1)

[1710] A means of receiving a message,

[1711] A means of analyzing the aforementioned message to recognize emotions,

[1712] A means for analyzing the aforementioned message and extracting the request,

[1713] A means for selecting the optimal generative AI service based on the extracted requests and recognized emotions,

[1714] A means for generating and sending request data to the aforementioned AI generation service,

[1715] Means for receiving generation results from the aforementioned generation AI service,

[1716] Means for performing necessary post-processing on the aforementioned generation results,

[1717] A means for returning the aforementioned generation result to the user,

[1718] A system that includes this.

[1719] (Claim 2)

[1720] The system according to claim 1, characterized in that natural language processing techniques are used for analyzing the aforementioned message.

[1721] (Claim 3)

[1722] The system according to claim 1, characterized in that the means for post-processing the generation result includes adjusting the content according to the emotion recognition result.

[1723] "Application example 2 when combining with an emotional engine"

[1724] (Claim 1)

[1725] A means of receiving a message,

[1726] A means for analyzing the aforementioned message to recognize emotions and extract requests,

[1727] A means for selecting the optimal generative AI service based on the aforementioned emotions and requests,

[1728] A means for sending a request to the aforementioned generation AI service,

[1729] Means for receiving generation results from the aforementioned generation AI service,

[1730] A means for returning the aforementioned generation result to the user,

[1731] A system that includes this.

[1732] (Claim 2)

[1733] The system according to claim 1, characterized in that natural language processing techniques are used for analyzing the aforementioned message.

[1734] (Claim 3)

[1735] The system according to claim 1, further comprising means for post-processing the generation result, including emotion-based adjustments. [Explanation of Symbols]

[1736] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of receiving a message, A means for analyzing the aforementioned message and extracting the request, A means for selecting the optimal generation AI service based on the aforementioned requirements, A means for sending a request to the aforementioned generation AI service, Means for receiving generation results from the aforementioned generation AI service, A means for returning the aforementioned generation result to the user, A system that includes this.

2. The system according to claim 1, characterized in that natural language processing technology is used for analyzing the aforementioned message.

3. The system according to claim 1, further comprising means for performing post-processing on the generation result.

Images