system

Abstract

Provide a system. [Solution] A means for inputting a topic from a user's terminal and transmitting the topic to a server; A means for storing the received topics in a database; A method for sharing saved topics with multiple AIs and generating answers based on them; means for transmitting the generated answer to the user's terminal; A means for a user to input points for each answer from a terminal and transmit the evaluation to a server; a means for the server to aggregate the received ratings and display the results on the user's terminal; A system including:

Description

[Technical Field]

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

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

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

[0004] Conventional Ogiri systems and creative tasks (such as composing music, painting, and haiku) require the participation of many people in order for users to enjoy the game, and collecting the opinions of all participants takes time. Furthermore, since a high level of creativity is required to obtain original ideas and answers, it is difficult for beginners and inexperienced users. Furthermore, the evaluation process is subjective, making it difficult to use a unified standard for evaluation. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides a means for a user to input a theme from a terminal and send the theme to a server. The server stores the received theme in a database and shares it with multiple artificial intelligences, which then use a program to generate answers. The generated answers are then sent to the user's terminal, and the user inputs evaluation points for each answer. These evaluation points are sent to the server, which then aggregates the evaluations and displays the results on the user's terminal. Furthermore, the system is provided with a means for supporting other creative tasks, such as composing music, painting, and haiku poetry. Evaluation results can also be stored in a database for later reference, enabling transparent and objective evaluation.

[0006] "User" refers to a person who uses this system to input topics and evaluate the answers and works generated by the AI.

[0007] "Terminal" refers to an electronic device operated by a user, such as a computer, smartphone, or tablet.

[0008] A "topic" refers to a question or theme that a user enters and that the AI ​​uses to generate an answer or work accordingly.

[0009] A "server" refers to a computer system that receives the topics sent from the user's device, stores them in a database, and sends them to the AI.

[0010] "Database" refers to an electronic data storage system for organizing and storing data such as questions, answers, and evaluation results.

[0011] "AI (artificial intelligence)" refers to algorithms or programs that automatically generate answers or works based on input topics.

[0012] "Answer" refers to the response or suggestion generated by the AI ​​based on the user's topic.

[0013] "Evaluation points" refer to the score that users give to answers or works generated by AI.

[0014] "Aggregation" refers to the process by which the server calculates the reputation points submitted by users and derives an overall result.

[0015] "Works" refer to deliverables generated by AI based on creative tasks such as composing music, painting, or writing haiku.

[0016] "Transparency" refers to a state in which the evaluation and creation processes are clear, fair, and objective.

[0017] "Objectivity" refers to a state in which evaluations and results are not influenced by individual subjectivity but are evaluated according to uniform standards. [Brief explanation of the drawings]

[0018] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9]1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0019] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0021] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0022] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0023] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0024] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0026] [First embodiment]

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

[0028] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0029] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0030] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0031] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0032] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0035] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0036] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0037] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0038] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0039] This invention provides a system in which a user inputs a theme from a terminal, an artificial intelligence generates answers and works based on the theme, and the user then evaluates them. Below, the program processing of the system of the present invention is explained in natural language, with specific examples.

[0040] Program processing overview

[0041] Register a topic

[0042] 1. The user enters a topic from the device.

[0043] For example, a user may input the topic "Come up with a name for a new sport."

[0044] 2. The device sends the entered topic to the server.

[0045] 3. The server stores the received topic in a database.

[0046] Generate answers

[0047] 1. The server shares the saved topics with multiple AIs.

[0048] For example, the server sends a topic to different AI engines (such as natural language generation AI and image generation AI).

[0049] 2. Each AI generates an answer based on the topic.

[0050] An example would be a natural language generation AI generating the answer "chameleon rugby."

[0051] The image generation AI generates paintings based on the theme of "the sea."

[0052] 3. The server collects the answers and creations from each AI and sends them to the user's device.

[0053] Evaluating answers

[0054] 1. The user enters evaluation points for each AI's answers and works from their device.

[0055] For example, a user may give "chameleon rugby" an 8-point rating and "bound basket" a 6-point rating.

[0056] 2. The device sends the user's evaluation points to the server.

[0057] 3. The server aggregates the received ratings and stores them in a database.

[0058] 4. The server displays the evaluation results on the user's device.

[0059] For example, display the result "AI 1's 'Chameleon Rugby' wins."

[0060] Responding to other creative tasks

[0061] This system can be applied not only to Ogiri but also to other creative tasks (composing music, painting, haiku, etc.). Specific examples are shown below.

[0062] 1. Composition Examples

[0063] The user inputs the theme "music that evokes a summer landscape" into the terminal.

[0064] The server sends the theme to the composition AI.

[0065] The composition AI generates music files and sends them to the server.

[0066] The server transmits the generated music file to the user's terminal.

[0067] The user rates the generated music and transmits the rating points from the terminal to the server.

[0068] The server compiles the evaluation results and displays them on the user's device.

[0069] 2. Examples of paintings

[0070] The user inputs a topic on the theme of "sea at sunset" into the terminal.

[0071] The server sends the theme to the image generation AI.

[0072] The image generation AI generates a painting based on the image and sends it to the server.

[0073] The server transmits the generated painting to the user's terminal.

[0074] The user evaluates the generated painting and transmits the evaluation points from the terminal to the server.

[0075] The server compiles the evaluation results and displays them on the user's device.

[0076] In this way, users can evaluate various creative tasks with the help of AI, and enjoy the creative process. The system stores the evaluation results in a database and makes them available for future reference, enabling transparent and objective evaluation.

[0077] The processing flow will be explained below.

[0078] Specific process flow for generating and evaluating answers to Ogiri topics

[0079] Register a topic

[0080] Step 1:

[0081] The user inputs a topic from the terminal.

[0082] Example: A user enters the topic "Think of a name for a new sport."

[0083] Step 2:

[0084] The device sends the input topic to the server.

[0085] The device sends the topic to the server using an HTTP request.

[0086] Step 3:

[0087] The server stores the topics in a database.

[0088] The server saves the topic in the database using an INSERT query.

[0089] Generate answers

[0090] Step 4:

[0091] The server shares the saved topics with multiple AIs.

[0092] The server sends a task to each AI using APIs and modifiers. For example, it sends a request to the ChatGPT (registered trademark) API.

[0093] Step 5:

[0094] AI generates answers based on the topic.

[0095] Each AI uses its own natural language processing algorithm to generate answers. For example, ChatGPT generates the answer "Chameleon Rugby."

[0096] Step 6:

[0097] The server collects the responses from each AI.

[0098] The server processes the API responses of each AI and stores them in a database.

[0099] Step 7:

[0100] The server sends the response to the user's terminal.

[0101] The server sends a list of answers to the user's terminal.

[0102] Evaluating answers

[0103] Step 8:

[0104] The user inputs evaluation points for each AI's answer from the terminal.

[0105] Users enter points from 1 to 10 for each answer using a slider or input box.

[0106] Step 9:

[0107] The terminal transmits the user's rating to the server.

[0108] The device sends the evaluation points to the server in JSON format or similar.

[0109] Step 10:

[0110] The server aggregates the ratings and stores them in a database.

[0111] The server tallies the evaluation points for each answer and stores them in a database.

[0112] Step 11:

[0113] The server displays the final result on the user's terminal.

[0114] The server generates the results in HTML or JSON format and sends them to the user's device. Example: The server displays the result "AI 1's 'Chameleon Rugby' wins."

[0115] Application to other creative tasks (composing music, painting, haiku, etc.)

[0116] Specific examples of composition

[0117] Step 1:

[0118] The user inputs the theme "music that evokes a summer landscape" into the terminal.

[0119] Step 2:

[0120] The device sends the input topic to the server.

[0121] Step 3:

[0122] The server stores the received questions in a database.

[0123] Step 4:

[0124] The server sends the theme to the composition AI.

[0125] Step 5:

[0126] The AI ​​generates music files and sends them to the server.

[0127] Step 6:

[0128] The server stores the generated music files in a database.

[0129] Step 7:

[0130] The server sends the music files to the user's device.

[0131] Step 8:

[0132] The user rates the generated music and inputs rating points.

[0133] Step 9:

[0134] The terminal transmits the evaluation points to the server.

[0135] Step 10:

[0136] The server compiles the evaluation results and stores them in a database.

[0137] Step 11:

[0138] The server displays the final result on the user's device. Example: The server displays the result "Music that evokes a summer landscape received a score of 9."

[0139] Examples of paintings

[0140] Step 1:

[0141] The user inputs a topic on the theme of "sea at sunset" into the terminal.

[0142] Step 2:

[0143] The device sends the input topic to the server.

[0144] Step 3:

[0145] The server stores the received questions in a database.

[0146] Step 4:

[0147] The server sends the theme to the image generation AI.

[0148] Step 5:

[0149] The AI ​​generates a painting based on the image and sends it to the server.

[0150] Step 6:

[0151] The server stores the generated painting in a database.

[0152] Step 7:

[0153] The server sends the picture file to the user's terminal.

[0154] Step 8:

[0155] The user evaluates the generated painting and inputs evaluation points.

[0156] Step 9:

[0157] The terminal transmits the evaluation points to the server.

[0158] Step 10:

[0159] The server compiles the evaluation results and stores them in a database.

[0160] Step 11:

[0161] The server displays the final result on the user's terminal. Example: The server displays the result "The painting of the sea at sunset received 8 points."

[0162] Through the above process, a system is realized that allows users to use AI in various creative tasks and receive objective evaluations in a fun way.

[0163] Example 1

[0164] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0165] Existing AI systems generate creative answers and works based on user-entered topics, and the process of evaluating them is complex and difficult to carry out efficiently. Furthermore, there is no mechanism in place for reviewing the evaluation results later, making it difficult to conduct transparent and objective evaluations.

[0166] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0167] In this invention, the server includes means for inputting a theme from a user's communication device and transmitting the theme to the server device, means for storing the theme received by the server device in a storage device, means for sharing the stored theme with multiple information processing devices and generating answers based on it, means for transmitting the generated answers to the user's communication device, means for the user to input evaluation points for each answer from the communication device and transmit the evaluations to the server device, and means for the server device to tally up the evaluations received and display the results on the user's communication device. This enables users to efficiently input themes, generate creative answers and works based on them, and refer to the evaluation results transparently and objectively.

[0168] A "user" is an entity that uses the system to input a topic and evaluate the generated answers and works.

[0169] A "communication device" is a terminal used by a user, such as a computer or smartphone, that can connect to the Internet.

[0170] "Server device" refers to a centralized computer system that receives topics and ratings from users and processes that data.

[0171] "Storage device" refers to hardware that has a database or other data storage function connected to a server device.

[0172] "Information processing device" refers to a system that includes artificial intelligence to generate creative answers and works based on a given theme.

[0173] A "topic" refers to a prompt that a user enters and the AI ​​generates a creative answer or piece of work based on it.

[0174] "Evaluation points" refer to the evaluation value entered by the user for the generated answer or work.

[0175] "Generated answer" refers to a creative output generated by an information processing device (AI) based on input (topic) from a user.

[0176] "Evaluation results" refers to information that indicates which answers or works are superior, calculated by tallying up the evaluation points entered by users.

[0177] "Transparency and objectivity" refers to the characteristics of managing and displaying user-entered ratings and generated results fairly and clearly throughout the system.

[0178] The present invention relates to a system in which a user inputs a theme, an artificial intelligence generates creative answers and works based on the theme, and the user evaluates them. Hereinafter, embodiments of the present invention will be described in detail.

[0179] Enter and save the topic

[0180] A user uses a communication device (e.g., a computer or a smartphone) to access a dedicated interface. This interface has a text box where the user can input a topic. For example, the topic could be "Please think of a name for a new sport." The communication device then transmits the topic to a server device. The server device analyzes the received topic and stores it in a storage device (e.g., a database).

[0181] Generate answers

[0182] The server device retrieves the theme stored in the storage device periodically or based on a trigger event. Then, the server device transmits the theme to multiple information processing devices (artificial intelligence models). For example, the server device transmits the theme to a natural language generation AI (e.g., GPT-3 (registered trademark)) or an image generation AI (e.g., DALL-E). These information processing devices generate answers or works based on the theme.

[0183] An example of a prompt for a natural language generation AI is "Come up with a name for a new sport."

[0184] An example of a prompt for the image generation AI is "Please draw a picture of the sea at sunset."

[0185] Collecting and submitting responses

[0186] The server device receives the responses generated by each information processing device, aggregates them, and then transmits the aggregated responses to the user's communication device, where the user can view the responses through the interface of the communication device.

[0187] Evaluating answers

[0188] The user can use the communication device to input evaluation points for each answer. For example, the user inputs 8 points for the answer "chameleon rugby" and 6 points for the answer "bound basket." The evaluation points are transmitted from the communication device to the server device.

[0189] Calculation and display of evaluation results

[0190] The server device stores the received evaluation points in a storage device and tally up the evaluation results. The tally up results are displayed on the communication device in a format that is easy for the user to understand. For example, the result displayed may be "AI 1's 'Chameleon Rugby' wins."

[0191] Application to other creative tasks

[0192] This system can be applied not only to Ogiri but also to other creative tasks such as composing music, painting, and generating text.

[0193] Composition examples

[0194] The user inputs "music that evokes a summer landscape" as a theme. The server device sends this theme to the composition AI, which then generates a music file. The generated music file is then sent to the user's communication device, and the user evaluates the music.

[0195] Painting examples

[0196] The user inputs a theme such as "sea at sunset." The server device sends the theme to the image generation AI, which then generates a painting. The generated painting is then sent to the user's communication device, and the user evaluates the painting.

[0197] In this way, users can evaluate various creative tasks with the help of artificial intelligence, and enjoy the creative process. The system also stores the evaluation results in a storage device and makes them available for later reference, enabling transparent and objective evaluation.

[0198] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0199] Step 1:

[0200] The user enters a topic

[0201] The user accesses a dedicated interface on the communication device and inputs a topic into the text box. As an example, consider the topic "Please think of a name for a new sport." When the user clicks the "Send" button, the device accepts this input data.

[0202] Input: User-entered question

[0203] Output: A data packet containing the question

[0204] Step 2:

[0205] The device sends the topic to the server

[0206] The device sends the topic entered by the user to the server as an HTTP request (POST request). The request includes the topic text and the user ID.

[0207] Input: Data packet containing the question

[0208] Output: HTTP request to the server

[0209] Step 3:

[0210] The server saves the topic in a database

[0211] The server parses the received HTTP request, extracts the question text and the user ID, and stores this information in a database using an SQL query.

[0212] Input: HTTP request to the server

[0213] Output: Insert operation into the database

[0214] Step 4:

[0215] The server sends the theme to each information processing device.

[0216] The server retrieves the topics stored in the database periodically or upon trigger events and sends them as prompts to multiple information processing devices (artificial intelligence models). For example, it sends topics to a natural language generation AI and an image generation AI.

[0217] Input: Questions stored in the database

[0218] Output: Prompt to each information processing device

[0219] Step 5:

[0220] Each information processing device generates an answer

[0221] Each AI generates an answer based on the prompt. For example, a natural language generation AI might generate the answer "chameleon rugby," while an image generation AI might generate an image with an "ocean" theme.

[0222] Input: Prompt to each information processing device

[0223] Output: Generated answers and works

[0224] Step 6:

[0225] The server collects the answers and sends them to the user's device.

[0226] The server receives the responses from the information processing devices, compiles them, and sends them to the user's terminal, usually as an HTTP response.

[0227] Input: Generated answers and works

[0228] Output: HTTP response to the user's device

[0229] Step 7:

[0230] Users rate the answers

[0231] The user uses the interface on the communication device to input evaluation points for each answer, for example, a user might input 8 points for "chameleon rugby" and 6 points for "bound basket."

[0232] Input: Generated answers and works

[0233] Output: Rating points

[0234] Step 8:

[0235] The device sends the rating to the server

[0236] The terminal receives the evaluation points from the user and sends them to the server as an HTTP request (POST request). The request includes the evaluation points for each answer and the user ID.

[0237] Input: Rating points

[0238] Output: HTTP request to the server

[0239] Step 9:

[0240] The server aggregates the ratings and stores them in a database

[0241] The server parses the received reputation points and stores them in a database, using an SQL query to store the reputation points for each answer.

[0242] Input: HTTP request to the server

[0243] Output: Insert operation into the database

[0244] Step 10:

[0245] The server displays the evaluation results on the user's device.

[0246] The server aggregates the evaluation results and sends them as an HTTP response to the user's device for display. For example, it sends the result "AI 1's 'Chameleon Rugby' wins."

[0247] Input: Reputation points stored in the database

[0248] Output: HTTP response to the user's device

[0249] (Application example 1)

[0250] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0251] There is a need to use artificial intelligence to improve the quality of content generated based on user-entered topics, and to efficiently evaluate that content and store it in a reusable format. Conventional systems have issues with making effective use of user evaluation results and being unable to handle a wide range of creative tasks.

[0252] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0253] In this invention, the server includes means for inputting a theme from a user's information processing device and transmitting the theme to the data processing device, means for storing the theme received by the data processing device in a storage device, means for sharing the stored theme with multiple intelligent processing devices and generating answers based on the theme, means for transmitting the generated answers to the user's information processing device, means for the user to input points for each answer from the information processing device and transmit the evaluation to the data processing device, means for aggregating the received evaluations by the data processing device and displaying the results on the user's information processing device, means for storing the generated content together with the evaluation points in a database so that the data processing device can later refer to it, means for the intelligent processing device to generate content such as text, images, music, and video based on the theme input by the user, means for the user to evaluate the generated content and transmit the evaluation points from the information processing device to the data processing device, and means for the data processing device to aggregate the evaluation results and display them on the user's information processing device. This makes it possible to effectively utilize the user's evaluation results, respond to a wide range of creative tasks, and generate and evaluate high-quality content.

[0254] An "information processing device" is a device that has the function of processing, transmitting, and receiving data input by a user.

[0255] A "data processing device" is a device that receives data sent from a user and stores and aggregates the data.

[0256] A "storage device" is a device that records data and keeps it accessible when needed.

[0257] An "intelligent processing device" is a device that includes artificial intelligence to generate answers and content based on a given topic.

[0258] "Generated content" refers to creative output such as text, images, music, and video generated by an intelligent processing device based on a theme entered by a user.

[0259] "Evaluation points" are numerical values ​​of evaluations given to generated content by users.

[0260] A "database" is a system that stores data in an organized manner and manages it so that necessary information can be retrieved efficiently.

[0261] The term "topic" refers to a sentence or command that indicates an instruction or request from a user regarding the content that the user wants the intelligent processing device to generate.

[0262] This invention is a system in which a user inputs a theme from an information processing device, an intelligent processing device is used to generate creative content based on the theme, and the generated content is evaluated. The details of this system are described below.

[0263] System Configuration

[0264] The system mainly consists of the following components:

[0265] User's information processing device (smartphone, tablet, etc.)

[0266] Data processing device (cloud server, etc.)

[0267] Intelligent Processing Units (devices containing generative AI models)

[0268] Storage devices (databases, etc.)

[0269] The specific hardware and software used

[0270] Hardware:

[0271] Cloud server (e.g., AWS (registered trademark) EC2 instance)

[0272] Smartphones (e.g. iOS / ANDROID devices)

[0273] software:

[0274] Natural language processing AI (e.g. GPT-3)

[0275] Image generation AI (e.g. DALL-E)

[0276] Music generation AI (e.g. Amper Music)

[0277] Database management system (e.g., MySQL®)

[0278] Program processing flow

[0279] 1. Enter your topic and submit

[0280] A user inputs a topic using an information processing device. The topic is written in natural language.

[0281] Example: Enter the subject as "Draw a cityscape of the future."

[0282] 2. Receiving and saving the topic

[0283] The data processing device receives the theme sent by the user and stores it in a storage device.

[0284] 3. Sharing topics and creating content

[0285] The theme stored in the storage device is shared with multiple intelligent processing devices, and each intelligent processing device generates content based on the theme.

[0286] Examples: Natural language processing AI generates text, image generation AI generates images, and music generation AI generates music.

[0287] Example prompt: "Create an image of a futuristic city landscape with flying cars and skyscrapers."

[0288] 4. Submitting and Displaying Content

[0289] The content generated by the intelligent processing device is transmitted to the data processing device and distributed to the user's information processing device.

[0290] 5. Content Rating

[0291] A user gives evaluation points to content generated using an information processing device, and the evaluation points are transmitted to the data processing device.

[0292] 6. Calculation and display of evaluation results

[0293] The data processing device tallies the received evaluation points and displays the results on the user's information processing device.

[0294] Adding specific examples

[0295] A user inputs a theme, "Please create music that evokes the image of a summer landscape," into an information processing device.

[0296] The data processing device sends this theme to the music generation AI, and the generated music is stored in a storage device and distributed to the user's information processing device.

[0297] The user rates the generated music and the rating points are transmitted to the data processing device.

[0298] The data processing device compiles the evaluation results, stores them in a storage device for future reference, and notifies the user.

[0299] This system allows users to generate and evaluate high-quality content based on a topic they input.

[0300] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0301] Step 1:

[0302] A user inputs a topic using an information processing device and sends the topic to the server. The topic is input using natural language, specifically a prompt such as "Please draw a picture of a future cityscape." This input data is sent to the server.

[0303] Step 2:

[0304] The server stores the received topic in a database (storage device). In this process, the topic data sent by the user is received and stored in the appropriate table in the database.

[0305] Step 3:

[0306] The server shares the topics stored in the storage device with multiple intelligent processing devices. Specifically, it sends the stored topics to different intelligent processing devices, such as natural language processing AI, image generation AI, and music generation AI. The server formats the topics so that each intelligent processing device can generate appropriate content.

[0307] Step 4:

[0308] Each intelligent processing device generates content based on a given theme. For example, a natural language processing AI generates sentences, an image generation AI generates images, and a music generation AI generates music. For the prompt "Please draw a futuristic cityscape," the image generation AI processes it as "Create an image of a futuristic city landscape with flying cars and skyscrapers."

[0309] Step 5:

[0310] The generated content is sent from each intelligent processing device to a server, which receives the generated content data and sends it to the user's information processing device, i.e., collects the generated text, images, music, etc. and provides them to the user.

[0311] Step 6:

[0312] The user inputs evaluation points for the content generated by the information processing device. For example, the user assigns evaluation points such as "9 points" to the generated image. This evaluation point data is sent to the server.

[0313] Step 7:

[0314] The server aggregates the received evaluation points. Specifically, it aggregates the evaluation points sent by multiple users and generates statistical data such as the average score and the highest score.

[0315] Step 8:

[0316] The results of the counting are sent from the server to the user's information processing device and displayed to the user. Specifically, the results are displayed in a format such as "The average rating for this content is 8.5 points."

[0317] Step 9:

[0318] The generated content and the evaluation results are stored in a database by the server. For future reference, the generated content along with the evaluation points are stored in a storage device and can be accessed by users or other processing devices.

[0319] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0320] This invention provides a system in which a user inputs a theme from a terminal, an artificial intelligence generates answers and works based on that theme, and the user evaluates them, in addition to a system that combines an emotion engine that recognizes the user's emotions. Below, the program processing of the system of the present invention will be explained in natural language, with concrete examples.

[0321] Program processing overview

[0322] Register a topic

[0323] 1. The user enters a topic from the device.

[0324] For example, a user may input the topic "Come up with a name for a new sport."

[0325] 2. The device sends the entered topic to the server.

[0326] 3. The server stores the received questions in a database.

[0327] Generate answers

[0328] 1. The server shares the saved topics with multiple AIs.

[0329] The server sends a task to each AI using APIs and modifiers. For example, it sends a request to the ChatGPT API.

[0330] 2. Each AI generates an answer based on the topic.

[0331] Each AI uses its own natural language processing algorithm to generate answers. For example, ChatGPT generates the answer "Chameleon Rugby."

[0332] 3. The server collects the answers from each AI.

[0333] The server processes the API responses of each AI and stores them in a database.

[0334] 4. The server sends the answer to the user's device.

[0335] The server sends a list of answers to the user's terminal.

[0336] Evaluating answers

[0337] 1. The user enters evaluation points for each AI's answers and works from their device.

[0338] For example, a user gives "chameleon rugby" an 8-point rating and "bound basket" a 6-point rating.

[0339] 2. The device sends the user's evaluation points to the server.

[0340] 3. The server aggregates the received ratings and stores them in a database.

[0341] 4. The server displays the evaluation results on the user's device.

[0342] For example, the server might display the result "AI 1's 'Chameleon Rugby' wins."

[0343] Applying the Emotion Engine

[0344] The system incorporates an emotion engine that recognizes the user's emotions and provides appropriate feedback and adjustments based on those emotions.

[0345] 1. When a user enters a topic on their device, the emotion engine collects emotional data from the user's facial expressions, voice, and text.

[0346] Example: When a user types "Think of a name for a new sport," facial expression and voice data are captured from the camera and microphone.

[0347] 2. The emotion engine analyzes the emotion data and recognizes the user's current emotional state.

[0348] Example: The emotion engine detects emotions such as "enjoyed" or "troubled" from the user's facial expressions and voice.

[0349] 3. The server filters the questions and generated answers based on data from the emotion engine.

[0350] Example: If a user is having trouble, prioritize displaying questions with low difficulty and simple answers.

[0351] 4. The server influences the user's evaluation points with the emotional data.

[0352] Example: If a user is having a lot of fun, the evaluation points are adjusted to be positive.

[0353] 5. The server stores the evaluation results, including emotional data, in a database so that they can be referenced later.

[0354] Example: Recording a user's emotional state so that the relationship between that data and rating points can be analyzed later.

[0355] Specific examples

[0356] Ogiri using an emotional engine

[0357] 1. The user enters the topic, "Look at a picture of a cat and say one thing."

[0358] 2. The emotion engine detects the user's "smile."

[0359] 3. The server uses the emotional data to prioritize and display more humorous answers.

[0360] 4. The AI-generated answer, "This cat is making its modeling debut!" will be displayed.

[0361] 5. If the user gives it a high rating, it will be stored in the database along with the emotional data.

[0362] Composing with an Emotion Engine

[0363] 1. The user enters the theme "a song that evokes a gentle landscape."

[0364] 2. The emotion engine detects the user's "relaxed" state.

[0365] 3. The composition AI will then generate a relaxing, calming song based on that.

[0366] 4. The server sends the generated song to the user's device.

[0367] 5. The user rates the generated song highly, and the emotional data is saved as a rating.

[0368] In this way, by effectively utilizing the user's emotional data, a system can be realized that can provide a more personalized experience.

[0369] The processing flow will be explained below.

[0370] Specific processing flow of the invention that combines the emotion engine

[0371] Register a topic

[0372] Step 1:

[0373] The user inputs a topic from the terminal.

[0374] Example: A user enters the topic "Think of a name for a new sport."

[0375] Step 2:

[0376] The device sends the input topic to the server.

[0377] The device sends the topic to the server using an HTTP request.

[0378] Step 3:

[0379] The server stores the topics in a database.

[0380] The server saves the topic in the database using an INSERT query.

[0381] Emotion recognition

[0382] Step 4:

[0383] The terminal acquires the user's emotion data.

[0384] The device's camera and microphone are used to collect the user's facial expressions and voice data.

[0385] Step 5:

[0386] The terminal transmits emotion data to the emotion engine.

[0387] The device transmits emotion data to the emotion engine in real time.

[0388] Step 6:

[0389] The emotion engine analyzes the emotion data and recognizes the user's emotional state.

[0390] Example: An emotion engine detects emotions such as "enjoyed" or "troubled."

[0391] Generate answers

[0392] Step 7:

[0393] The server shares the saved topics with multiple AIs.

[0394] The server sends a task to each AI using APIs and modifiers. For example, it sends a request to the ChatGPT API.

[0395] Step 8:

[0396] AI generates answers based on the topic.

[0397] Each AI uses its own natural language processing algorithm to generate answers. For example, ChatGPT generates the answer "Chameleon Rugby."

[0398] Step 9:

[0399] The server collects the responses from each AI.

[0400] The server processes the API responses of each AI and stores them in a database.

[0401] Step 10:

[0402] The server filters the answers and works based on data from the emotion engine.

[0403] Example: If a user is having trouble, prioritize displaying questions with low difficulty and simple answers.

[0404] Step 11:

[0405] The server sends the filtered response to the user's terminal.

[0406] The server sends a list of answers to the user's terminal.

[0407] Evaluating answers

[0408] Step 12:

[0409] The user inputs evaluation points for each AI's answers and works from the device.

[0410] Users enter points from 1 to 10 for each answer using a slider or input box.

[0411] Step 13:

[0412] The terminal transmits the evaluation points to the server.

[0413] The device sends the evaluation points to the server in JSON format or similar.

[0414] Step 14:

[0415] The server aggregates the received ratings and adjusts points as necessary based on emotional data.

[0416] Example: If a user is having a lot of fun, the evaluation points are adjusted to be positive.

[0417] Step 15:

[0418] The server stores the evaluation results in a database.

[0419] The server stores the evaluation points and emotion data for each answer in a database.

[0420] Step 16:

[0421] The server displays the final result on the user's terminal.

[0422] The server generates the results in HTML or JSON format and sends them to the user's device. Example: The server displays the result "AI 1's 'Chameleon Rugby' wins."

[0423] Specific examples

[0424] Ogiri using an emotional engine

[0425] Step 1:

[0426] The user inputs the topic "Say one thing when you look at a picture of a cat."

[0427] Step 2:

[0428] The device sends the input topic to the server.

[0429] Step 3:

[0430] The server stores the topics in a database.

[0431] Step 4:

[0432] The terminal acquires the user's facial expression data using a camera.

[0433] Step 5:

[0434] The device sends the facial expression data to the emotion engine.

[0435] Step 6:

[0436] The emotion engine analyzes the transmitted data and detects the user's "smile."

[0437] Step 7:

[0438] The server sends the topic to multiple AIs, which generate answers.

[0439] Step 8:

[0440] The AI ​​generates the answer "This cat is making its modeling debut!" and sends it to the server.

[0441] Step 9:

[0442] The server collects the responses and filters them based on the sentiment data.

[0443] Step 10:

[0444] The server sends the filtered response to the user's terminal.

[0445] Step 11:

[0446] The user gives a high rating of 8 points to the answer "This cat is making her modeling debut!"

[0447] Step 12:

[0448] The terminal transmits the evaluation points to the server.

[0449] Step 13:

[0450] The server makes corrections based on the evaluation points and emotion data and stores the results in a database.

[0451] Step 14:

[0452] The server displays the final result, "AI 1's 'This cat is a model!' wins" on the user's device.

[0453] In this way, by effectively utilizing the user's emotional data, a system can be realized that can provide a more personalized experience.

[0454] Example 2

[0455] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0456] In conventional creative tasks, systems existed that generated and evaluated answers to user-provided questions, but they lacked a mechanism to consider the user's emotional state. As a result, users were often dissatisfied with answers or questions that did not match their emotions. Furthermore, because the evaluation results did not incorporate emotional data, the accuracy of the evaluation and the improvement of the user experience were not fully realized.

[0457] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0458] In this invention, the server includes means including an emotion engine that collects user emotion data, means for filtering questions and answers based on the emotion data, and means for correcting evaluation points using the emotion data, thereby making it possible to provide questions and answers that suit the user's emotions and to reflect the emotion data in the evaluation results.

[0459] A "user" is a person who uses the system to input questions and evaluate generated answers.

[0460] A "terminal" is a device operated by a user, which provides an interface for input and evaluation.

[0461] The "server" is a computer system that receives questions, stores them, shares them with the AI, collects answers, and compiles evaluations.

[0462] A "topic" is a question or theme that a user enters through a device, and is the basis for the AI ​​to generate an answer.

[0463] The "database" is a system for storing the questions received by the server, the answers generated, and the user's evaluation points.

[0464] "Artificial intelligence (AI)" is a program that generates answers based on questions provided by users.

[0465] An "answer" is an output result generated by the artificial intelligence based on a topic provided by the user.

[0466] "Evaluation points" are numerical values ​​that are given to a user to evaluate a generated answer.

[0467] An "emotion engine" is a system that recognizes a user's emotional state and collects and analyzes that data.

[0468] "Emotional Data" is information about a user's emotional state that is collected and analyzed by the emotion engine.

[0469] "Filtering" is a process of adjusting the priority of the questions and generated answers based on emotional data.

[0470] "Correction of evaluation points" is a process of modifying evaluation points based on the user's emotion data.

[0471] This invention uses artificial intelligence to generate answers based on topics entered by users, and improves the performance of the entire system based on the user's evaluations and emotional data. This system is realized by combining users, terminals, servers, an emotional engine, and artificial intelligence (AI).

[0472] First, the user inputs a topic using a device. This device refers to hardware (smartphone, tablet, PC, etc.) that runs software such as a web browser or mobile app. For example, the user might input a topic in text format, such as "Please think of a name for a new sport." This input data is sent from the device to the server. At this time, the device converts the topic into JSON format and sends it to the server via an HTTP POST request. This process transmits the user's topic to the server.

[0473] The server stores the received questions in a database (e.g., MongoDB). The stored questions are shared with various artificial intelligences (generative AI models). The server sends the questions to each AI's API, and each AI generates an answer using its own natural language processing algorithm. For example, if the server sends a request to ChatGPT's API saying, "Please think of a name for a new sport," ChatGPT generates the answer "Chameleon Rugby."

[0474] Next, the server collects the answers from each AI and sends them to the user's device. These answers are displayed on the user's device, and the user enters evaluation points for each answer. The evaluation points are again sent from the device to the server, which tallies them and stores the evaluation results in a database. The tallied results are then displayed on the user's device. For example, if a user rates "Chameleon Rugby" as 8 points and "Bounce Basket" as 6 points, the server tallies these and displays a result such as "AI 1's 'Chameleon Rugby' wins."

[0475] Furthermore, the system incorporates an emotion engine. When a user inputs a topic from their device, the emotion engine uses a camera and microphone to collect facial and voice data and analyze the user's emotional state. From the analysis results, the engine recognizes emotions such as "enjoying" or "struggling," and filters the topics and generated answers based on this emotional data. For example, if the server recognizes that the user is struggling, it will prioritize displaying topics with low difficulty and simple answers. Furthermore, evaluation points are also adjusted based on the user's emotional state. As a result, the system stores the user's evaluation points and emotional data in a database for later analysis.

[0476] For example, if a user inputs the topic "Say something when you look at a photo of a cat," and the emotion engine detects a "smile," the server will prioritize humorous responses, such as "This cat is ready to make its debut as a model!" If the user gives a high rating, the rating and emotion data are saved in the database.

[0477] In addition, if a user inputs a theme of "a song that evokes a gentle landscape" and the emotion engine detects a "relaxed" state, the composition AI will generate a relaxing, calm song, which will be sent to the user's device. The user can then rate the generated song highly, and their emotional data will be saved as a rating. The system is similarly configured to handle other creative tasks, such as composing music, painting, and haiku poetry.

[0478] In this way, the present invention is a system that can effectively utilize a user's emotional data to provide a more personalized experience.

[0479] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0480] Step 1:

[0481] The user inputs a topic from the terminal.

[0482] Input: A user types "Think of a new sport name" into an input field in a web browser or app.

[0483] Data processing: The terminal converts the user input into JSON format.

[0484] Output: The generated JSON data.

[0485] Specific operation: The user presses the "Submit" button to send the topic to the server.

[0486] Step 2:

[0487] The device sends the input topic to the server.

[0488] Input: JSON data generated on the terminal.

[0489] Data operation: Send an HTTP POST request to the server.

[0490] Output: The topic data sent to the server.

[0491] Specific operation: The device sends an HTTP POST request to the " / submit_topic" endpoint.

[0492] Step 3:

[0493] The server stores the received questions in a database.

[0494] Input: The question data received by the server.

[0495] Data processing: Insert the received data into the database.

[0496] Output: The questions stored in the database.

[0497] Specific operation: The server stores the subject data in a NoSQL database such as MongoDB.

[0498] Step 4:

[0499] The server shares the saved topics with each AI's API.

[0500] Input: A question stored in the database.

[0501] Data processing: Generate requests corresponding to each AI's API.

[0502] Output: The requests sent to each AI.

[0503] Specific operation: The server sends a request to an API endpoint such as ChatGPT.

[0504] Step 5:

[0505] Each AI receives a question from the server and generates an answer.

[0506] Input: The topic requests received by each AI.

[0507] Data Computing: Uses natural language processing algorithms to generate answers.

[0508] Output: The generated answer.

[0509] Specific operation: AI such as ChatGPT generates answers such as "Chameleon Rugby."

[0510] Step 6:

[0511] The server collects the responses from each AI and sends them to the user's device.

[0512] Input: The answers generated by each AI.

[0513] Data processing: Compile the answers into a list.

[0514] Output: The answer list sent to the user's device.

[0515] Specific operation: The server converts the answer list into JSON format and sends it to the specified endpoint on the user's device.

[0516] Step 7:

[0517] The user inputs evaluation points for each AI's answer from the terminal.

[0518] Input: Rating points entered by the user.

[0519] Data processing: Convert the evaluation points into JSON format.

[0520] Output: JSON data of the evaluation points.

[0521] Specific operation: The user enters a score in the evaluation form and presses the "Submit" button.

[0522] Step 8:

[0523] The terminal transmits the evaluation points to the server.

[0524] Input: JSON data of the rating points entered by the user.

[0525] Data operation: Send an HTTP POST request to the server.

[0526] Output: The rating data sent to the server.

[0527] Specific operation: The device sends an HTTP POST request to the " / submit_evaluation" endpoint.

[0528] Step 9:

[0529] The server tallies the received evaluation points and stores them in a database.

[0530] Input: The rating data received by the server.

[0531] Data processing: The evaluation data is inserted into the database.

[0532] Output: Evaluation results stored in a database.

[0533] Specific operation: The server aggregates the evaluation data and stores it in a database.

[0534] Step 10:

[0535] The server displays the evaluation results on the user's terminal.

[0536] Input: Evaluation results stored in a database.

[0537] Data processing: The evaluation results are formatted and sent to the user's terminal.

[0538] Output: Evaluation results displayed on the user's terminal.

[0539] Specific operation: The server converts the evaluation results into JSON format and sends the evaluation results, such as "AI 1's 'Chameleon Rugby' wins," to the user device.

[0540] Step 11:

[0541] When a user inputs a topic from the device, the emotion engine collects the user's facial expressions and voice data.

[0542] Input: User's facial and voice data.

[0543] Data calculation: The emotion engine generates emotion data using facial expression recognition algorithms and voice analysis algorithms.

[0544] Output: The generated emotion data.

[0545] Specific operation: The device's camera and microphone will automatically start up and capture the user's facial expressions and voice.

[0546] Step 12:

[0547] The emotion engine analyzes the emotion data and recognizes the user's emotional state.

[0548] Input: Collected facial and voice data.

[0549] Data calculation: The emotion engine analyzes the collected data and classifies it as "enjoying" or "troubled."

[0550] Output: Parsed emotional state data.

[0551] Specific operation: The emotion engine performs facial expression recognition and voice analysis to identify the user's emotions.

[0552] Step 13:

[0553] The server filters the questions and answers based on emotional data.

[0554] Input: Parsed emotional state data.

[0555] Data processing: Execute filtering logic to select questions and answers.

[0556] Output: Questions and answers after filtering.

[0557] Specific operation: The server prioritizes displaying easy questions and simple answers depending on the user's emotional state.

[0558] Step 14:

[0559] The server corrects the evaluation points using the emotion data.

[0560] Input: Rating points and sentiment data.

[0561] Data calculation: Apply a positive correction to the evaluation points.

[0562] Output: Corrected rating points.

[0563] Specific operation: The server adjusts the rating points based on the user's emotional state.

[0564] Step 15:

[0565] The server stores the emotion data and evaluation results in a database, making them available for later reference.

[0566] Input: Emotion data and evaluation results.

[0567] Data processing: The emotion data and evaluation results are inserted into the database.

[0568] Output: Emotion data and evaluation results stored in a database.

[0569] Specific operation: The server stores the emotion data and evaluation results in a database so that they can be analyzed at a later date.

[0570] (Application example 2)

[0571] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0572] In conventional incident management systems, operators can report incident details and AI can suggest countermeasures, but it is difficult to provide value-added feedback or appropriate countermeasures that take into account the operator's emotional state. Furthermore, there is no system that collects and analyzes operator emotional data and provides filtering or appropriate countermeasures based on that data, so there is a lack of means to reduce operator stress and fatigue. This has led to issues such as a decline in the efficiency and quality of incident response.

[0573] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for inputting a topic from a user's terminal and transmitting the topic to the server; means for storing the topic received by the server in a database; means for sharing the stored topic with multiple artificial intelligences and generating answers based on the topics; means for transmitting the generated answers to the user's terminal; means for collecting and analyzing emotion data from the user's terminal, an emotion engine for analyzing the emotion data; means for filtering the generated answers based on the collected emotion data; and means for providing appropriate feedback based on the operator's emotion data. This enables added-value incident management, such as presenting incident response measures that take the operator's emotional state into consideration and managing operator stress.

[0574] A "user" is someone who uses the system to input questions and receive generated answers.

[0575] A "terminal" is a device used by a user, such as a smartphone or tablet.

[0576] A "topic" is a request or task entered by a user, based on which an answer is generated.

[0577] A "server" is a device or system that receives topics sent from a user's terminal, stores them, and shares them with multiple artificial intelligences.

[0578] A "database" is a storage device for storing questions received by the server and answers generated by the server.

[0579] "Artificial intelligence" is a program or system that generates answers based on input questions.

[0580] An "answer" is the output generated by the artificial intelligence based on the topic.

[0581] The "emotion engine" is a system for collecting and analyzing emotional data such as a user's facial expressions and voice.

[0582] "Filtering" is the process of adjusting the display order and content of generated answers based on collected emotional data.

[0583] "Feedback" refers to information or instructions provided to a user, with appropriate content presented based on their emotional state.

[0584] "Incident" means a security occurrence or problem reported by an Operator.

[0585] To implement this invention, a user inputs a topic from a terminal and sends the topic to a server. The server stores the received topic in a database and shares the stored topics with multiple AIs. Each AI generates an answer based on the topic, and the generated answer is sent back to the user's terminal via the server. This system includes an emotion engine that collects and analyzes emotion data from the user's terminal. Based on the collected emotion data, the generated answers are filtered and appropriate feedback is provided to the user.

[0586] Hardware and software used

[0587] Hardware:

[0588] Smartphone / tablet: A device where users can enter incident information and collect emotional data.

[0589] Camera: Used to collect facial expression data from the user.

[0590] Microphone: Used to collect user voice data.

[0591] software:

[0592] Python: Used as the main programming language.

[0593] EmotionRecognition (facial_emotion_recognition): An emotion recognition library for analyzing user facial expressions.

[0594] TextBlob: A natural language processing library for analyzing sentiment in text data.

[0595] Requests: An HTTP request library for sending and receiving data between the server and the device.

[0596] Data processing and calculation

[0597] The server first receives incident information from the user's device and stores it in a database. The stored questions are then shared with multiple AIs, which then generate answers based on the information. The answers are then sent back to the user's device via the server.

[0598] The emotion engine collects and analyzes the user's facial expressions and voice data in real time. The analyzed emotion data recognizes the user's current emotional state and filters the content and display order of the generated answers based on that. As a result, appropriate feedback can be provided to the user.

[0599] Specific examples

[0600] 1. Incident Reporting:

[0601] Users use their smartphones to report incidents such as "suspicious people loitering around the building."

[0602] 2. Generate answers:

[0603] The server stores reported incident information in a database and shares it with multiple artificial intelligence systems.

[0604] Each AI system generates the answer, "Contact the police and save the surveillance camera footage."

[0605] 3. Applying the Emotion Engine:

[0606] When a user reports an incident, the device's camera and microphone are used to collect the user's emotional data.

[0607] If the emotion engine analyzes and determines that the user is feeling very stressed, filtering will provide feedback such as "take a five-minute break."

[0608] Prompt Sentence Examples

[0609] Think of a name for a new sport.

[0610] "Look at a picture of a cat and say something"

[0611] "A song that evokes a gentle landscape"

[0612] In this way, by effectively utilizing user emotional data, it is possible to provide a more personalized experience and improve the efficiency of stress management for operators.

[0613] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0614] Step 1:

[0615] The user enters details of the incident on their smartphone or tablet, including a description of the incident and its location. For example, a user might enter "a suspicious person is loitering around the building," and this data is sent from the device to the server.

[0616] Step 2:

[0617] The server stores the incident information it receives in a database. Input data includes incident descriptions and location information, which are stored in the database as structured data. This data is then used for analysis and the generation of countermeasures.

[0618] Step 3:

[0619] The server shares the saved incident information with multiple AI systems. The server sends API requests to each AI system to provide the incident information. Each AI system generates countermeasures and advice based on this information.

[0620] Step 4:

[0621] Each AI generates a response to the incident. For example, it generates a specific response such as "contact the police and save the surveillance camera footage" in response to the incident information. This generated data is sent to the server.

[0622] Step 5:

[0623] The server collects the responses from each AI and sends them to the user's device. The server then sends the collected response data to the user's device in an appropriate format, allowing the user to view multiple countermeasures.

[0624] Step 6:

[0625] The user's device collects emotional data using a camera and microphone. While entering incident information, the user's facial expressions and voice data are captured and analyzed by the emotion engine. The emotion engine identifies the user's emotional state from their facial expressions and voice.

[0626] Step 7:

[0627] The emotion engine sends the analysis results to the server. The emotion engine then sends the analyzed user's emotion data (e.g., stress state, relaxed state, etc.) to the server. This data reflects the user's emotional state.

[0628] Step 8:

[0629] The server filters the generated answers based on emotion data and provides appropriate feedback. For example, if the user is feeling extremely stressed, the server displays additional feedback such as "Take a 5-minute break."

[0630] Step 9:

[0631] The server provides filtered answers and feedback to the user, allowing the user to receive not only appropriate responses but also feedback that takes into account their emotional state at the time.

[0632] Step 10:

[0633] The user inputs an evaluation of the generated answer and the provided feedback. The user assigns points based on whether the provided solution was effective or whether the feedback was useful. This evaluation data is sent back to the server.

[0634] Step 11:

[0635] The server collects the evaluation data and stores it in a database, along with additional information such as evaluation points and emotional data, and uses this data to improve the quality of incident response and optimize feedback.

[0636] Through these steps, incident response and effective feedback are achieved that take into account the user's emotional state.

[0637] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0638] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0639] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0640] [Second embodiment]

[0641] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0642] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0643] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0644] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0645] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0646] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0647] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0648] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0649] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0650] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0651] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0652] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0653] This invention provides a system in which a user inputs a theme from a terminal, an artificial intelligence generates answers and works based on the theme, and the user then evaluates them. Below, the program processing of the system of the present invention is explained in natural language, with specific examples.

[0654] Program processing overview

[0655] Register a topic

[0656] 1. The user enters a topic from the device.

[0657] For example, a user may input the topic "Come up with a name for a new sport."

[0658] 2. The device sends the entered topic to the server.

[0659] 3. The server stores the received topic in a database.

[0660] Generate answers

[0661] 1. The server shares the saved topics with multiple AIs.

[0662] For example, the server sends a topic to different AI engines (such as natural language generation AI and image generation AI).

[0663] 2. Each AI generates an answer based on the topic.

[0664] An example would be a natural language generation AI generating the answer "chameleon rugby."

[0665] The image generation AI generates paintings based on the theme of "the sea."

[0666] 3. The server collects the answers and creations from each AI and sends them to the user's device.

[0667] Evaluating answers

[0668] 1. The user enters evaluation points for each AI's answers and works from their device.

[0669] For example, a user may give "chameleon rugby" an 8-point rating and "bound basket" a 6-point rating.

[0670] 2. The device sends the user's evaluation points to the server.

[0671] 3. The server aggregates the received ratings and stores them in a database.

[0672] 4. The server displays the evaluation results on the user's device.

[0673] For example, display the result "AI 1's 'Chameleon Rugby' wins."

[0674] Responding to other creative tasks

[0675] This system can be applied not only to Ogiri but also to other creative tasks (composing music, painting, haiku, etc.). Specific examples are shown below.

[0676] 1. Composition Examples

[0677] The user inputs the theme "music that evokes a summer landscape" into the terminal.

[0678] The server sends the theme to the composition AI.

[0679] The composition AI generates music files and sends them to the server.

[0680] The server transmits the generated music file to the user's terminal.

[0681] The user rates the generated music and transmits the rating points from the terminal to the server.

[0682] The server compiles the evaluation results and displays them on the user's device.

[0683] 2. Examples of paintings

[0684] The user inputs a topic on the theme of "sea at sunset" into the terminal.

[0685] The server sends the theme to the image generation AI.

[0686] The image generation AI generates a painting based on the image and sends it to the server.

[0687] The server transmits the generated painting to the user's terminal.

[0688] The user evaluates the generated painting and transmits the evaluation points from the terminal to the server.

[0689] The server compiles the evaluation results and displays them on the user's device.

[0690] In this way, users can evaluate various creative tasks with the help of AI, and enjoy the creative process. The system stores the evaluation results in a database and makes them available for future reference, enabling transparent and objective evaluation.

[0691] The processing flow will be explained below.

[0692] Specific process flow for generating and evaluating answers to Ogiri topics

[0693] Register a topic

[0694] Step 1:

[0695] The user inputs a topic from the terminal.

[0696] Example: A user enters the topic "Think of a name for a new sport."

[0697] Step 2:

[0698] The device sends the input topic to the server.

[0699] The device sends the topic to the server using an HTTP request.

[0700] Step 3:

[0701] The server stores the topics in a database.

[0702] The server saves the topic in the database using an INSERT query.

[0703] Generate answers

[0704] Step 4:

[0705] The server shares the saved topics with multiple AIs.

[0706] The server sends a task to each AI using APIs and modifiers. For example, it sends a request to the ChatGPT API.

[0707] Step 5:

[0708] AI generates answers based on the topic.

[0709] Each AI uses its own natural language processing algorithm to generate answers. For example, ChatGPT generates the answer "Chameleon Rugby."

[0710] Step 6:

[0711] The server collects the responses from each AI.

[0712] The server processes the API responses of each AI and stores them in a database.

[0713] Step 7:

[0714] The server sends the response to the user's terminal.

[0715] The server sends a list of answers to the user's terminal.

[0716] Evaluating answers

[0717] Step 8:

[0718] The user inputs evaluation points for each AI's answer from the terminal.

[0719] Users enter points from 1 to 10 for each answer using a slider or input box.

[0720] Step 9:

[0721] The terminal transmits the user's rating to the server.

[0722] The device sends the evaluation points to the server in JSON format or similar.

[0723] Step 10:

[0724] The server aggregates the ratings and stores them in a database.

[0725] The server tallies the evaluation points for each answer and stores them in a database.

[0726] Step 11:

[0727] The server displays the final result on the user's terminal.

[0728] The server generates the results in HTML or JSON format and sends them to the user's device. Example: The server displays the result "AI 1's 'Chameleon Rugby' wins."

[0729] Application to other creative tasks (composing music, painting, haiku, etc.)

[0730] Specific examples of composition

[0731] Step 1:

[0732] The user inputs the theme "music that evokes a summer landscape" into the terminal.

[0733] Step 2:

[0734] The device sends the input topic to the server.

[0735] Step 3:

[0736] The server stores the received questions in a database.

[0737] Step 4:

[0738] The server sends the theme to the composition AI.

[0739] Step 5:

[0740] The AI ​​generates music files and sends them to the server.

[0741] Step 6:

[0742] The server stores the generated music files in a database.

[0743] Step 7:

[0744] The server sends the music files to the user's device.

[0745] Step 8:

[0746] The user rates the generated music and inputs rating points.

[0747] Step 9:

[0748] The terminal transmits the evaluation points to the server.

[0749] Step 10:

[0750] The server compiles the evaluation results and stores them in a database.

[0751] Step 11:

[0752] The server displays the final result on the user's device. Example: The server displays the result "Music that evokes a summer landscape received a score of 9."

[0753] Examples of paintings

[0754] Step 1:

[0755] The user inputs a topic on the theme of "sea at sunset" into the terminal.

[0756] Step 2:

[0757] The device sends the input topic to the server.

[0758] Step 3:

[0759] The server stores the received questions in a database.

[0760] Step 4:

[0761] The server sends the theme to the image generation AI.

[0762] Step 5:

[0763] The AI ​​generates a painting based on the image and sends it to the server.

[0764] Step 6:

[0765] The server stores the generated painting in a database.

[0766] Step 7:

[0767] The server sends the picture file to the user's terminal.

[0768] Step 8:

[0769] The user evaluates the generated painting and inputs evaluation points.

[0770] Step 9:

[0771] The terminal transmits the evaluation points to the server.

[0772] Step 10:

[0773] The server compiles the evaluation results and stores them in a database.

[0774] Step 11:

[0775] The server displays the final result on the user's terminal. Example: The server displays the result "The painting of the sea at sunset received 8 points."

[0776] Through the above process, a system is realized that allows users to use AI in various creative tasks and receive objective evaluations in a fun way.

[0777] Example 1

[0778] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0779] Existing AI systems generate creative answers and works based on user-entered topics, and the process of evaluating them is complex and difficult to carry out efficiently. Furthermore, there is no mechanism in place for reviewing the evaluation results later, making it difficult to conduct transparent and objective evaluations.

[0780] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0781] In this invention, the server includes means for inputting a theme from a user's communication device and transmitting the theme to the server device, means for storing the theme received by the server device in a storage device, means for sharing the stored theme with multiple information processing devices and generating answers based on it, means for transmitting the generated answers to the user's communication device, means for the user to input evaluation points for each answer from the communication device and transmit the evaluations to the server device, and means for the server device to tally up the evaluations received and display the results on the user's communication device. This enables users to efficiently input themes, generate creative answers and works based on them, and refer to the evaluation results transparently and objectively.

[0782] A "user" is an entity that uses the system to input a topic and evaluate the generated answers and works.

[0783] A "communication device" is a terminal used by a user, such as a computer or smartphone, that can connect to the Internet.

[0784] "Server device" refers to a centralized computer system that receives topics and ratings from users and processes that data.

[0785] "Storage device" refers to hardware that has a database or other data storage function connected to a server device.

[0786] "Information processing device" refers to a system that includes artificial intelligence to generate creative answers and works based on a given theme.

[0787] A "topic" refers to a prompt that a user enters and the AI ​​generates a creative answer or piece of work based on it.

[0788] "Evaluation points" refer to the evaluation value entered by the user for the generated answer or work.

[0789] "Generated answer" refers to a creative output generated by an information processing device (AI) based on input (topic) from a user.

[0790] "Evaluation results" refers to information that indicates which answers or works are superior, calculated by tallying up the evaluation points entered by users.

[0791] "Transparency and objectivity" refers to the characteristics of managing and displaying user-entered ratings and generated results fairly and clearly throughout the system.

[0792] The present invention relates to a system in which a user inputs a theme, an artificial intelligence generates creative answers and works based on the theme, and the user evaluates them. Hereinafter, embodiments of the present invention will be described in detail.

[0793] Enter and save the topic

[0794] A user uses a communication device (e.g., a computer or a smartphone) to access a dedicated interface. This interface has a text box where the user can input a topic. For example, the topic could be "Please think of a name for a new sport." The communication device then transmits the topic to a server device. The server device analyzes the received topic and stores it in a storage device (e.g., a database).

[0795] Generate answers

[0796] The server device retrieves the theme stored in the storage device periodically or based on a trigger event. Then, it sends this theme to multiple information processing devices (artificial intelligence models). For example, it sends the theme to a natural language generation AI (e.g., GPT-3) or an image generation AI (e.g., DALL-E). These information processing devices then generate answers or artwork based on the theme.

[0797] An example of a prompt for a natural language generation AI is "Come up with a name for a new sport."

[0798] An example of a prompt for the image generation AI is "Please draw a picture of the sea at sunset."

[0799] Collecting and submitting responses

[0800] The server device receives the responses generated by each information processing device, aggregates them, and then transmits the aggregated responses to the user's communication device, where the user can view the responses through the interface of the communication device.

[0801] Evaluating answers

[0802] The user can use the communication device to input evaluation points for each answer. For example, the user inputs 8 points for the answer "chameleon rugby" and 6 points for the answer "bound basket." The evaluation points are transmitted from the communication device to the server device.

[0803] Calculation and display of evaluation results

[0804] The server device stores the received evaluation points in a storage device and tally up the evaluation results. The tally up results are displayed on the communication device in a format that is easy for the user to understand. For example, the result displayed may be "AI 1's 'Chameleon Rugby' wins."

[0805] Application to other creative tasks

[0806] This system can be applied not only to Ogiri but also to other creative tasks such as composing music, painting, and generating text.

[0807] Composition examples

[0808] The user inputs "music that evokes a summer landscape" as a theme. The server device sends this theme to the composition AI, which then generates a music file. The generated music file is then sent to the user's communication device, and the user evaluates the music.

[0809] Painting examples

[0810] The user inputs a theme such as "sea at sunset." The server device sends the theme to the image generation AI, which then generates a painting. The generated painting is then sent to the user's communication device, and the user evaluates the painting.

[0811] In this way, users can evaluate various creative tasks with the help of artificial intelligence, and enjoy the creative process. The system also stores the evaluation results in a storage device and makes them available for later reference, enabling transparent and objective evaluation.

[0812] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0813] Step 1:

[0814] The user enters a topic

[0815] The user accesses a dedicated interface on the communication device and inputs a topic into the text box. As an example, consider the topic "Please think of a name for a new sport." When the user clicks the "Send" button, the device accepts this input data.

[0816] Input: User-entered question

[0817] Output: A data packet containing the question

[0818] Step 2:

[0819] The device sends the topic to the server

[0820] The device sends the topic entered by the user to the server as an HTTP request (POST request). The request includes the topic text and the user ID.

[0821] Input: Data packet containing the question

[0822] Output: HTTP request to the server

[0823] Step 3:

[0824] The server saves the topic in a database

[0825] The server parses the received HTTP request, extracts the question text and the user ID, and stores this information in a database using an SQL query.

[0826] Input: HTTP request to the server

[0827] Output: Insert operation into the database

[0828] Step 4:

[0829] The server sends the theme to each information processing device.

[0830] The server retrieves the topics stored in the database periodically or upon trigger events and sends them as prompts to multiple information processing devices (artificial intelligence models). For example, it sends topics to a natural language generation AI and an image generation AI.

[0831] Input: Questions stored in the database

[0832] Output: Prompt to each information processing device

[0833] Step 5:

[0834] Each information processing device generates an answer

[0835] Each AI generates an answer based on the prompt. For example, a natural language generation AI might generate the answer "chameleon rugby," while an image generation AI might generate an image with an "ocean" theme.

[0836] Input: Prompt to each information processing device

[0837] Output: Generated answers and works

[0838] Step 6:

[0839] The server collects the answers and sends them to the user's device.

[0840] The server receives the responses from the information processing devices, compiles them, and sends them to the user's terminal, usually as an HTTP response.

[0841] Input: Generated answers and works

[0842] Output: HTTP response to the user's device

[0843] Step 7:

[0844] Users rate the answers

[0845] The user uses the interface on the communication device to input evaluation points for each answer, for example, a user might input 8 points for "chameleon rugby" and 6 points for "bound basket."

[0846] Input: Generated answers and works

[0847] Output: Rating points

[0848] Step 8:

[0849] The device sends the rating to the server

[0850] The terminal receives the evaluation points from the user and sends them to the server as an HTTP request (POST request). The request includes the evaluation points for each answer and the user ID.

[0851] Input: Rating points

[0852] Output: HTTP request to the server

[0853] Step 9:

[0854] The server aggregates the ratings and stores them in a database

[0855] The server parses the received reputation points and stores them in a database, using an SQL query to store the reputation points for each answer.

[0856] Input: HTTP request to the server

[0857] Output: Insert operation into the database

[0858] Step 10:

[0859] The server displays the evaluation results on the user's device.

[0860] The server aggregates the evaluation results and sends them as an HTTP response to the user's device for display. For example, it sends the result "AI 1's 'Chameleon Rugby' wins."

[0861] Input: Reputation points stored in the database

[0862] Output: HTTP response to the user's device

[0863] (Application example 1)

[0864] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0865] There is a need to use artificial intelligence to improve the quality of content generated based on user-entered topics, and to efficiently evaluate that content and store it in a reusable format. Conventional systems have issues with making effective use of user evaluation results and being unable to handle a wide range of creative tasks.

[0866] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0867] In this invention, the server includes means for inputting a theme from a user's information processing device and transmitting the theme to the data processing device, means for storing the theme received by the data processing device in a storage device, means for sharing the stored theme with multiple intelligent processing devices and generating answers based on the theme, means for transmitting the generated answers to the user's information processing device, means for the user to input points for each answer from the information processing device and transmit the evaluation to the data processing device, means for aggregating the received evaluations by the data processing device and displaying the results on the user's information processing device, means for storing the generated content together with the evaluation points in a database so that the data processing device can later refer to it, means for the intelligent processing device to generate content such as text, images, music, and video based on the theme input by the user, means for the user to evaluate the generated content and transmit the evaluation points from the information processing device to the data processing device, and means for the data processing device to aggregate the evaluation results and display them on the user's information processing device. This makes it possible to effectively utilize the user's evaluation results, respond to a wide range of creative tasks, and generate and evaluate high-quality content.

[0868] An "information processing device" is a device that has the function of processing, transmitting, and receiving data input by a user.

[0869] A "data processing device" is a device that receives data sent from a user and stores and aggregates the data.

[0870] A "storage device" is a device that records data and keeps it accessible when needed.

[0871] An "intelligent processing device" is a device that includes artificial intelligence to generate answers and content based on a given topic.

[0872] "Generated content" refers to creative output such as text, images, music, and video generated by an intelligent processing device based on a theme entered by a user.

[0873] "Evaluation points" are numerical values ​​of evaluations given to generated content by users.

[0874] A "database" is a system that stores data in an organized manner and manages it so that necessary information can be retrieved efficiently.

[0875] The term "topic" refers to a sentence or command that indicates an instruction or request from a user regarding the content that the user wants the intelligent processing device to generate.

[0876] This invention is a system in which a user inputs a theme from an information processing device, an intelligent processing device is used to generate creative content based on the theme, and the generated content is evaluated. The details of this system are described below.

[0877] System Configuration

[0878] The system mainly consists of the following components:

[0879] User's information processing device (smartphone, tablet, etc.)

[0880] Data processing device (cloud server, etc.)

[0881] Intelligent Processing Units (devices containing generative AI models)

[0882] Storage devices (databases, etc.)

[0883] The specific hardware and software used

[0884] Hardware:

[0885] Cloud servers (e.g. AWS EC2 instances)

[0886] Smartphones (e.g. iOS / Android devices)

[0887] software:

[0888] Natural language processing AI (e.g. GPT-3)

[0889] Image generation AI (e.g. DALL-E)

[0890] Music generation AI (e.g. Amper Music)

[0891] Database management system (e.g. MySQL)

[0892] Program processing flow

[0893] 1. Enter your topic and submit

[0894] A user inputs a topic using an information processing device. The topic is written in natural language.

[0895] Example: Enter the subject as "Draw a cityscape of the future."

[0896] 2. Receiving and saving the topic

[0897] The data processing device receives the theme sent by the user and stores it in a storage device.

[0898] 3. Sharing topics and creating content

[0899] The theme stored in the storage device is shared with multiple intelligent processing devices, and each intelligent processing device generates content based on the theme.

[0900] Examples: Natural language processing AI generates text, image generation AI generates images, and music generation AI generates music.

[0901] Example prompt: "Create an image of a futuristic city landscape with flying cars and skyscrapers."

[0902] 4. Submitting and Displaying Content

[0903] The content generated by the intelligent processing device is transmitted to the data processing device and distributed to the user's information processing device.

[0904] 5. Content Rating

[0905] A user gives evaluation points to content generated using an information processing device, and the evaluation points are transmitted to the data processing device.

[0906] 6. Calculation and display of evaluation results

[0907] The data processing device tallies the received evaluation points and displays the results on the user's information processing device.

[0908] Adding specific examples

[0909] A user inputs a theme, "Please create music that evokes the image of a summer landscape," into an information processing device.

[0910] The data processing device sends this theme to the music generation AI, and the generated music is stored in a storage device and distributed to the user's information processing device.

[0911] The user rates the generated music and the rating points are transmitted to the data processing device.

[0912] The data processing device compiles the evaluation results, stores them in a storage device for future reference, and notifies the user.

[0913] This system allows users to generate and evaluate high-quality content based on a topic they input.

[0914] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0915] Step 1:

[0916] A user inputs a topic using an information processing device and sends the topic to the server. The topic is input using natural language, specifically a prompt such as "Please draw a picture of a future cityscape." This input data is sent to the server.

[0917] Step 2:

[0918] The server stores the received topic in a database (storage device). In this process, the topic data sent by the user is received and stored in the appropriate table in the database.

[0919] Step 3:

[0920] The server shares the topics stored in the storage device with multiple intelligent processing devices. Specifically, it sends the stored topics to different intelligent processing devices, such as natural language processing AI, image generation AI, and music generation AI. The server formats the topics so that each intelligent processing device can generate appropriate content.

[0921] Step 4:

[0922] Each intelligent processing device generates content based on a given theme. For example, a natural language processing AI generates sentences, an image generation AI generates images, and a music generation AI generates music. For the prompt "Please draw a futuristic cityscape," the image generation AI processes it as "Create an image of a futuristic city landscape with flying cars and skyscrapers."

[0923] Step 5:

[0924] The generated content is sent from each intelligent processing device to a server, which receives the generated content data and sends it to the user's information processing device, i.e., collects the generated text, images, music, etc. and provides them to the user.

[0925] Step 6:

[0926] The user inputs evaluation points for the content generated by the information processing device. For example, the user assigns evaluation points such as "9 points" to the generated image. This evaluation point data is sent to the server.

[0927] Step 7:

[0928] The server aggregates the received evaluation points. Specifically, it aggregates the evaluation points sent by multiple users and generates statistical data such as the average score and the highest score.

[0929] Step 8:

[0930] The results of the counting are sent from the server to the user's information processing device and displayed to the user. Specifically, the results are displayed in a format such as "The average rating for this content is 8.5 points."

[0931] Step 9:

[0932] The generated content and the evaluation results are stored in a database by the server. For future reference, the generated content along with the evaluation points are stored in a storage device and can be accessed by users or other processing devices.

[0933] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0934] This invention provides a system in which a user inputs a theme from a terminal, an artificial intelligence generates answers and works based on that theme, and the user evaluates them, in addition to a system that combines an emotion engine that recognizes the user's emotions. Below, the program processing of the system of the present invention will be explained in natural language, with concrete examples.

[0935] Program processing overview

[0936] Register a topic

[0937] 1. The user enters a topic from the device.

[0938] For example, a user may input the topic "Come up with a name for a new sport."

[0939] 2. The device sends the entered topic to the server.

[0940] 3. The server stores the received questions in a database.

[0941] Generate answers

[0942] 1. The server shares the saved topics with multiple AIs.

[0943] The server sends a task to each AI using APIs and modifiers. For example, it sends a request to the ChatGPT API.

[0944] 2. Each AI generates an answer based on the topic.

[0945] Each AI uses its own natural language processing algorithm to generate answers. For example, ChatGPT generates the answer "Chameleon Rugby."

[0946] 3. The server collects the answers from each AI.

[0947] The server processes the API responses of each AI and stores them in a database.

[0948] 4. The server sends the answer to the user's device.

[0949] The server sends a list of answers to the user's terminal.

[0950] Evaluating answers

[0951] 1. The user enters evaluation points for each AI's answers and works from their device.

[0952] For example, a user gives "chameleon rugby" an 8-point rating and "bound basket" a 6-point rating.

[0953] 2. The device sends the user's evaluation points to the server.

[0954] 3. The server aggregates the received ratings and stores them in a database.

[0955] 4. The server displays the evaluation results on the user's device.

[0956] For example, the server might display the result "AI 1's 'Chameleon Rugby' wins."

[0957] Applying the Emotion Engine

[0958] The system incorporates an emotion engine that recognizes the user's emotions and provides appropriate feedback and adjustments based on those emotions.

[0959] 1. When a user enters a topic on their device, the emotion engine collects emotional data from the user's facial expressions, voice, and text.

[0960] Example: When a user types "Think of a name for a new sport," facial expression and voice data are captured from the camera and microphone.

[0961] 2. The emotion engine analyzes the emotion data and recognizes the user's current emotional state.

[0962] Example: The emotion engine detects emotions such as "enjoyed" or "troubled" from the user's facial expressions and voice.

[0963] 3. The server filters the questions and generated answers based on data from the emotion engine.

[0964] Example: If a user is having trouble, prioritize displaying questions with low difficulty and simple answers.

[0965] 4. The server influences the user's evaluation points with the emotional data.

[0966] Example: If a user is having a lot of fun, the evaluation points are adjusted to be positive.

[0967] 5. The server stores the evaluation results, including emotional data, in a database so that they can be referenced later.

[0968] Example: Recording a user's emotional state so that the relationship between that data and rating points can be analyzed later.

[0969] Specific examples

[0970] Ogiri using an emotional engine

[0971] 1. The user enters the topic, "Look at a picture of a cat and say one thing."

[0972] 2. The emotion engine detects the user's "smile."

[0973] 3. The server uses the emotional data to prioritize and display more humorous answers.

[0974] 4. The AI-generated answer, "This cat is making its modeling debut!" will be displayed.

[0975] 5. If the user gives it a high rating, it will be stored in the database along with the emotional data.

[0976] Composing with an Emotion Engine

[0977] 1. The user enters the theme "a song that evokes a gentle landscape."

[0978] 2. The emotion engine detects the user's "relaxed" state.

[0979] 3. The composition AI will then generate a relaxing, calming song based on that.

[0980] 4. The server sends the generated song to the user's device.

[0981] 5. The user rates the generated song highly, and the emotional data is saved as a rating.

[0982] In this way, by effectively utilizing the user's emotional data, a system can be realized that can provide a more personalized experience.

[0983] The processing flow will be explained below.

[0984] Specific processing flow of the invention that combines the emotion engine

[0985] Register a topic

[0986] Step 1:

[0987] The user inputs a topic from the terminal.

[0988] Example: A user enters the topic "Think of a name for a new sport."

[0989] Step 2:

[0990] The device sends the input topic to the server.

[0991] The device sends the topic to the server using an HTTP request.

[0992] Step 3:

[0993] The server stores the topics in a database.

[0994] The server saves the topic in the database using an INSERT query.

[0995] Emotion recognition

[0996] Step 4:

[0997] The terminal acquires the user's emotion data.

[0998] The device's camera and microphone are used to collect the user's facial expressions and voice data.

[0999] Step 5:

[1000] The terminal transmits emotion data to the emotion engine.

[1001] The device transmits emotion data to the emotion engine in real time.

[1002] Step 6:

[1003] The emotion engine analyzes the emotion data and recognizes the user's emotional state.

[1004] Example: An emotion engine detects emotions such as "enjoyed" or "troubled."

[1005] Generate answers

[1006] Step 7:

[1007] The server shares the saved topics with multiple AIs.

[1008] The server sends a task to each AI using APIs and modifiers. For example, it sends a request to the ChatGPT API.

[1009] Step 8:

[1010] AI generates answers based on the topic.

[1011] Each AI uses its own natural language processing algorithm to generate answers. For example, ChatGPT generates the answer "Chameleon Rugby."

[1012] Step 9:

[1013] The server collects the responses from each AI.

[1014] The server processes the API responses of each AI and stores them in a database.

[1015] Step 10:

[1016] The server filters the answers and works based on data from the emotion engine.

[1017] Example: If a user is having trouble, prioritize displaying questions with low difficulty and simple answers.

[1018] Step 11:

[1019] The server sends the filtered response to the user's terminal.

[1020] The server sends a list of answers to the user's terminal.

[1021] Evaluating answers

[1022] Step 12:

[1023] The user inputs evaluation points for each AI's answers and works from the device.

[1024] Users enter points from 1 to 10 for each answer using a slider or input box.

[1025] Step 13:

[1026] The terminal transmits the evaluation points to the server.

[1027] The device sends the evaluation points to the server in JSON format or similar.

[1028] Step 14:

[1029] The server aggregates the received ratings and adjusts points as necessary based on emotional data.

[1030] Example: If a user is having a lot of fun, the evaluation points are adjusted to be positive.

[1031] Step 15:

[1032] The server stores the evaluation results in a database.

[1033] The server stores the evaluation points and emotion data for each answer in a database.

[1034] Step 16:

[1035] The server displays the final result on the user's terminal.

[1036] The server generates the results in HTML or JSON format and sends them to the user's device. Example: The server displays the result "AI 1's 'Chameleon Rugby' wins."

[1037] Specific examples

[1038] Ogiri using an emotional engine

[1039] Step 1:

[1040] The user inputs the topic "Say one thing when you look at a picture of a cat."

[1041] Step 2:

[1042] The device sends the input topic to the server.

[1043] Step 3:

[1044] The server stores the topics in a database.

[1045] Step 4:

[1046] The terminal acquires the user's facial expression data using a camera.

[1047] Step 5:

[1048] The device sends the facial expression data to the emotion engine.

[1049] Step 6:

[1050] The emotion engine analyzes the transmitted data and detects the user's "smile."

[1051] Step 7:

[1052] The server sends the topic to multiple AIs, which generate answers.

[1053] Step 8:

[1054] The AI ​​generates the answer "This cat is making its modeling debut!" and sends it to the server.

[1055] Step 9:

[1056] The server collects the responses and filters them based on the sentiment data.

[1057] Step 10:

[1058] The server sends the filtered response to the user's terminal.

[1059] Step 11:

[1060] The user gives a high rating of 8 points to the answer "This cat is making her modeling debut!"

[1061] Step 12:

[1062] The terminal transmits the evaluation points to the server.

[1063] Step 13:

[1064] The server makes corrections based on the evaluation points and emotion data and stores the results in a database.

[1065] Step 14:

[1066] The server displays the final result, "AI 1's 'This cat is a model!' wins" on the user's device.

[1067] In this way, by effectively utilizing the user's emotional data, a system can be realized that can provide a more personalized experience.

[1068] Example 2

[1069] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1070] In conventional creative tasks, systems existed that generated and evaluated answers to user-provided questions, but they lacked a mechanism to consider the user's emotional state. As a result, users were often dissatisfied with answers or questions that did not match their emotions. Furthermore, because the evaluation results did not incorporate emotional data, the accuracy of the evaluation and the improvement of the user experience were not fully realized.

[1071] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1072] In this invention, the server includes means including an emotion engine that collects user emotion data, means for filtering questions and answers based on the emotion data, and means for correcting evaluation points using the emotion data, thereby making it possible to provide questions and answers that suit the user's emotions and to reflect the emotion data in the evaluation results.

[1073] A "user" is a person who uses the system to input questions and evaluate generated answers.

[1074] A "terminal" is a device operated by a user, which provides an interface for input and evaluation.

[1075] The "server" is a computer system that receives questions, stores them, shares them with the AI, collects answers, and compiles evaluations.

[1076] A "topic" is a question or theme that a user enters through a device, and is the basis for the AI ​​to generate an answer.

[1077] The "database" is a system for storing the questions received by the server, the answers generated, and the user's evaluation points.

[1078] "Artificial intelligence (AI)" is a program that generates answers based on questions provided by users.

[1079] An "answer" is an output result generated by the artificial intelligence based on a topic provided by the user.

[1080] "Evaluation points" are numerical values ​​that are given to a user to evaluate a generated answer.

[1081] An "emotion engine" is a system that recognizes a user's emotional state and collects and analyzes that data.

[1082] "Emotional Data" is information about a user's emotional state that is collected and analyzed by the emotion engine.

[1083] "Filtering" is a process of adjusting the priority of the questions and generated answers based on emotional data.

[1084] "Correction of evaluation points" is a process of modifying evaluation points based on the user's emotion data.

[1085] This invention uses artificial intelligence to generate answers based on topics entered by users, and improves the performance of the entire system based on the user's evaluations and emotional data. This system is realized by combining users, terminals, servers, an emotional engine, and artificial intelligence (AI).

[1086] First, the user inputs a topic using a device. This device refers to hardware (smartphone, tablet, PC, etc.) that runs software such as a web browser or mobile app. For example, the user might input a topic in text format, such as "Please think of a name for a new sport." This input data is sent from the device to the server. At this time, the device converts the topic into JSON format and sends it to the server via an HTTP POST request. This process transmits the user's topic to the server.

[1087] The server stores the received questions in a database (e.g., MongoDB). The stored questions are shared with various artificial intelligences (generative AI models). The server sends the questions to each AI's API, and each AI generates an answer using its own natural language processing algorithm. For example, if the server sends a request to ChatGPT's API saying, "Please think of a name for a new sport," ChatGPT generates the answer "Chameleon Rugby."

[1088] Next, the server collects the answers from each AI and sends them to the user's device. These answers are displayed on the user's device, and the user enters evaluation points for each answer. The evaluation points are again sent from the device to the server, which tallies them and stores the evaluation results in a database. The tallied results are then displayed on the user's device. For example, if a user rates "Chameleon Rugby" as 8 points and "Bounce Basket" as 6 points, the server tallies these and displays a result such as "AI 1's 'Chameleon Rugby' wins."

[1089] Furthermore, the system incorporates an emotion engine. When a user inputs a topic from their device, the emotion engine uses a camera and microphone to collect facial and voice data and analyze the user's emotional state. From the analysis results, the engine recognizes emotions such as "enjoying" or "struggling," and filters the topics and generated answers based on this emotional data. For example, if the server recognizes that the user is struggling, it will prioritize displaying topics with low difficulty and simple answers. Furthermore, evaluation points are also adjusted based on the user's emotional state. As a result, the system stores the user's evaluation points and emotional data in a database for later analysis.

[1090] For example, if a user inputs the topic "Say something when you look at a photo of a cat," and the emotion engine detects a "smile," the server will prioritize humorous responses, such as "This cat is ready to make its debut as a model!" If the user gives a high rating, the rating and emotion data are saved in the database.

[1091] In addition, if a user inputs a theme of "a song that evokes a gentle landscape" and the emotion engine detects a "relaxed" state, the composition AI will generate a relaxing, calm song, which will be sent to the user's device. The user can then rate the generated song highly, and their emotional data will be saved as a rating. The system is similarly configured to handle other creative tasks, such as composing music, painting, and haiku poetry.

[1092] In this way, the present invention is a system that can effectively utilize a user's emotional data to provide a more personalized experience.

[1093] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1094] Step 1:

[1095] The user inputs a topic from the terminal.

[1096] Input: A user types "Think of a new sport name" into an input field in a web browser or app.

[1097] Data processing: The terminal converts the user input into JSON format.

[1098] Output: The generated JSON data.

[1099] Specific operation: The user presses the "Submit" button to send the topic to the server.

[1100] Step 2:

[1101] The device sends the input topic to the server.

[1102] Input: JSON data generated on the terminal.

[1103] Data operation: Send an HTTP POST request to the server.

[1104] Output: The topic data sent to the server.

[1105] Specific operation: The device sends an HTTP POST request to the " / submit_topic" endpoint.

[1106] Step 3:

[1107] The server stores the received questions in a database.

[1108] Input: The question data received by the server.

[1109] Data processing: Insert the received data into the database.

[1110] Output: The questions stored in the database.

[1111] Specific operation: The server stores the subject data in a NoSQL database such as MongoDB.

[1112] Step 4:

[1113] The server shares the saved topics with each AI's API.

[1114] Input: A question stored in the database.

[1115] Data processing: Generate requests corresponding to each AI's API.

[1116] Output: The requests sent to each AI.

[1117] Specific operation: The server sends a request to an API endpoint such as ChatGPT.

[1118] Step 5:

[1119] Each AI receives a question from the server and generates an answer.

[1120] Input: The topic requests received by each AI.

[1121] Data Computing: Uses natural language processing algorithms to generate answers.

[1122] Output: The generated answer.

[1123] Specific operation: AI such as ChatGPT generates answers such as "Chameleon Rugby."

[1124] Step 6:

[1125] The server collects the responses from each AI and sends them to the user's device.

[1126] Input: The answers generated by each AI.

[1127] Data processing: Compile the answers into a list.

[1128] Output: The answer list sent to the user's device.

[1129] Specific operation: The server converts the answer list into JSON format and sends it to the specified endpoint on the user's device.

[1130] Step 7:

[1131] The user inputs evaluation points for each AI's answer from the terminal.

[1132] Input: Rating points entered by the user.

[1133] Data processing: Convert the evaluation points into JSON format.

[1134] Output: JSON data of the evaluation points.

[1135] Specific operation: The user enters a score in the evaluation form and presses the "Submit" button.

[1136] Step 8:

[1137] The terminal transmits the evaluation points to the server.

[1138] Input: JSON data of the rating points entered by the user.

[1139] Data operation: Send an HTTP POST request to the server.

[1140] Output: The rating data sent to the server.

[1141] Specific operation: The device sends an HTTP POST request to the " / submit_evaluation" endpoint.

[1142] Step 9:

[1143] The server tallies the received evaluation points and stores them in a database.

[1144] Input: The rating data received by the server.

[1145] Data processing: The evaluation data is inserted into the database.

[1146] Output: Evaluation results stored in a database.

[1147] Specific operation: The server aggregates the evaluation data and stores it in a database.

[1148] Step 10:

[1149] The server displays the evaluation results on the user's terminal.

[1150] Input: Evaluation results stored in a database.

[1151] Data processing: The evaluation results are formatted and sent to the user's terminal.

[1152] Output: Evaluation results displayed on the user's terminal.

[1153] Specific operation: The server converts the evaluation results into JSON format and sends the evaluation results, such as "AI 1's 'Chameleon Rugby' wins," to the user device.

[1154] Step 11:

[1155] When a user inputs a topic from the device, the emotion engine collects the user's facial expressions and voice data.

[1156] Input: User's facial and voice data.

[1157] Data calculation: The emotion engine generates emotion data using facial expression recognition algorithms and voice analysis algorithms.

[1158] Output: The generated emotion data.

[1159] Specific operation: The device's camera and microphone will automatically start up and capture the user's facial expressions and voice.

[1160] Step 12:

[1161] The emotion engine analyzes the emotion data and recognizes the user's emotional state.

[1162] Input: Collected facial and voice data.

[1163] Data calculation: The emotion engine analyzes the collected data and classifies it as "enjoying" or "troubled."

[1164] Output: Parsed emotional state data.

[1165] Specific operation: The emotion engine performs facial expression recognition and voice analysis to identify the user's emotions.

[1166] Step 13:

[1167] The server filters the questions and answers based on emotional data.

[1168] Input: Parsed emotional state data.

[1169] Data processing: Execute filtering logic to select questions and answers.

[1170] Output: Questions and answers after filtering.

[1171] Specific operation: The server prioritizes displaying easy questions and simple answers depending on the user's emotional state.

[1172] Step 14:

[1173] The server corrects the evaluation points using the emotion data.

[1174] Input: Rating points and sentiment data.

[1175] Data calculation: Apply a positive correction to the evaluation points.

[1176] Output: Corrected rating points.

[1177] Specific operation: The server adjusts the rating points based on the user's emotional state.

[1178] Step 15:

[1179] The server stores the emotion data and evaluation results in a database, making them available for later reference.

[1180] Input: Emotion data and evaluation results.

[1181] Data processing: The emotion data and evaluation results are inserted into the database.

[1182] Output: Emotion data and evaluation results stored in a database.

[1183] Specific operation: The server stores the emotion data and evaluation results in a database so that they can be analyzed at a later date.

[1184] (Application example 2)

[1185] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1186] In conventional incident management systems, operators can report incident details and AI can suggest countermeasures, but it is difficult to provide value-added feedback or appropriate countermeasures that take into account the operator's emotional state. Furthermore, there is no system that collects and analyzes operator emotional data and provides filtering or appropriate countermeasures based on that data, so there is a lack of means to reduce operator stress and fatigue. This has led to issues such as a decline in the efficiency and quality of incident response.

[1187] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for inputting a topic from a user's terminal and transmitting the topic to the server; means for storing the topic received by the server in a database; means for sharing the stored topic with multiple artificial intelligences and generating answers based on the topics; means for transmitting the generated answers to the user's terminal; means for collecting and analyzing emotion data from the user's terminal, an emotion engine for analyzing the emotion data; means for filtering the generated answers based on the collected emotion data; and means for providing appropriate feedback based on the operator's emotion data. This enables added-value incident management, such as presenting incident response measures that take the operator's emotional state into consideration and managing operator stress.

[1188] A "user" is someone who uses the system to input questions and receive generated answers.

[1189] A "terminal" is a device used by a user, such as a smartphone or tablet.

[1190] A "topic" is a request or task entered by a user, based on which an answer is generated.

[1191] A "server" is a device or system that receives topics sent from a user's terminal, stores them, and shares them with multiple artificial intelligences.

[1192] A "database" is a storage device for storing questions received by the server and answers generated by the server.

[1193] "Artificial intelligence" is a program or system that generates answers based on input questions.

[1194] An "answer" is the output generated by the artificial intelligence based on the topic.

[1195] The "emotion engine" is a system for collecting and analyzing emotional data such as a user's facial expressions and voice.

[1196] "Filtering" is the process of adjusting the display order and content of generated answers based on collected emotional data.

[1197] "Feedback" refers to information or instructions provided to a user, with appropriate content presented based on their emotional state.

[1198] "Incident" means a security occurrence or problem reported by an Operator.

[1199] To implement this invention, a user inputs a topic from a terminal and sends the topic to a server. The server stores the received topic in a database and shares the stored topics with multiple AIs. Each AI generates an answer based on the topic, and the generated answer is sent back to the user's terminal via the server. This system includes an emotion engine that collects and analyzes emotion data from the user's terminal. Based on the collected emotion data, the generated answers are filtered and appropriate feedback is provided to the user.

[1200] Hardware and software used

[1201] Hardware:

[1202] Smartphone / tablet: A device where users can enter incident information and collect emotional data.

[1203] Camera: Used to collect facial expression data from the user.

[1204] Microphone: Used to collect user voice data.

[1205] software:

[1206] Python: Used as the main programming language.

[1207] EmotionRecognition (facial_emotion_recognition): An emotion recognition library for analyzing user facial expressions.

[1208] TextBlob: A natural language processing library for analyzing sentiment in text data.

[1209] Requests: An HTTP request library for sending and receiving data between the server and the device.

[1210] Data processing and calculation

[1211] The server first receives incident information from the user's device and stores it in a database. The stored questions are then shared with multiple AIs, which then generate answers based on the information. The answers are then sent back to the user's device via the server.

[1212] The emotion engine collects and analyzes the user's facial expressions and voice data in real time. The analyzed emotion data recognizes the user's current emotional state and filters the content and display order of the generated answers based on that. As a result, appropriate feedback can be provided to the user.

[1213] Specific examples

[1214] 1. Incident Reporting:

[1215] Users use their smartphones to report incidents such as "suspicious people loitering around the building."

[1216] 2. Generate answers:

[1217] The server stores reported incident information in a database and shares it with multiple artificial intelligence systems.

[1218] Each AI system generates the answer, "Contact the police and save the surveillance camera footage."

[1219] 3. Applying the Emotion Engine:

[1220] When a user reports an incident, the device's camera and microphone are used to collect the user's emotional data.

[1221] If the emotion engine analyzes and determines that the user is feeling very stressed, filtering will provide feedback such as "take a five-minute break."

[1222] Prompt Sentence Examples

[1223] Think of a name for a new sport.

[1224] "Look at a picture of a cat and say something"

[1225] "A song that evokes a gentle landscape"

[1226] In this way, by effectively utilizing user emotional data, it is possible to provide a more personalized experience and improve the efficiency of stress management for operators.

[1227] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1228] Step 1:

[1229] The user enters details of the incident on their smartphone or tablet, including a description of the incident and its location. For example, a user might enter "a suspicious person is loitering around the building," and this data is sent from the device to the server.

[1230] Step 2:

[1231] The server stores the incident information it receives in a database. Input data includes incident descriptions and location information, which are stored in the database as structured data. This data is then used for analysis and the generation of countermeasures.

[1232] Step 3:

[1233] The server shares the saved incident information with multiple AI systems. The server sends API requests to each AI system to provide the incident information. Each AI system generates countermeasures and advice based on this information.

[1234] Step 4:

[1235] Each AI generates a response to the incident. For example, it generates a specific response such as "contact the police and save the surveillance camera footage" in response to the incident information. This generated data is sent to the server.

[1236] Step 5:

[1237] The server collects the responses from each AI and sends them to the user's device. The server then sends the collected response data to the user's device in an appropriate format, allowing the user to view multiple countermeasures.

[1238] Step 6:

[1239] The user's device collects emotional data using a camera and microphone. While entering incident information, the user's facial expressions and voice data are captured and analyzed by the emotion engine. The emotion engine identifies the user's emotional state from their facial expressions and voice.

[1240] Step 7:

[1241] The emotion engine sends the analysis results to the server. The emotion engine then sends the analyzed user's emotion data (e.g., stress state, relaxed state, etc.) to the server. This data reflects the user's emotional state.

[1242] Step 8:

[1243] The server filters the generated answers based on emotion data and provides appropriate feedback. For example, if the user is feeling extremely stressed, the server displays additional feedback such as "Take a 5-minute break."

[1244] Step 9:

[1245] The server provides filtered answers and feedback to the user, allowing the user to receive not only appropriate responses but also feedback that takes into account their emotional state at the time.

[1246] Step 10:

[1247] The user inputs an evaluation of the generated answer and the provided feedback. The user assigns points based on whether the provided solution was effective or whether the feedback was useful. This evaluation data is sent back to the server.

[1248] Step 11:

[1249] The server collects the evaluation data and stores it in a database, along with additional information such as evaluation points and emotional data, and uses this data to improve the quality of incident response and optimize feedback.

[1250] Through these steps, incident response and effective feedback are achieved that take into account the user's emotional state.

[1251] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1252] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1253] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1254] [Third embodiment]

[1255] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1256] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1257] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1258] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1259] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1260] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1261] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1262] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1263] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1264] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1265] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1266] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1267] This invention provides a system in which a user inputs a theme from a terminal, an artificial intelligence generates answers and works based on the theme, and the user then evaluates them. Below, the program processing of the system of the present invention is explained in natural language, with specific examples.

[1268] Program processing overview

[1269] Register a topic

[1270] 1. The user enters a topic from the device.

[1271] For example, a user may input the topic "Come up with a name for a new sport."

[1272] 2. The device sends the entered topic to the server.

[1273] 3. The server stores the received topic in a database.

[1274] Generate answers

[1275] 1. The server shares the saved topics with multiple AIs.

[1276] For example, the server sends a topic to different AI engines (such as natural language generation AI and image generation AI).

[1277] 2. Each AI generates an answer based on the topic.

[1278] An example would be a natural language generation AI generating the answer "chameleon rugby."

[1279] The image generation AI generates paintings based on the theme of "the sea."

[1280] 3. The server collects the answers and creations from each AI and sends them to the user's device.

[1281] Evaluating answers

[1282] 1. The user enters evaluation points for each AI's answers and works from their device.

[1283] For example, a user may give "chameleon rugby" an 8-point rating and "bound basket" a 6-point rating.

[1284] 2. The device sends the user's evaluation points to the server.

[1285] 3. The server aggregates the received ratings and stores them in a database.

[1286] 4. The server displays the evaluation results on the user's device.

[1287] For example, display the result "AI 1's 'Chameleon Rugby' wins."

[1288] Responding to other creative tasks

[1289] This system can be applied not only to Ogiri but also to other creative tasks (composing music, painting, haiku, etc.). Specific examples are shown below.

[1290] 1. Composition Examples

[1291] The user inputs the theme "music that evokes a summer landscape" into the terminal.

[1292] The server sends the theme to the composition AI.

[1293] The composition AI generates music files and sends them to the server.

[1294] The server transmits the generated music file to the user's terminal.

[1295] The user rates the generated music and transmits the rating points from the terminal to the server.

[1296] The server compiles the evaluation results and displays them on the user's device.

[1297] 2. Examples of paintings

[1298] The user inputs a topic on the theme of "sea at sunset" into the terminal.

[1299] The server sends the theme to the image generation AI.

[1300] The image generation AI generates a painting based on the image and sends it to the server.

[1301] The server transmits the generated painting to the user's terminal.

[1302] The user evaluates the generated painting and transmits the evaluation points from the terminal to the server.

[1303] The server compiles the evaluation results and displays them on the user's device.

[1304] In this way, users can evaluate various creative tasks with the help of AI, and enjoy the creative process. The system stores the evaluation results in a database and makes them available for future reference, enabling transparent and objective evaluation.

[1305] The processing flow will be explained below.

[1306] Specific process flow for generating and evaluating answers to Ogiri topics

[1307] Register a topic

[1308] Step 1:

[1309] The user inputs a topic from the terminal.

[1310] Example: A user enters the topic "Think of a name for a new sport."

[1311] Step 2:

[1312] The device sends the input topic to the server.

[1313] The device sends the topic to the server using an HTTP request.

[1314] Step 3:

[1315] The server stores the topics in a database.

[1316] The server saves the topic in the database using an INSERT query.

[1317] Generate answers

[1318] Step 4:

[1319] The server shares the saved topics with multiple AIs.

[1320] The server sends a task to each AI using APIs and modifiers. For example, it sends a request to the ChatGPT API.

[1321] Step 5:

[1322] AI generates answers based on the topic.

[1323] Each AI uses its own natural language processing algorithm to generate answers. For example, ChatGPT generates the answer "Chameleon Rugby."

[1324] Step 6:

[1325] The server collects the responses from each AI.

[1326] The server processes the API responses of each AI and stores them in a database.

[1327] Step 7:

[1328] The server sends the response to the user's terminal.

[1329] The server sends a list of answers to the user's terminal.

[1330] Evaluating answers

[1331] Step 8:

[1332] The user inputs evaluation points for each AI's answer from the terminal.

[1333] Users enter points from 1 to 10 for each answer using a slider or input box.

[1334] Step 9:

[1335] The terminal transmits the user's rating to the server.

[1336] The device sends the evaluation points to the server in JSON format or similar.

[1337] Step 10:

[1338] The server aggregates the ratings and stores them in a database.

[1339] The server tallies the evaluation points for each answer and stores them in a database.

[1340] Step 11:

[1341] The server displays the final result on the user's terminal.

[1342] The server generates the results in HTML or JSON format and sends them to the user's device. Example: The server displays the result "AI 1's 'Chameleon Rugby' wins."

[1343] Application to other creative tasks (composing music, painting, haiku, etc.)

[1344] Specific examples of composition

[1345] Step 1:

[1346] The user inputs the theme "music that evokes a summer landscape" into the terminal.

[1347] Step 2:

[1348] The device sends the input topic to the server.

[1349] Step 3:

[1350] The server stores the received questions in a database.

[1351] Step 4:

[1352] The server sends the theme to the composition AI.

[1353] Step 5:

[1354] The AI ​​generates music files and sends them to the server.

[1355] Step 6:

[1356] The server stores the generated music files in a database.

[1357] Step 7:

[1358] The server sends the music files to the user's device.

[1359] Step 8:

[1360] The user rates the generated music and inputs rating points.

[1361] Step 9:

[1362] The terminal transmits the evaluation points to the server.

[1363] Step 10:

[1364] The server compiles the evaluation results and stores them in a database.

[1365] Step 11:

[1366] The server displays the final result on the user's device. Example: The server displays the result "Music that evokes a summer landscape received a score of 9."

[1367] Examples of paintings

[1368] Step 1:

[1369] The user inputs a topic on the theme of "sea at sunset" into the terminal.

[1370] Step 2:

[1371] The device sends the input topic to the server.

[1372] Step 3:

[1373] The server stores the received questions in a database.

[1374] Step 4:

[1375] The server sends the theme to the image generation AI.

[1376] Step 5:

[1377] The AI ​​generates a painting based on the image and sends it to the server.

[1378] Step 6:

[1379] The server stores the generated painting in a database.

[1380] Step 7:

[1381] The server sends the picture file to the user's terminal.

[1382] Step 8:

[1383] The user evaluates the generated painting and inputs evaluation points.

[1384] Step 9:

[1385] The terminal transmits the evaluation points to the server.

[1386] Step 10:

[1387] The server compiles the evaluation results and stores them in a database.

[1388] Step 11:

[1389] The server displays the final result on the user's terminal. Example: The server displays the result "The painting of the sea at sunset received 8 points."

[1390] Through the above process, a system is realized that allows users to use AI in various creative tasks and receive objective evaluations in a fun way.

[1391] Example 1

[1392] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1393] Existing AI systems generate creative answers and works based on user-entered topics, and the process of evaluating them is complex and difficult to carry out efficiently. Furthermore, there is no mechanism in place for reviewing the evaluation results later, making it difficult to conduct transparent and objective evaluations.

[1394] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1395] In this invention, the server includes means for inputting a theme from a user's communication device and transmitting the theme to the server device, means for storing the theme received by the server device in a storage device, means for sharing the stored theme with multiple information processing devices and generating answers based on it, means for transmitting the generated answers to the user's communication device, means for the user to input evaluation points for each answer from the communication device and transmit the evaluations to the server device, and means for the server device to tally up the evaluations received and display the results on the user's communication device. This enables users to efficiently input themes, generate creative answers and works based on them, and refer to the evaluation results transparently and objectively.

[1396] A "user" is an entity that uses the system to input a topic and evaluate the generated answers and works.

[1397] A "communication device" is a terminal used by a user, such as a computer or smartphone, that can connect to the Internet.

[1398] "Server device" refers to a centralized computer system that receives topics and ratings from users and processes that data.

[1399] "Storage device" refers to hardware that has a database or other data storage function connected to a server device.

[1400] "Information processing device" refers to a system that includes artificial intelligence to generate creative answers and works based on a given theme.

[1401] A "topic" refers to a prompt that a user enters and the AI ​​generates a creative answer or piece of work based on it.

[1402] "Evaluation points" refer to the evaluation value entered by the user for the generated answer or work.

[1403] "Generated answer" refers to a creative output generated by an information processing device (AI) based on input (topic) from a user.

[1404] "Evaluation results" refers to information that indicates which answers or works are superior, calculated by tallying up the evaluation points entered by users.

[1405] "Transparency and objectivity" refers to the characteristics of managing and displaying user-entered ratings and generated results fairly and clearly throughout the system.

[1406] The present invention relates to a system in which a user inputs a theme, an artificial intelligence generates creative answers and works based on the theme, and the user evaluates them. Hereinafter, embodiments of the present invention will be described in detail.

[1407] Enter and save the topic

[1408] A user uses a communication device (e.g., a computer or a smartphone) to access a dedicated interface. This interface has a text box where the user can input a topic. For example, the topic could be "Please think of a name for a new sport." The communication device then transmits the topic to a server device. The server device analyzes the received topic and stores it in a storage device (e.g., a database).

[1409] Generate answers

[1410] The server device retrieves the theme stored in the storage device periodically or based on a trigger event. Then, it sends this theme to multiple information processing devices (artificial intelligence models). For example, it sends the theme to a natural language generation AI (e.g., GPT-3) or an image generation AI (e.g., DALL-E). These information processing devices then generate answers or artwork based on the theme.

[1411] An example of a prompt for a natural language generation AI is "Come up with a name for a new sport."

[1412] An example of a prompt for the image generation AI is "Please draw a picture of the sea at sunset."

[1413] Collecting and submitting responses

[1414] The server device receives the responses generated by each information processing device, aggregates them, and then transmits the aggregated responses to the user's communication device, where the user can view the responses through the interface of the communication device.

[1415] Evaluating answers

[1416] The user can use the communication device to input evaluation points for each answer. For example, the user inputs 8 points for the answer "chameleon rugby" and 6 points for the answer "bound basket." The evaluation points are transmitted from the communication device to the server device.

[1417] Calculation and display of evaluation results

[1418] The server device stores the received evaluation points in a storage device and tally up the evaluation results. The tally up results are displayed on the communication device in a format that is easy for the user to understand. For example, the result displayed may be "AI 1's 'Chameleon Rugby' wins."

[1419] Application to other creative tasks

[1420] This system can be applied not only to Ogiri but also to other creative tasks such as composing music, painting, and generating text.

[1421] Composition examples

[1422] The user inputs "music that evokes a summer landscape" as a theme. The server device sends this theme to the composition AI, which then generates a music file. The generated music file is then sent to the user's communication device, and the user evaluates the music.

[1423] Painting examples

[1424] The user inputs a theme such as "sea at sunset." The server device sends the theme to the image generation AI, which then generates a painting. The generated painting is then sent to the user's communication device, and the user evaluates the painting.

[1425] In this way, users can evaluate various creative tasks with the help of artificial intelligence, and enjoy the creative process. The system also stores the evaluation results in a storage device and makes them available for later reference, enabling transparent and objective evaluation.

[1426] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1427] Step 1:

[1428] The user enters a topic

[1429] The user accesses a dedicated interface on the communication device and inputs a topic into the text box. As an example, consider the topic "Please think of a name for a new sport." When the user clicks the "Send" button, the device accepts this input data.

[1430] Input: User-entered question

[1431] Output: A data packet containing the question

[1432] Step 2:

[1433] The device sends the topic to the server

[1434] The device sends the topic entered by the user to the server as an HTTP request (POST request). The request includes the topic text and the user ID.

[1435] Input: Data packet containing the question

[1436] Output: HTTP request to the server

[1437] Step 3:

[1438] The server saves the topic in a database

[1439] The server parses the received HTTP request, extracts the question text and the user ID, and stores this information in a database using an SQL query.

[1440] Input: HTTP request to the server

[1441] Output: Insert operation into the database

[1442] Step 4:

[1443] The server sends the theme to each information processing device.

[1444] The server retrieves the topics stored in the database periodically or upon trigger events and sends them as prompts to multiple information processing devices (artificial intelligence models). For example, it sends topics to a natural language generation AI and an image generation AI.

[1445] Input: Questions stored in the database

[1446] Output: Prompt to each information processing device

[1447] Step 5:

[1448] Each information processing device generates an answer

[1449] Each AI generates an answer based on the prompt. For example, a natural language generation AI might generate the answer "chameleon rugby," while an image generation AI might generate an image with an "ocean" theme.

[1450] Input: Prompt to each information processing device

[1451] Output: Generated answers and works

[1452] Step 6:

[1453] The server collects the answers and sends them to the user's device.

[1454] The server receives the responses from the information processing devices, compiles them, and sends them to the user's terminal, usually as an HTTP response.

[1455] Input: Generated answers and works

[1456] Output: HTTP response to the user's device

[1457] Step 7:

[1458] Users rate the answers

[1459] The user uses the interface on the communication device to input evaluation points for each answer, for example, a user might input 8 points for "chameleon rugby" and 6 points for "bound basket."

[1460] Input: Generated answers and works

[1461] Output: Rating points

[1462] Step 8:

[1463] The device sends the rating to the server

[1464] The terminal receives the evaluation points from the user and sends them to the server as an HTTP request (POST request). The request includes the evaluation points for each answer and the user ID.

[1465] Input: Rating points

[1466] Output: HTTP request to the server

[1467] Step 9:

[1468] The server aggregates the ratings and stores them in a database

[1469] The server parses the received reputation points and stores them in a database, using an SQL query to store the reputation points for each answer.

[1470] Input: HTTP request to the server

[1471] Output: Insert operation into the database

[1472] Step 10:

[1473] The server displays the evaluation results on the user's device.

[1474] The server aggregates the evaluation results and sends them as an HTTP response to the user's device for display. For example, it sends the result "AI 1's 'Chameleon Rugby' wins."

[1475] Input: Reputation points stored in the database

[1476] Output: HTTP response to the user's device

[1477] (Application example 1)

[1478] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1479] There is a need to use artificial intelligence to improve the quality of content generated based on user-entered topics, and to efficiently evaluate that content and store it in a reusable format. Conventional systems have issues with making effective use of user evaluation results and being unable to handle a wide range of creative tasks.

[1480] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1481] In this invention, the server includes means for inputting a theme from a user's information processing device and transmitting the theme to the data processing device, means for storing the theme received by the data processing device in a storage device, means for sharing the stored theme with multiple intelligent processing devices and generating answers based on the theme, means for transmitting the generated answers to the user's information processing device, means for the user to input points for each answer from the information processing device and transmit the evaluation to the data processing device, means for aggregating the received evaluations by the data processing device and displaying the results on the user's information processing device, means for storing the generated content together with the evaluation points in a database so that the data processing device can later refer to it, means for the intelligent processing device to generate content such as text, images, music, and video based on the theme input by the user, means for the user to evaluate the generated content and transmit the evaluation points from the information processing device to the data processing device, and means for the data processing device to aggregate the evaluation results and display them on the user's information processing device. This makes it possible to effectively utilize the user's evaluation results, respond to a wide range of creative tasks, and generate and evaluate high-quality content.

[1482] An "information processing device" is a device that has the function of processing, transmitting, and receiving data input by a user.

[1483] A "data processing device" is a device that receives data sent from a user and stores and aggregates the data.

[1484] A "storage device" is a device that records data and keeps it accessible when needed.

[1485] An "intelligent processing device" is a device that includes artificial intelligence to generate answers and content based on a given topic.

[1486] "Generated content" refers to creative output such as text, images, music, and video generated by an intelligent processing device based on a theme entered by a user.

[1487] "Evaluation points" are numerical values ​​of evaluations given to generated content by users.

[1488] A "database" is a system that stores data in an organized manner and manages it so that necessary information can be retrieved efficiently.

[1489] The term "topic" refers to a sentence or command that indicates an instruction or request from a user regarding the content that the user wants the intelligent processing device to generate.

[1490] This invention is a system in which a user inputs a theme from an information processing device, an intelligent processing device is used to generate creative content based on the theme, and the generated content is evaluated. The details of this system are described below.

[1491] System Configuration

[1492] The system mainly consists of the following components:

[1493] User's information processing device (smartphone, tablet, etc.)

[1494] Data processing device (cloud server, etc.)

[1495] Intelligent Processing Units (devices containing generative AI models)

[1496] Storage devices (databases, etc.)

[1497] The specific hardware and software used

[1498] Hardware:

[1499] Cloud servers (e.g. AWS EC2 instances)

[1500] Smartphones (e.g. iOS / Android devices)

[1501] software:

[1502] Natural language processing AI (e.g. GPT-3)

[1503] Image generation AI (e.g. DALL-E)

[1504] Music generation AI (e.g. Amper Music)

[1505] Database management system (e.g. MySQL)

[1506] Program processing flow

[1507] 1. Enter your topic and submit

[1508] A user inputs a topic using an information processing device. The topic is written in natural language.

[1509] Example: Enter the subject as "Draw a cityscape of the future."

[1510] 2. Receiving and saving the topic

[1511] The data processing device receives the theme sent by the user and stores it in a storage device.

[1512] 3. Sharing topics and creating content

[1513] The theme stored in the storage device is shared with multiple intelligent processing devices, and each intelligent processing device generates content based on the theme.

[1514] Examples: Natural language processing AI generates text, image generation AI generates images, and music generation AI generates music.

[1515] Example prompt: "Create an image of a futuristic city landscape with flying cars and skyscrapers."

[1516] 4. Submitting and Displaying Content

[1517] The content generated by the intelligent processing device is transmitted to the data processing device and distributed to the user's information processing device.

[1518] 5. Content Rating

[1519] A user gives evaluation points to content generated using an information processing device, and the evaluation points are transmitted to the data processing device.

[1520] 6. Calculation and display of evaluation results

[1521] The data processing device tallies the received evaluation points and displays the results on the user's information processing device.

[1522] Adding specific examples

[1523] A user inputs a theme, "Please create music that evokes the image of a summer landscape," into an information processing device.

[1524] The data processing device sends this theme to the music generation AI, and the generated music is stored in a storage device and distributed to the user's information processing device.

[1525] The user rates the generated music and the rating points are transmitted to the data processing device.

[1526] The data processing device compiles the evaluation results, stores them in a storage device for future reference, and notifies the user.

[1527] This system allows users to generate and evaluate high-quality content based on a topic they input.

[1528] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1529] Step 1:

[1530] A user inputs a topic using an information processing device and sends the topic to the server. The topic is input using natural language, specifically a prompt such as "Please draw a picture of a future cityscape." This input data is sent to the server.

[1531] Step 2:

[1532] The server stores the received topic in a database (storage device). In this process, the topic data sent by the user is received and stored in the appropriate table in the database.

[1533] Step 3:

[1534] The server shares the topics stored in the storage device with multiple intelligent processing devices. Specifically, it sends the stored topics to different intelligent processing devices, such as natural language processing AI, image generation AI, and music generation AI. The server formats the topics so that each intelligent processing device can generate appropriate content.

[1535] Step 4:

[1536] Each intelligent processing device generates content based on a given theme. For example, a natural language processing AI generates sentences, an image generation AI generates images, and a music generation AI generates music. For the prompt "Please draw a futuristic cityscape," the image generation AI processes it as "Create an image of a futuristic city landscape with flying cars and skyscrapers."

[1537] Step 5:

[1538] The generated content is sent from each intelligent processing device to a server, which receives the generated content data and sends it to the user's information processing device, i.e., collects the generated text, images, music, etc. and provides them to the user.

[1539] Step 6:

[1540] The user inputs evaluation points for the content generated by the information processing device. For example, the user assigns evaluation points such as "9 points" to the generated image. This evaluation point data is sent to the server.

[1541] Step 7:

[1542] The server aggregates the received evaluation points. Specifically, it aggregates the evaluation points sent by multiple users and generates statistical data such as the average score and the highest score.

[1543] Step 8:

[1544] The results of the counting are sent from the server to the user's information processing device and displayed to the user. Specifically, the results are displayed in a format such as "The average rating for this content is 8.5 points."

[1545] Step 9:

[1546] The generated content and the evaluation results are stored in a database by the server. For future reference, the generated content along with the evaluation points are stored in a storage device and can be accessed by users or other processing devices.

[1547] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1548] This invention provides a system in which a user inputs a theme from a terminal, an artificial intelligence generates answers and works based on that theme, and the user evaluates them, in addition to a system that combines an emotion engine that recognizes the user's emotions. Below, the program processing of the system of the present invention will be explained in natural language, with concrete examples.

[1549] Program processing overview

[1550] Register a topic

[1551] 1. The user enters a topic from the device.

[1552] For example, a user may input the topic "Come up with a name for a new sport."

[1553] 2. The device sends the entered topic to the server.

[1554] 3. The server stores the received questions in a database.

[1555] Generate answers

[1556] 1. The server shares the saved topics with multiple AIs.

[1557] The server sends a task to each AI using APIs and modifiers. For example, it sends a request to the ChatGPT API.

[1558] 2. Each AI generates an answer based on the topic.

[1559] Each AI uses its own natural language processing algorithm to generate answers. For example, ChatGPT generates the answer "Chameleon Rugby."

[1560] 3. The server collects the answers from each AI.

[1561] The server processes the API responses of each AI and stores them in a database.

[1562] 4. The server sends the answer to the user's device.

[1563] The server sends a list of answers to the user's terminal.

[1564] Evaluating answers

[1565] 1. The user enters evaluation points for each AI's answers and works from their device.

[1566] For example, a user gives "chameleon rugby" an 8-point rating and "bound basket" a 6-point rating.

[1567] 2. The device sends the user's evaluation points to the server.

[1568] 3. The server aggregates the received ratings and stores them in a database.

[1569] 4. The server displays the evaluation results on the user's device.

[1570] For example, the server might display the result "AI 1's 'Chameleon Rugby' wins."

[1571] Applying the Emotion Engine

[1572] The system incorporates an emotion engine that recognizes the user's emotions and provides appropriate feedback and adjustments based on those emotions.

[1573] 1. When a user enters a topic on their device, the emotion engine collects emotional data from the user's facial expressions, voice, and text.

[1574] Example: When a user types "Think of a name for a new sport," facial expression and voice data are captured from the camera and microphone.

[1575] 2. The emotion engine analyzes the emotion data and recognizes the user's current emotional state.

[1576] Example: The emotion engine detects emotions such as "enjoyed" or "troubled" from the user's facial expressions and voice.

[1577] 3. The server filters the questions and generated answers based on data from the emotion engine.

[1578] Example: If a user is having trouble, prioritize displaying questions with low difficulty and simple answers.

[1579] 4. The server influences the user's evaluation points with the emotional data.

[1580] Example: If a user is having a lot of fun, the evaluation points are adjusted to be positive.

[1581] 5. The server stores the evaluation results, including emotional data, in a database so that they can be referenced later.

[1582] Example: Recording a user's emotional state so that the relationship between that data and rating points can be analyzed later.

[1583] Specific examples

[1584] Ogiri using an emotional engine

[1585] 1. The user enters the topic, "Look at a picture of a cat and say one thing."

[1586] 2. The emotion engine detects the user's "smile."

[1587] 3. The server uses the emotional data to prioritize and display more humorous answers.

[1588] 4. The AI-generated answer, "This cat is making its modeling debut!" will be displayed.

[1589] 5. If the user gives it a high rating, it will be stored in the database along with the emotional data.

[1590] Composing with an Emotion Engine

[1591] 1. The user enters the theme "a song that evokes a gentle landscape."

[1592] 2. The emotion engine detects the user's "relaxed" state.

[1593] 3. The composition AI will then generate a relaxing, calming song based on that.

[1594] 4. The server sends the generated song to the user's device.

[1595] 5. The user rates the generated song highly, and the emotional data is saved as a rating.

[1596] In this way, by effectively utilizing the user's emotional data, a system can be realized that can provide a more personalized experience.

[1597] The processing flow will be explained below.

[1598] Specific processing flow of the invention that combines the emotion engine

[1599] Register a topic

[1600] Step 1:

[1601] The user inputs a topic from the terminal.

[1602] Example: A user enters the topic "Think of a name for a new sport."

[1603] Step 2:

[1604] The device sends the input topic to the server.

[1605] The device sends the topic to the server using an HTTP request.

[1606] Step 3:

[1607] The server stores the topics in a database.

[1608] The server saves the topic in the database using an INSERT query.

[1609] Emotion recognition

[1610] Step 4:

[1611] The terminal acquires the user's emotion data.

[1612] The device's camera and microphone are used to collect the user's facial expressions and voice data.

[1613] Step 5:

[1614] The terminal transmits emotion data to the emotion engine.

[1615] The device transmits emotion data to the emotion engine in real time.

[1616] Step 6:

[1617] The emotion engine analyzes the emotion data and recognizes the user's emotional state.

[1618] Example: An emotion engine detects emotions such as "enjoyed" or "troubled."

[1619] Generate answers

[1620] Step 7:

[1621] The server shares the saved topics with multiple AIs.

[1622] The server sends a task to each AI using APIs and modifiers. For example, it sends a request to the ChatGPT API.

[1623] Step 8:

[1624] AI generates answers based on the topic.

[1625] Each AI uses its own natural language processing algorithm to generate answers. For example, ChatGPT generates the answer "Chameleon Rugby."

[1626] Step 9:

[1627] The server collects the responses from each AI.

[1628] The server processes the API responses of each AI and stores them in a database.

[1629] Step 10:

[1630] The server filters the answers and works based on data from the emotion engine.

[1631] Example: If a user is having trouble, prioritize displaying questions with low difficulty and simple answers.

[1632] Step 11:

[1633] The server sends the filtered response to the user's terminal.

[1634] The server sends a list of answers to the user's terminal.

[1635] Evaluating answers

[1636] Step 12:

[1637] The user inputs evaluation points for each AI's answers and works from the device.

[1638] Users enter points from 1 to 10 for each answer using a slider or input box.

[1639] Step 13:

[1640] The terminal transmits the evaluation points to the server.

[1641] The device sends the evaluation points to the server in JSON format or similar.

[1642] Step 14:

[1643] The server aggregates the received ratings and adjusts points as necessary based on emotional data.

[1644] Example: If a user is having a lot of fun, the evaluation points are adjusted to be positive.

[1645] Step 15:

[1646] The server stores the evaluation results in a database.

[1647] The server stores the evaluation points and emotion data for each answer in a database.

[1648] Step 16:

[1649] The server displays the final result on the user's terminal.

[1650] The server generates the results in HTML or JSON format and sends them to the user's device. Example: The server displays the result "AI 1's 'Chameleon Rugby' wins."

[1651] Specific examples

[1652] Ogiri using an emotional engine

[1653] Step 1:

[1654] The user inputs the topic "Say one thing when you look at a picture of a cat."

[1655] Step 2:

[1656] The device sends the input topic to the server.

[1657] Step 3:

[1658] The server stores the topics in a database.

[1659] Step 4:

[1660] The terminal acquires the user's facial expression data using a camera.

[1661] Step 5:

[1662] The device sends the facial expression data to the emotion engine.

[1663] Step 6:

[1664] The emotion engine analyzes the transmitted data and detects the user's "smile."

[1665] Step 7:

[1666] The server sends the topic to multiple AIs, which generate answers.

[1667] Step 8:

[1668] The AI ​​generates the answer "This cat is making its modeling debut!" and sends it to the server.

[1669] Step 9:

[1670] The server collects the responses and filters them based on the sentiment data.

[1671] Step 10:

[1672] The server sends the filtered response to the user's terminal.

[1673] Step 11:

[1674] The user gives a high rating of 8 points to the answer "This cat is making her modeling debut!"

[1675] Step 12:

[1676] The terminal transmits the evaluation points to the server.

[1677] Step 13:

[1678] The server makes corrections based on the evaluation points and emotion data and stores the results in a database.

[1679] Step 14:

[1680] The server displays the final result, "AI 1's 'This cat is a model!' wins" on the user's device.

[1681] In this way, by effectively utilizing the user's emotional data, a system can be realized that can provide a more personalized experience.

[1682] Example 2

[1683] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1684] In conventional creative tasks, systems existed that generated and evaluated answers to user-provided questions, but they lacked a mechanism to consider the user's emotional state. As a result, users were often dissatisfied with answers or questions that did not match their emotions. Furthermore, because the evaluation results did not incorporate emotional data, the accuracy of the evaluation and the improvement of the user experience were not fully realized.

[1685] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1686] In this invention, the server includes means including an emotion engine that collects user emotion data, means for filtering questions and answers based on the emotion data, and means for correcting evaluation points using the emotion data, thereby making it possible to provide questions and answers that suit the user's emotions and to reflect the emotion data in the evaluation results.

[1687] A "user" is a person who uses the system to input questions and evaluate generated answers.

[1688] A "terminal" is a device operated by a user, which provides an interface for input and evaluation.

[1689] The "server" is a computer system that receives questions, stores them, shares them with the AI, collects answers, and compiles evaluations.

[1690] A "topic" is a question or theme that a user enters through a device, and is the basis for the AI ​​to generate an answer.

[1691] The "database" is a system for storing the questions received by the server, the answers generated, and the user's evaluation points.

[1692] "Artificial intelligence (AI)" is a program that generates answers based on questions provided by users.

[1693] An "answer" is an output result generated by the artificial intelligence based on a topic provided by the user.

[1694] "Evaluation points" are numerical values ​​that are given to a user to evaluate a generated answer.

[1695] An "emotion engine" is a system that recognizes a user's emotional state and collects and analyzes that data.

[1696] "Emotional Data" is information about a user's emotional state that is collected and analyzed by the emotion engine.

[1697] "Filtering" is a process of adjusting the priority of the questions and generated answers based on emotional data.

[1698] "Correction of evaluation points" is a process of modifying evaluation points based on the user's emotion data.

[1699] This invention uses artificial intelligence to generate answers based on topics entered by users, and improves the performance of the entire system based on the user's evaluations and emotional data. This system is realized by combining users, terminals, servers, an emotional engine, and artificial intelligence (AI).

[1700] First, the user inputs a topic using a device. This device refers to hardware (smartphone, tablet, PC, etc.) that runs software such as a web browser or mobile app. For example, the user might input a topic in text format, such as "Please think of a name for a new sport." This input data is sent from the device to the server. At this time, the device converts the topic into JSON format and sends it to the server via an HTTP POST request. This process transmits the user's topic to the server.

[1701] The server stores the received questions in a database (e.g., MongoDB). The stored questions are shared with various artificial intelligences (generative AI models). The server sends the questions to each AI's API, and each AI generates an answer using its own natural language processing algorithm. For example, if the server sends a request to ChatGPT's API saying, "Please think of a name for a new sport," ChatGPT generates the answer "Chameleon Rugby."

[1702] Next, the server collects the answers from each AI and sends them to the user's device. These answers are displayed on the user's device, and the user enters evaluation points for each answer. The evaluation points are again sent from the device to the server, which tallies them and stores the evaluation results in a database. The tallied results are then displayed on the user's device. For example, if a user rates "Chameleon Rugby" as 8 points and "Bounce Basket" as 6 points, the server tallies these and displays a result such as "AI 1's 'Chameleon Rugby' wins."

[1703] Furthermore, the system incorporates an emotion engine. When a user inputs a topic from their device, the emotion engine uses a camera and microphone to collect facial and voice data and analyze the user's emotional state. From the analysis results, the engine recognizes emotions such as "enjoying" or "struggling," and filters the topics and generated answers based on this emotional data. For example, if the server recognizes that the user is struggling, it will prioritize displaying topics with low difficulty and simple answers. Furthermore, evaluation points are also adjusted based on the user's emotional state. As a result, the system stores the user's evaluation points and emotional data in a database for later analysis.

[1704] For example, if a user inputs the topic "Say something when you look at a photo of a cat," and the emotion engine detects a "smile," the server will prioritize humorous responses, such as "This cat is ready to make its debut as a model!" If the user gives a high rating, the rating and emotion data are saved in the database.

[1705] In addition, if a user inputs a theme of "a song that evokes a gentle landscape" and the emotion engine detects a "relaxed" state, the composition AI will generate a relaxing, calm song, which will be sent to the user's device. The user can then rate the generated song highly, and their emotional data will be saved as a rating. The system is similarly configured to handle other creative tasks, such as composing music, painting, and haiku poetry.

[1706] In this way, the present invention is a system that can effectively utilize a user's emotional data to provide a more personalized experience.

[1707] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1708] Step 1:

[1709] The user inputs a topic from the terminal.

[1710] Input: A user types "Think of a new sport name" into an input field in a web browser or app.

[1711] Data processing: The terminal converts the user input into JSON format.

[1712] Output: The generated JSON data.

[1713] Specific operation: The user presses the "Submit" button to send the topic to the server.

[1714] Step 2:

[1715] The device sends the input topic to the server.

[1716] Input: JSON data generated on the terminal.

[1717] Data operation: Send an HTTP POST request to the server.

[1718] Output: The topic data sent to the server.

[1719] Specific operation: The device sends an HTTP POST request to the " / submit_topic" endpoint.

[1720] Step 3:

[1721] The server stores the received questions in a database.

[1722] Input: The question data received by the server.

[1723] Data processing: Insert the received data into the database.

[1724] Output: The questions stored in the database.

[1725] Specific operation: The server stores the subject data in a NoSQL database such as MongoDB.

[1726] Step 4:

[1727] The server shares the saved topics with each AI's API.

[1728] Input: A question stored in the database.

[1729] Data processing: Generate requests corresponding to each AI's API.

[1730] Output: The requests sent to each AI.

[1731] Specific operation: The server sends a request to an API endpoint such as ChatGPT.

[1732] Step 5:

[1733] Each AI receives a question from the server and generates an answer.

[1734] Input: The topic requests received by each AI.

[1735] Data Computing: Uses natural language processing algorithms to generate answers.

[1736] Output: The generated answer.

[1737] Specific operation: AI such as ChatGPT generates answers such as "Chameleon Rugby."

[1738] Step 6:

[1739] The server collects the responses from each AI and sends them to the user's device.

[1740] Input: The answers generated by each AI.

[1741] Data processing: Compile the answers into a list.

[1742] Output: The answer list sent to the user's device.

[1743] Specific operation: The server converts the answer list into JSON format and sends it to the specified endpoint on the user's device.

[1744] Step 7:

[1745] The user inputs evaluation points for each AI's answer from the terminal.

[1746] Input: Rating points entered by the user.

[1747] Data processing: Convert the evaluation points into JSON format.

[1748] Output: JSON data of the evaluation points.

[1749] Specific operation: The user enters a score in the evaluation form and presses the "Submit" button.

[1750] Step 8:

[1751] The terminal transmits the evaluation points to the server.

[1752] Input: JSON data of the rating points entered by the user.

[1753] Data operation: Send an HTTP POST request to the server.

[1754] Output: The rating data sent to the server.

[1755] Specific operation: The device sends an HTTP POST request to the " / submit_evaluation" endpoint.

[1756] Step 9:

[1757] The server tallies the received evaluation points and stores them in a database.

[1758] Input: The rating data received by the server.

[1759] Data processing: The evaluation data is inserted into the database.

[1760] Output: Evaluation results stored in a database.

[1761] Specific operation: The server aggregates the evaluation data and stores it in a database.

[1762] Step 10:

[1763] The server displays the evaluation results on the user's terminal.

[1764] Input: Evaluation results stored in a database.

[1765] Data processing: The evaluation results are formatted and sent to the user's terminal.

[1766] Output: Evaluation results displayed on the user's terminal.

[1767] Specific operation: The server converts the evaluation results into JSON format and sends the evaluation results, such as "AI 1's 'Chameleon Rugby' wins," to the user device.

[1768] Step 11:

[1769] When a user inputs a topic from the device, the emotion engine collects the user's facial expressions and voice data.

[1770] Input: User's facial and voice data.

[1771] Data calculation: The emotion engine generates emotion data using facial expression recognition algorithms and voice analysis algorithms.

[1772] Output: The generated emotion data.

[1773] Specific operation: The device's camera and microphone will automatically start up and capture the user's facial expressions and voice.

[1774] Step 12:

[1775] The emotion engine analyzes the emotion data and recognizes the user's emotional state.

[1776] Input: Collected facial and voice data.

[1777] Data calculation: The emotion engine analyzes the collected data and classifies it as "enjoying" or "troubled."

[1778] Output: Parsed emotional state data.

[1779] Specific operation: The emotion engine performs facial expression recognition and voice analysis to identify the user's emotions.

[1780] Step 13:

[1781] The server filters the questions and answers based on emotional data.

[1782] Input: Parsed emotional state data.

[1783] Data processing: Execute filtering logic to select questions and answers.

[1784] Output: Questions and answers after filtering.

[1785] Specific operation: The server prioritizes displaying easy questions and simple answers depending on the user's emotional state.

[1786] Step 14:

[1787] The server corrects the evaluation points using the emotion data.

[1788] Input: Rating points and sentiment data.

[1789] Data calculation: Apply a positive correction to the evaluation points.

[1790] Output: Corrected rating points.

[1791] Specific operation: The server adjusts the rating points based on the user's emotional state.

[1792] Step 15:

[1793] The server stores the emotion data and evaluation results in a database, making them available for later reference.

[1794] Input: Emotion data and evaluation results.

[1795] Data processing: The emotion data and evaluation results are inserted into the database.

[1796] Output: Emotion data and evaluation results stored in a database.

[1797] Specific operation: The server stores the emotion data and evaluation results in a database so that they can be analyzed at a later date.

[1798] (Application example 2)

[1799] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1800] In conventional incident management systems, operators can report incident details and AI can suggest countermeasures, but it is difficult to provide value-added feedback or appropriate countermeasures that take into account the operator's emotional state. Furthermore, there is no system that collects and analyzes operator emotional data and provides filtering or appropriate countermeasures based on that data, so there is a lack of means to reduce operator stress and fatigue. This has led to issues such as a decline in the efficiency and quality of incident response.

[1801] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for inputting a topic from a user's terminal and transmitting the topic to the server; means for storing the topic received by the server in a database; means for sharing the stored topic with multiple artificial intelligences and generating answers based on the topics; means for transmitting the generated answers to the user's terminal; means for collecting and analyzing emotion data from the user's terminal, an emotion engine for analyzing the emotion data; means for filtering the generated answers based on the collected emotion data; and means for providing appropriate feedback based on the operator's emotion data. This enables added-value incident management, such as presenting incident response measures that take the operator's emotional state into consideration and managing operator stress.

[1802] A "user" is someone who uses the system to input questions and receive generated answers.

[1803] A "terminal" is a device used by a user, such as a smartphone or tablet.

[1804] A "topic" is a request or task entered by a user, based on which an answer is generated.

[1805] A "server" is a device or system that receives topics sent from a user's terminal, stores them, and shares them with multiple artificial intelligences.

[1806] A "database" is a storage device for storing questions received by the server and answers generated by the server.

[1807] "Artificial intelligence" is a program or system that generates answers based on input questions.

[1808] An "answer" is the output generated by the artificial intelligence based on the topic.

[1809] The "emotion engine" is a system for collecting and analyzing emotional data such as a user's facial expressions and voice.

[1810] "Filtering" is the process of adjusting the display order and content of generated answers based on collected emotional data.

[1811] "Feedback" refers to information or instructions provided to a user, with appropriate content presented based on their emotional state.

[1812] "Incident" means a security occurrence or problem reported by an Operator.

[1813] To implement this invention, a user inputs a topic from a terminal and sends the topic to a server. The server stores the received topic in a database and shares the stored topics with multiple AIs. Each AI generates an answer based on the topic, and the generated answer is sent back to the user's terminal via the server. This system includes an emotion engine that collects and analyzes emotion data from the user's terminal. Based on the collected emotion data, the generated answers are filtered and appropriate feedback is provided to the user.

[1814] Hardware and software used

[1815] Hardware:

[1816] Smartphone / tablet: A device where users can enter incident information and collect emotional data.

[1817] Camera: Used to collect facial expression data from the user.

[1818] Microphone: Used to collect user voice data.

[1819] software:

[1820] Python: Used as the main programming language.

[1821] EmotionRecognition (facial_emotion_recognition): An emotion recognition library for analyzing user facial expressions.

[1822] TextBlob: A natural language processing library for analyzing sentiment in text data.

[1823] Requests: An HTTP request library for sending and receiving data between the server and the device.

[1824] Data processing and calculation

[1825] The server first receives incident information from the user's device and stores it in a database. The stored questions are then shared with multiple AIs, which then generate answers based on the information. The answers are then sent back to the user's device via the server.

[1826] The emotion engine collects and analyzes the user's facial expressions and voice data in real time. The analyzed emotion data recognizes the user's current emotional state and filters the content and display order of the generated answers based on that. As a result, appropriate feedback can be provided to the user.

[1827] Specific examples

[1828] 1. Incident Reporting:

[1829] Users use their smartphones to report incidents such as "suspicious people loitering around the building."

[1830] 2. Generate answers:

[1831] The server stores reported incident information in a database and shares it with multiple artificial intelligence systems.

[1832] Each AI system generates the answer, "Contact the police and save the surveillance camera footage."

[1833] 3. Applying the Emotion Engine:

[1834] When a user reports an incident, the device's camera and microphone are used to collect the user's emotional data.

[1835] If the emotion engine analyzes and determines that the user is feeling very stressed, filtering will provide feedback such as "take a five-minute break."

[1836] Prompt Sentence Examples

[1837] Think of a name for a new sport.

[1838] "Look at a picture of a cat and say something"

[1839] "A song that evokes a gentle landscape"

[1840] In this way, by effectively utilizing user emotional data, it is possible to provide a more personalized experience and improve the efficiency of stress management for operators.

[1841] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1842] Step 1:

[1843] The user enters details of the incident on their smartphone or tablet, including a description of the incident and its location. For example, a user might enter "a suspicious person is loitering around the building," and this data is sent from the device to the server.

[1844] Step 2:

[1845] The server stores the incident information it receives in a database. Input data includes incident descriptions and location information, which are stored in the database as structured data. This data is then used for analysis and the generation of countermeasures.

[1846] Step 3:

[1847] The server shares the saved incident information with multiple AI systems. The server sends API requests to each AI system to provide the incident information. Each AI system generates countermeasures and advice based on this information.

[1848] Step 4:

[1849] Each AI generates a response to the incident. For example, it generates a specific response such as "contact the police and save the surveillance camera footage" in response to the incident information. This generated data is sent to the server.

[1850] Step 5:

[1851] The server collects the responses from each AI and sends them to the user's device. The server then sends the collected response data to the user's device in an appropriate format, allowing the user to view multiple countermeasures.

[1852] Step 6:

[1853] The user's device collects emotional data using a camera and microphone. While entering incident information, the user's facial expressions and voice data are captured and analyzed by the emotion engine. The emotion engine identifies the user's emotional state from their facial expressions and voice.

[1854] Step 7:

[1855] The emotion engine sends the analysis results to the server. The emotion engine then sends the analyzed user's emotion data (e.g., stress state, relaxed state, etc.) to the server. This data reflects the user's emotional state.

[1856] Step 8:

[1857] The server filters the generated answers based on emotion data and provides appropriate feedback. For example, if the user is feeling extremely stressed, the server displays additional feedback such as "Take a 5-minute break."

[1858] Step 9:

[1859] The server provides filtered answers and feedback to the user, allowing the user to receive not only appropriate responses but also feedback that takes into account their emotional state at the time.

[1860] Step 10:

[1861] The user inputs an evaluation of the generated answer and the provided feedback. The user assigns points based on whether the provided solution was effective or whether the feedback was useful. This evaluation data is sent back to the server.

[1862] Step 11:

[1863] The server collects the evaluation data and stores it in a database, along with additional information such as evaluation points and emotional data, and uses this data to improve the quality of incident response and optimize feedback.

[1864] Through these steps, incident response and effective feedback are achieved that take into account the user's emotional state.

[1865] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1866] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1867] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1868] [Fourth embodiment]

[1869] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1870] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1871] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1872] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1873] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1874] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1875] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1876] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1877] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1878] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1879] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1880] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1881] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1882] This invention provides a system in which a user inputs a theme from a terminal, an artificial intelligence generates answers and works based on the theme, and the user then evaluates them. Below, the program processing of the system of the present invention is explained in natural language, with specific examples.

[1883] Program processing overview

[1884] Register a topic

[1885] 1. The user enters a topic from the device.

[1886] For example, a user may input the topic "Come up with a name for a new sport."

[1887] 2. The device sends the entered topic to the server.

[1888] 3. The server stores the received topic in a database.

[1889] Generate answers

[1890] 1. The server shares the saved topics with multiple AIs.

[1891] For example, the server sends a topic to different AI engines (such as natural language generation AI and image generation AI).

[1892] 2. Each AI generates an answer based on the topic.

[1893] An example would be a natural language generation AI generating the answer "chameleon rugby."

[1894] The image generation AI generates paintings based on the theme of "the sea."

[1895] 3. The server collects the answers and creations from each AI and sends them to the user's device.

[1896] Evaluating answers

[1897] 1. The user enters evaluation points for each AI's answers and works from their device.

[1898] For example, a user may give "chameleon rugby" an 8-point rating and "bound basket" a 6-point rating.

[1899] 2. The device sends the user's evaluation points to the server.

[1900] 3. The server aggregates the received ratings and stores them in a database.

[1901] 4. The server displays the evaluation results on the user's device.

[1902] For example, display the result "AI 1's 'Chameleon Rugby' wins."

[1903] Responding to other creative tasks

[1904] This system can be applied not only to Ogiri but also to other creative tasks (composing music, painting, haiku, etc.). Specific examples are shown below.

[1905] 1. Composition Examples

[1906] The user inputs the theme "music that evokes a summer landscape" into the terminal.

[1907] The server sends the theme to the composition AI.

[1908] The composition AI generates music files and sends them to the server.

[1909] The server transmits the generated music file to the user's terminal.

[1910] The user rates the generated music and transmits the rating points from the terminal to the server.

[1911] The server compiles the evaluation results and displays them on the user's device.

[1912] 2. Examples of paintings

[1913] The user inputs a topic on the theme of "sea at sunset" into the terminal.

[1914] The server sends the theme to the image generation AI.

[1915] The image generation AI generates a painting based on the image and sends it to the server.

[1916] The server transmits the generated painting to the user's terminal.

[1917] The user evaluates the generated painting and transmits the evaluation points from the terminal to the server.

[1918] The server compiles the evaluation results and displays them on the user's device.

[1919] In this way, users can evaluate various creative tasks with the help of AI, and enjoy the creative process. The system stores the evaluation results in a database and makes them available for future reference, enabling transparent and objective evaluation.

[1920] The processing flow will be explained below.

[1921] Specific process flow for generating and evaluating answers to Ogiri topics

[1922] Register a topic

[1923] Step 1:

[1924] The user inputs a topic from the terminal.

[1925] Example: A user enters the topic "Think of a name for a new sport."

[1926] Step 2:

[1927] The device sends the input topic to the server.

[1928] The device sends the topic to the server using an HTTP request.

[1929] Step 3:

[1930] The server stores the topics in a database.

[1931] The server saves the topic in the database using an INSERT query.

[1932] Generate answers

[1933] Step 4:

[1934] The server shares the saved topics with multiple AIs.

[1935] The server sends a task to each AI using APIs and modifiers. For example, it sends a request to the ChatGPT API.

[1936] Step 5:

[1937] AI generates answers based on the topic.

[1938] Each AI uses its own natural language processing algorithm to generate answers. For example, ChatGPT generates the answer "Chameleon Rugby."

[1939] Step 6:

[1940] The server collects the responses from each AI.

[1941] The server processes the API responses of each AI and stores them in a database.

[1942] Step 7:

[1943] The server sends the response to the user's terminal.

[1944] The server sends a list of answers to the user's terminal.

[1945] Evaluating answers

[1946] Step 8:

[1947] The user inputs evaluation points for each AI's answer from the terminal.

[1948] Users enter points from 1 to 10 for each answer using a slider or input box.

[1949] Step 9:

[1950] The terminal transmits the user's rating to the server.

[1951] The device sends the evaluation points to the server in JSON format or similar.

[1952] Step 10:

[1953] The server aggregates the ratings and stores them in a database.

[1954] The server tallies the evaluation points for each answer and stores them in a database.

[1955] Step 11:

[1956] The server displays the final result on the user's terminal.

[1957] The server generates the results in HTML or JSON format and sends them to the user's device. Example: The server displays the result "AI 1's 'Chameleon Rugby' wins."

[1958] Application to other creative tasks (composing music, painting, haiku, etc.)

[1959] Specific examples of composition

[1960] Step 1:

[1961] The user inputs the theme "music that evokes a summer landscape" into the terminal.

[1962] Step 2:

[1963] The device sends the input topic to the server.

[1964] Step 3:

[1965] The server stores the received questions in a database.

[1966] Step 4:

[1967] The server sends the theme to the composition AI.

[1968] Step 5:

[1969] The AI ​​generates music files and sends them to the server.

[1970] Step 6:

[1971] The server stores the generated music files in a database.

[1972] Step 7:

[1973] The server sends the music files to the user's device.

[1974] Step 8:

[1975] The user rates the generated music and inputs rating points.

[1976] Step 9:

[1977] The terminal transmits the evaluation points to the server.

[1978] Step 10:

[1979] The server compiles the evaluation results and stores them in a database.

[1980] Step 11:

[1981] The server displays the final result on the user's device. Example: The server displays the result "Music that evokes a summer landscape received a score of 9."

[1982] Examples of paintings

[1983] Step 1:

[1984] The user inputs a topic on the theme of "sea at sunset" into the terminal.

[1985] Step 2:

[1986] The device sends the input topic to the server.

[1987] Step 3:

[1988] The server stores the received questions in a database.

[1989] Step 4:

[1990] The server sends the theme to the image generation AI.

[1991] Step 5:

[1992] The AI ​​generates a painting based on the image and sends it to the server.

[1993] Step 6:

[1994] The server stores the generated painting in a database.

[1995] Step 7:

[1996] The server sends the picture file to the user's terminal.

[1997] Step 8:

[1998] The user evaluates the generated painting and inputs evaluation points.

[1999] Step 9:

[2000] The terminal transmits the evaluation points to the server.

[2001] Step 10:

[2002] The server compiles the evaluation results and stores them in a database.

[2003] Step 11:

[2004] The server displays the final result on the user's terminal. Example: The server displays the result "The painting of the sea at sunset received 8 points."

[2005] Through the above process, a system is realized that allows users to use AI in various creative tasks and receive objective evaluations in a fun way.

[2006] Example 1

[2007] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2008] Existing AI systems generate creative answers and works based on user-entered topics, and the process of evaluating them is complex and difficult to carry out efficiently. Furthermore, there is no mechanism in place for reviewing the evaluation results later, making it difficult to conduct transparent and objective evaluations.

[2009] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[2010] In this invention, the server includes means for inputting a theme from a user's communication device and transmitting the theme to the server device, means for storing the theme received by the server device in a storage device, means for sharing the stored theme with multiple information processing devices and generating answers based on it, means for transmitting the generated answers to the user's communication device, means for the user to input evaluation points for each answer from the communication device and transmit the evaluations to the server device, and means for the server device to tally up the evaluations received and display the results on the user's communication device. This enables users to efficiently input themes, generate creative answers and works based on them, and refer to the evaluation results transparently and objectively.

[2011] A "user" is an entity that uses the system to input a topic and evaluate the generated answers and works.

[2012] A "communication device" is a terminal used by a user, such as a computer or smartphone, that can connect to the Internet.

[2013] "Server device" refers to a centralized computer system that receives topics and ratings from users and processes that data.

[2014] "Storage device" refers to hardware that has a database or other data storage function connected to a server device.

[2015] "Information processing device" refers to a system that includes artificial intelligence to generate creative answers and works based on a given theme.

[2016] A "topic" refers to a prompt that a user enters and the AI ​​generates a creative answer or piece of work based on it.

[2017] "Evaluation points" refer to the evaluation value entered by the user for the generated answer or work.

[2018] "Generated answer" refers to a creative output generated by an information processing device (AI) based on input (topic) from a user.

[2019] "Evaluation results" refers to information that indicates which answers or works are superior, calculated by tallying up the evaluation points entered by users.

[2020] "Transparency and objectivity" refers to the characteristics of managing and displaying user-entered ratings and generated results fairly and clearly throughout the system.

[2021] The present invention relates to a system in which a user inputs a theme, an artificial intelligence generates creative answers and works based on the theme, and the user evaluates them. Hereinafter, embodiments of the present invention will be described in detail.

[2022] Enter and save the topic

[2023] A user uses a communication device (e.g., a computer or a smartphone) to access a dedicated interface. This interface has a text box where the user can input a topic. For example, the topic could be "Please think of a name for a new sport." The communication device then transmits the topic to a server device. The server device analyzes the received topic and stores it in a storage device (e.g., a database).

[2024] Generate answers

[2025] The server device retrieves the theme stored in the storage device periodically or based on a trigger event. Then, it sends this theme to multiple information processing devices (artificial intelligence models). For example, it sends the theme to a natural language generation AI (e.g., GPT-3) or an image generation AI (e.g., DALL-E). These information processing devices then generate answers or artwork based on the theme.

[2026] An example of a prompt for a natural language generation AI is "Come up with a name for a new sport."

[2027] An example of a prompt for the image generation AI is "Please draw a picture of the sea at sunset."

[2028] Collecting and submitting responses

[2029] The server device receives the responses generated by each information processing device, aggregates them, and then transmits the aggregated responses to the user's communication device, where the user can view the responses through the interface of the communication device.

[2030] Evaluating answers

[2031] The user can use the communication device to input evaluation points for each answer. For example, the user inputs 8 points for the answer "chameleon rugby" and 6 points for the answer "bound basket." The evaluation points are transmitted from the communication device to the server device.

[2032] Calculation and display of evaluation results

[2033] The server device stores the received evaluation points in a storage device and tally up the evaluation results. The tally up results are displayed on the communication device in a format that is easy for the user to understand. For example, the result displayed may be "AI 1's 'Chameleon Rugby' wins."

[2034] Application to other creative tasks

[2035] This system can be applied not only to Ogiri but also to other creative tasks such as composing music, painting, and generating text.

[2036] Composition examples

[2037] The user inputs "music that evokes a summer landscape" as a theme. The server device sends this theme to the composition AI, which then generates a music file. The generated music file is then sent to the user's communication device, and the user evaluates the music.

[2038] Painting examples

[2039] The user inputs a theme such as "sea at sunset." The server device sends the theme to the image generation AI, which then generates a painting. The generated painting is then sent to the user's communication device, and the user evaluates the painting.

[2040] In this way, users can evaluate various creative tasks with the help of artificial intelligence, and enjoy the creative process. The system also stores the evaluation results in a storage device and makes them available for later reference, enabling transparent and objective evaluation.

[2041] The flow of the identification process in the first embodiment will be described with reference to FIG.

[2042] Step 1:

[2043] The user enters a topic

[2044] The user accesses a dedicated interface on the communication device and inputs a topic into the text box. As an example, consider the topic "Please think of a name for a new sport." When the user clicks the "Send" button, the device accepts this input data.

[2045] Input: User-entered question

[2046] Output: A data packet containing the question

[2047] Step 2:

[2048] The device sends the topic to the server

[2049] The device sends the topic entered by the user to the server as an HTTP request (POST request). The request includes the topic text and the user ID.

[2050] Input: Data packet containing the question

[2051] Output: HTTP request to the server

[2052] Step 3:

[2053] The server saves the topic in a database

[2054] The server parses the received HTTP request, extracts the question text and the user ID, and stores this information in a database using an SQL query.

[2055] Input: HTTP request to the server

[2056] Output: Insert operation into the database

[2057] Step 4:

[2058] The server sends the theme to each information processing device.

[2059] The server retrieves the topics stored in the database periodically or upon trigger events and sends them as prompts to multiple information processing devices (artificial intelligence models). For example, it sends topics to a natural language generation AI and an image generation AI.

[2060] Input: Questions stored in the database

[2061] Output: Prompt to each information processing device

[2062] Step 5:

[2063] Each information processing device generates an answer

[2064] Each AI generates an answer based on the prompt. For example, a natural language generation AI might generate the answer "chameleon rugby," while an image generation AI might generate an image with an "ocean" theme.

[2065] Input: Prompt to each information processing device

[2066] Output: Generated answers and works

[2067] Step 6:

[2068] The server collects the answers and sends them to the user's device.

[2069] The server receives the responses from the information processing devices, compiles them, and sends them to the user's terminal, usually as an HTTP response.

[2070] Input: Generated answers and works

[2071] Output: HTTP response to the user's device

[2072] Step 7:

[2073] Users rate the answers

[2074] The user uses the interface on the communication device to input evaluation points for each answer, for example, a user might input 8 points for "chameleon rugby" and 6 points for "bound basket."

[2075] Input: Generated answers and works

[2076] Output: Rating points

[2077] Step 8:

[2078] The device sends the rating to the server

[2079] The terminal receives the evaluation points from the user and sends them to the server as an HTTP request (POST request). The request includes the evaluation points for each answer and the user ID.

[2080] Input: Rating points

[2081] Output: HTTP request to the server

[2082] Step 9:

[2083] The server aggregates the ratings and stores them in a database

[2084] The server parses the received reputation points and stores them in a database, using an SQL query to store the reputation points for each answer.

[2085] Input: HTTP request to the server

[2086] Output: Insert operation into the database

[2087] Step 10:

[2088] The server displays the evaluation results on the user's device.

[2089] The server aggregates the evaluation results and sends them as an HTTP response to the user's device for display. For example, it sends the result "AI 1's 'Chameleon Rugby' wins."

[2090] Input: Reputation points stored in the database

[2091] Output: HTTP response to the user's device

[2092] (Application example 1)

[2093] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2094] There is a need to use artificial intelligence to improve the quality of content generated based on user-entered topics, and to efficiently evaluate that content and store it in a reusable format. Conventional systems have issues with making effective use of user evaluation results and being unable to handle a wide range of creative tasks.

[2095] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[2096] In this invention, the server includes means for inputting a theme from a user's information processing device and transmitting the theme to the data processing device, means for storing the theme received by the data processing device in a storage device, means for sharing the stored theme with multiple intelligent processing devices and generating answers based on the theme, means for transmitting the generated answers to the user's information processing device, means for the user to input points for each answer from the information processing device and transmit the evaluation to the data processing device, means for aggregating the received evaluations by the data processing device and displaying the results on the user's information processing device, means for storing the generated content together with the evaluation points in a database so that the data processing device can later refer to it, means for the intelligent processing device to generate content such as text, images, music, and video based on the theme input by the user, means for the user to evaluate the generated content and transmit the evaluation points from the information processing device to the data processing device, and means for the data processing device to aggregate the evaluation results and display them on the user's information processing device. This makes it possible to effectively utilize the user's evaluation results, respond to a wide range of creative tasks, and generate and evaluate high-quality content.

[2097] An "information processing device" is a device that has the function of processing, transmitting, and receiving data input by a user.

[2098] A "data processing device" is a device that receives data sent from a user and stores and aggregates the data.

[2099] A "storage device" is a device that records data and keeps it accessible when needed.

[2100] An "intelligent processing device" is a device that includes artificial intelligence to generate answers and content based on a given topic.

[2101] "Generated content" refers to creative output such as text, images, music, and video generated by an intelligent processing device based on a theme entered by a user.

[2102] "Evaluation points" are numerical values ​​of evaluations given to generated content by users.

[2103] A "database" is a system that stores data in an organized manner and manages it so that necessary information can be retrieved efficiently.

[2104] The term "topic" refers to a sentence or command that indicates an instruction or request from a user regarding the content that the user wants the intelligent processing device to generate.

[2105] This invention is a system in which a user inputs a theme from an information processing device, an intelligent processing device is used to generate creative content based on the theme, and the generated content is evaluated. The details of this system are described below.

[2106] System Configuration

[2107] The system mainly consists of the following components:

[2108] User's information processing device (smartphone, tablet, etc.)

[2109] Data processing device (cloud server, etc.)

[2110] Intelligent Processing Units (devices containing generative AI models)

[2111] Storage devices (databases, etc.)

[2112] The specific hardware and software used

[2113] Hardware:

[2114] Cloud servers (e.g. AWS EC2 instances)

[2115] Smartphones (e.g. iOS / Android devices)

[2116] software:

[2117] Natural language processing AI (e.g. GPT-3)

[2118] Image generation AI (e.g. DALL-E)

[2119] Music generation AI (e.g. Amper Music)

[2120] Database management system (e.g. MySQL)

[2121] Program processing flow

[2122] 1. Enter your topic and submit

[2123] A user inputs a topic using an information processing device. The topic is written in natural language.

[2124] Example: Enter the subject as "Draw a cityscape of the future."

[2125] 2. Receiving and saving the topic

[2126] The data processing device receives the theme sent by the user and stores it in a storage device.

[2127] 3. Sharing topics and creating content

[2128] The theme stored in the storage device is shared with multiple intelligent processing devices, and each intelligent processing device generates content based on the theme.

[2129] Examples: Natural language processing AI generates text, image generation AI generates images, and music generation AI generates music.

[2130] Example prompt: "Create an image of a futuristic city landscape with flying cars and skyscrapers."

[2131] 4. Submitting and Displaying Content

[2132] The content generated by the intelligent processing device is transmitted to the data processing device and distributed to the user's information processing device.

[2133] 5. Content Rating

[2134] A user gives evaluation points to content generated using an information processing device, and the evaluation points are transmitted to the data processing device.

[2135] 6. Calculation and display of evaluation results

[2136] The data processing device tallies the received evaluation points and displays the results on the user's information processing device.

[2137] Adding specific examples

[2138] A user inputs a theme, "Please create music that evokes the image of a summer landscape," into an information processing device.

[2139] The data processing device sends this theme to the music generation AI, and the generated music is stored in a storage device and distributed to the user's information processing device.

[2140] The user rates the generated music and the rating points are transmitted to the data processing device.

[2141] The data processing device compiles the evaluation results, stores them in a storage device for future reference, and notifies the user.

[2142] This system allows users to generate and evaluate high-quality content based on a topic they input.

[2143] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2144] Step 1:

[2145] A user inputs a topic using an information processing device and sends the topic to the server. The topic is input using natural language, specifically a prompt such as "Please draw a picture of a future cityscape." This input data is sent to the server.

[2146] Step 2:

[2147] The server stores the received topic in a database (storage device). In this process, the topic data sent by the user is received and stored in the appropriate table in the database.

[2148] Step 3:

[2149] The server shares the topics stored in the storage device with multiple intelligent processing devices. Specifically, it sends the stored topics to different intelligent processing devices, such as natural language processing AI, image generation AI, and music generation AI. The server formats the topics so that each intelligent processing device can generate appropriate content.

[2150] Step 4:

[2151] Each intelligent processing device generates content based on a given theme. For example, a natural language processing AI generates sentences, an image generation AI generates images, and a music generation AI generates music. For the prompt "Please draw a futuristic cityscape," the image generation AI processes it as "Create an image of a futuristic city landscape with flying cars and skyscrapers."

[2152] Step 5:

[2153] The generated content is sent from each intelligent processing device to a server, which receives the generated content data and sends it to the user's information processing device, i.e., collects the generated text, images, music, etc. and provides them to the user.

[2154] Step 6:

[2155] The user inputs evaluation points for the content generated by the information processing device. For example, the user assigns evaluation points such as "9 points" to the generated image. This evaluation point data is sent to the server.

[2156] Step 7:

[2157] The server aggregates the received evaluation points. Specifically, it aggregates the evaluation points sent by multiple users and generates statistical data such as the average score and the highest score.

[2158] Step 8:

[2159] The results of the counting are sent from the server to the user's information processing device and displayed to the user. Specifically, the results are displayed in a format such as "The average rating for this content is 8.5 points."

[2160] Step 9:

[2161] The generated content and the evaluation results are stored in a database by the server. For future reference, the generated content along with the evaluation points are stored in a storage device and can be accessed by users or other processing devices.

[2162] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[2163] This invention provides a system in which a user inputs a theme from a terminal, an artificial intelligence generates answers and works based on that theme, and the user evaluates them, in addition to a system that combines an emotion engine that recognizes the user's emotions. Below, the program processing of the system of the present invention will be explained in natural language, with concrete examples.

[2164] Program processing overview

[2165] Register a topic

[2166] 1. The user enters a topic from the device.

[2167] For example, a user may input the topic "Come up with a name for a new sport."

[2168] 2. The device sends the entered topic to the server.

[2169] 3. The server stores the received questions in a database.

[2170] Generate answers

[2171] 1. The server shares the saved topics with multiple AIs.

[2172] The server sends a task to each AI using APIs and modifiers. For example, it sends a request to the ChatGPT API.

[2173] 2. Each AI generates an answer based on the topic.

[2174] Each AI uses its own natural language processing algorithm to generate answers. For example, ChatGPT generates the answer "Chameleon Rugby."

[2175] 3. The server collects the answers from each AI.

[2176] The server processes the API responses of each AI and stores them in a database.

[2177] 4. The server sends the answer to the user's device.

[2178] The server sends a list of answers to the user's terminal.

[2179] Evaluating answers

[2180] 1. The user enters evaluation points for each AI's answers and works from their device.

[2181] For example, a user gives "chameleon rugby" an 8-point rating and "bound basket" a 6-point rating.

[2182] 2. The device sends the user's evaluation points to the server.

[2183] 3. The server aggregates the received ratings and stores them in a database.

[2184] 4. The server displays the evaluation results on the user's device.

[2185] For example, the server might display the result "AI 1's 'Chameleon Rugby' wins."

[2186] Applying the Emotion Engine

[2187] The system incorporates an emotion engine that recognizes the user's emotions and provides appropriate feedback and adjustments based on those emotions.

[2188] 1. When a user enters a topic on their device, the emotion engine collects emotional data from the user's facial expressions, voice, and text.

[2189] Example: When a user types "Think of a name for a new sport," facial expression and voice data are captured from the camera and microphone.

[2190] 2. The emotion engine analyzes the emotion data and recognizes the user's current emotional state.

[2191] Example: The emotion engine detects emotions such as "enjoyed" or "troubled" from the user's facial expressions and voice.

[2192] 3. The server filters the questions and generated answers based on data from the emotion engine.

[2193] Example: If a user is having trouble, prioritize displaying questions with low difficulty and simple answers.

[2194] 4. The server influences the user's evaluation points with the emotional data.

[2195] Example: If a user is having a lot of fun, the evaluation points are adjusted to be positive.

[2196] 5. The server stores the evaluation results, including emotional data, in a database so that they can be referenced later.

[2197] Example: Recording a user's emotional state so that the relationship between that data and rating points can be analyzed later.

[2198] Specific examples

[2199] Ogiri using an emotional engine

[2200] 1. The user enters the topic, "Look at a picture of a cat and say one thing."

[2201] 2. The emotion engine detects the user's "smile."

[2202] 3. The server uses the emotional data to prioritize and display more humorous answers.

[2203] 4. The AI-generated answer, "This cat is making its modeling debut!" will be displayed.

[2204] 5. If the user gives it a high rating, it will be stored in the database along with the emotional data.

[2205] Composing with an Emotion Engine

[2206] 1. The user enters the theme "a song that evokes a gentle landscape."

[2207] 2. The emotion engine detects the user's "relaxed" state.

[2208] 3. The composition AI will then generate a relaxing, calming song based on that.

[2209] 4. The server sends the generated song to the user's device.

[2210] 5. The user rates the generated song highly, and the emotional data is saved as a rating.

[2211] In this way, by effectively utilizing the user's emotional data, a system can be realized that can provide a more personalized experience.

[2212] The processing flow will be explained below.

[2213] Specific processing flow of the invention that combines the emotion engine

[2214] Register a topic

[2215] Step 1:

[2216] The user inputs a topic from the terminal.

[2217] Example: A user enters the topic "Think of a name for a new sport."

[2218] Step 2:

[2219] The device sends the input topic to the server.

[2220] The device sends the topic to the server using an HTTP request.

[2221] Step 3:

[2222] The server stores the topics in a database.

[2223] The server saves the topic in the database using an INSERT query.

[2224] Emotion recognition

[2225] Step 4:

[2226] The terminal acquires the user's emotion data.

[2227] The device's camera and microphone are used to collect the user's facial expressions and voice data.

[2228] Step 5:

[2229] The terminal transmits emotion data to the emotion engine.

[2230] The device transmits emotion data to the emotion engine in real time.

[2231] Step 6:

[2232] The emotion engine analyzes the emotion data and recognizes the user's emotional state.

[2233] Example: An emotion engine detects emotions such as "enjoyed" or "troubled."

[2234] Generate answers

[2235] Step 7:

[2236] The server shares the saved topics with multiple AIs.

[2237] The server sends a task to each AI using APIs and modifiers. For example, it sends a request to the ChatGPT API.

[2238] Step 8:

[2239] AI generates answers based on the topic.

[2240] Each AI uses its own natural language processing algorithm to generate answers. For example, ChatGPT generates the answer "Chameleon Rugby."

[2241] Step 9:

[2242] The server collects the responses from each AI.

[2243] The server processes the API responses of each AI and stores them in a database.

[2244] Step 10:

[2245] The server filters the answers and works based on data from the emotion engine.

[2246] Example: If a user is having trouble, prioritize displaying questions with low difficulty and simple answers.

[2247] Step 11:

[2248] The server sends the filtered response to the user's terminal.

[2249] The server sends a list of answers to the user's terminal.

[2250] Evaluating answers

[2251] Step 12:

[2252] The user inputs evaluation points for each AI's answers and works from the device.

[2253] Users enter points from 1 to 10 for each answer using a slider or input box.

[2254] Step 13:

[2255] The terminal transmits the evaluation points to the server.

[2256] The device sends the evaluation points to the server in JSON format or similar.

[2257] Step 14:

[2258] The server aggregates the received ratings and adjusts points as necessary based on emotional data.

[2259] Example: If a user is having a lot of fun, the evaluation points are adjusted to be positive.

[2260] Step 15:

[2261] The server stores the evaluation results in a database.

[2262] The server stores the evaluation points and emotion data for each answer in a database.

[2263] Step 16:

[2264] The server displays the final result on the user's terminal.

[2265] The server generates the results in HTML or JSON format and sends them to the user's device. Example: The server displays the result "AI 1's 'Chameleon Rugby' wins."

[2266] Specific examples

[2267] Ogiri using an emotional engine

[2268] Step 1:

[2269] The user inputs the topic "Say one thing when you look at a picture of a cat."

[2270] Step 2:

[2271] The device sends the input topic to the server.

[2272] Step 3:

[2273] The server stores the topics in a database.

[2274] Step 4:

[2275] The terminal acquires the user's facial expression data using a camera.

[2276] Step 5:

[2277] The device sends the facial expression data to the emotion engine.

[2278] Step 6:

[2279] The emotion engine analyzes the transmitted data and detects the user's "smile."

[2280] Step 7:

[2281] The server sends the topic to multiple AIs, which generate answers.

[2282] Step 8:

[2283] The AI ​​generates the answer "This cat is making its modeling debut!" and sends it to the server.

[2284] Step 9:

[2285] The server collects the responses and filters them based on the sentiment data.

[2286] Step 10:

[2287] The server sends the filtered response to the user's terminal.

[2288] Step 11:

[2289] The user gives a high rating of 8 points to the answer "This cat is making her modeling debut!"

[2290] Step 12:

[2291] The terminal transmits the evaluation points to the server.

[2292] Step 13:

[2293] The server makes corrections based on the evaluation points and emotion data and stores the results in a database.

[2294] Step 14:

[2295] The server displays the final result, "AI 1's 'This cat is a model!' wins" on the user's device.

[2296] In this way, by effectively utilizing the user's emotional data, a system can be realized that can provide a more personalized experience.

[2297] Example 2

[2298] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2299] In conventional creative tasks, systems existed that generated and evaluated answers to user-provided questions, but they lacked a mechanism to consider the user's emotional state. As a result, users were often dissatisfied with answers or questions that did not match their emotions. Furthermore, because the evaluation results did not incorporate emotional data, the accuracy of the evaluation and the improvement of the user experience were not fully realized.

[2300] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[2301] In this invention, the server includes means including an emotion engine that collects user emotion data, means for filtering questions and answers based on the emotion data, and means for correcting evaluation points using the emotion data, thereby making it possible to provide questions and answers that suit the user's emotions and to reflect the emotion data in the evaluation results.

[2302] A "user" is a person who uses the system to input questions and evaluate generated answers.

[2303] A "terminal" is a device operated by a user, which provides an interface for input and evaluation.

[2304] The "server" is a computer system that receives questions, stores them, shares them with the AI, collects answers, and compiles evaluations.

[2305] A "topic" is a question or theme that a user enters through a device, and is the basis for the AI ​​to generate an answer.

[2306] The "database" is a system for storing the questions received by the server, the answers generated, and the user's evaluation points.

[2307] "Artificial intelligence (AI)" is a program that generates answers based on questions provided by users.

[2308] An "answer" is an output result generated by the artificial intelligence based on a topic provided by the user.

[2309] "Evaluation points" are numerical values ​​that are given to a user to evaluate a generated answer.

[2310] An "emotion engine" is a system that recognizes a user's emotional state and collects and analyzes that data.

[2311] "Emotional Data" is information about a user's emotional state that is collected and analyzed by the emotion engine.

[2312] "Filtering" is a process of adjusting the priority of the questions and generated answers based on emotional data.

[2313] "Correction of evaluation points" is a process of modifying evaluation points based on the user's emotion data.

[2314] This invention uses artificial intelligence to generate answers based on topics entered by users, and improves the performance of the entire system based on the user's evaluations and emotional data. This system is realized by combining users, terminals, servers, an emotional engine, and artificial intelligence (AI).

[2315] First, the user inputs a topic using a device. This device refers to hardware (smartphone, tablet, PC, etc.) that runs software such as a web browser or mobile app. For example, the user might input a topic in text format, such as "Please think of a name for a new sport." This input data is sent from the device to the server. At this time, the device converts the topic into JSON format and sends it to the server via an HTTP POST request. This process transmits the user's topic to the server.

[2316] The server stores the received questions in a database (e.g., MongoDB). The stored questions are shared with various artificial intelligences (generative AI models). The server sends the questions to each AI's API, and each AI generates an answer using its own natural language processing algorithm. For example, if the server sends a request to ChatGPT's API saying, "Please think of a name for a new sport," ChatGPT generates the answer "Chameleon Rugby."

[2317] Next, the server collects the answers from each AI and sends them to the user's device. These answers are displayed on the user's device, and the user enters evaluation points for each answer. The evaluation points are again sent from the device to the server, which tallies them and stores the evaluation results in a database. The tallied results are then displayed on the user's device. For example, if a user rates "Chameleon Rugby" as 8 points and "Bounce Basket" as 6 points, the server tallies these and displays a result such as "AI 1's 'Chameleon Rugby' wins."

[2318] Furthermore, the system incorporates an emotion engine. When a user inputs a topic from their device, the emotion engine uses a camera and microphone to collect facial and voice data and analyze the user's emotional state. From the analysis results, the engine recognizes emotions such as "enjoying" or "struggling," and filters the topics and generated answers based on this emotional data. For example, if the server recognizes that the user is struggling, it will prioritize displaying topics with low difficulty and simple answers. Furthermore, evaluation points are also adjusted based on the user's emotional state. As a result, the system stores the user's evaluation points and emotional data in a database for later analysis.

[2319] For example, if a user inputs the topic "Say something when you look at a photo of a cat," and the emotion engine detects a "smile," the server will prioritize humorous responses, such as "This cat is ready to make its debut as a model!" If the user gives a high rating, the rating and emotion data are saved in the database.

[2320] In addition, if a user inputs a theme of "a song that evokes a gentle landscape" and the emotion engine detects a "relaxed" state, the composition AI will generate a relaxing, calm song, which will be sent to the user's device. The user can then rate the generated song highly, and their emotional data will be saved as a rating. The system is similarly configured to handle other creative tasks, such as composing music, painting, and haiku poetry.

[2321] In this way, the present invention is a system that can effectively utilize a user's emotional data to provide a more personalized experience.

[2322] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2323] Step 1:

[2324] The user inputs a topic from the terminal.

[2325] Input: A user types "Think of a new sport name" into an input field in a web browser or app.

[2326] Data processing: The terminal converts the user input into JSON format.

[2327] Output: The generated JSON data.

[2328] Specific operation: The user presses the "Submit" button to send the topic to the server.

[2329] Step 2:

[2330] The device sends the input topic to the server.

[2331] Input: JSON data generated on the terminal.

[2332] Data operation: Send an HTTP POST request to the server.

[2333] Output: The topic data sent to the server.

[2334] Specific operation: The device sends an HTTP POST request to the " / submit_topic" endpoint.

[2335] Step 3:

[2336] The server stores the received questions in a database.

[2337] Input: The question data received by the server.

[2338] Data processing: Insert the received data into the database.

[2339] Output: The questions stored in the database.

[2340] Specific operation: The server stores the subject data in a NoSQL database such as MongoDB.

[2341] Step 4:

[2342] The server shares the saved topics with each AI's API.

[2343] Input: A question stored in the database.

[2344] Data processing: Generate requests corresponding to each AI's API.

[2345] Output: The requests sent to each AI.

[2346] Specific operation: The server sends a request to an API endpoint such as ChatGPT.

[2347] Step 5:

[2348] Each AI receives a question from the server and generates an answer.

[2349] Input: The topic requests received by each AI.

[2350] Data Computing: Uses natural language processing algorithms to generate answers.

[2351] Output: The generated answer.

[2352] Specific operation: AI such as ChatGPT generates answers such as "Chameleon Rugby."

[2353] Step 6:

[2354] The server collects the responses from each AI and sends them to the user's device.

[2355] Input: The answers generated by each AI.

[2356] Data processing: Compile the answers into a list.

[2357] Output: The answer list sent to the user's device.

[2358] Specific operation: The server converts the answer list into JSON format and sends it to the specified endpoint on the user's device.

[2359] Step 7:

[2360] The user inputs evaluation points for each AI's answer from the terminal.

[2361] Input: Rating points entered by the user.

[2362] Data processing: Convert the evaluation points into JSON format.

[2363] Output: JSON data of the evaluation points.

[2364] Specific operation: The user enters a score in the evaluation form and presses the "Submit" button.

[2365] Step 8:

[2366] The terminal transmits the evaluation points to the server.

[2367] Input: JSON data of the rating points entered by the user.

[2368] Data operation: Send an HTTP POST request to the server.

[2369] Output: The rating data sent to the server.

[2370] Specific operation: The device sends an HTTP POST request to the " / submit_evaluation" endpoint.

[2371] Step 9:

[2372] The server tallies the received evaluation points and stores them in a database.

[2373] Input: The rating data received by the server.

[2374] Data processing: The evaluation data is inserted into the database.

[2375] Output: Evaluation results stored in a database.

[2376] Specific operation: The server aggregates the evaluation data and stores it in a database.

[2377] Step 10:

[2378] The server displays the evaluation results on the user's terminal.

[2379] Input: Evaluation results stored in a database.

[2380] Data processing: The evaluation results are formatted and sent to the user's terminal.

[2381] Output: Evaluation results displayed on the user's terminal.

[2382] Specific operation: The server converts the evaluation results into JSON format and sends the evaluation results, such as "AI 1's 'Chameleon Rugby' wins," to the user device.

[2383] Step 11:

[2384] When a user inputs a topic from the device, the emotion engine collects the user's facial expressions and voice data.

[2385] Input: User's facial and voice data.

[2386] Data calculation: The emotion engine generates emotion data using facial expression recognition algorithms and voice analysis algorithms.

[2387] Output: The generated emotion data.

[2388] Specific operation: The device's camera and microphone will automatically start up and capture the user's facial expressions and voice.

[2389] Step 12:

[2390] The emotion engine analyzes the emotion data and recognizes the user's emotional state.

[2391] Input: Collected facial and voice data.

[2392] Data calculation: The emotion engine analyzes the collected data and classifies it as "enjoying" or "troubled."

[2393] Output: Parsed emotional state data.

[2394] Specific operation: The emotion engine performs facial expression recognition and voice analysis to identify the user's emotions.

[2395] Step 13:

[2396] The server filters the questions and answers based on emotional data.

[2397] Input: Parsed emotional state data.

[2398] Data processing: Execute filtering logic to select questions and answers.

[2399] Output: Questions and answers after filtering.

[2400] Specific operation: The server prioritizes displaying easy questions and simple answers depending on the user's emotional state.

[2401] Step 14:

[2402] The server corrects the evaluation points using the emotion data.

[2403] Input: Rating points and sentiment data.

[2404] Data calculation: Apply a positive correction to the evaluation points.

[2405] Output: Corrected rating points.

[2406] Specific operation: The server adjusts the rating points based on the user's emotional state.

[2407] Step 15:

[2408] The server stores the emotion data and evaluation results in a database, making them available for later reference.

[2409] Input: Emotion data and evaluation results.

[2410] Data processing: The emotion data and evaluation results are inserted into the database.

[2411] Output: Emotion data and evaluation results stored in a database.

[2412] Specific operation: The server stores the emotion data and evaluation results in a database so that they can be analyzed at a later date.

[2413] (Application example 2)

[2414] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2415] In conventional incident management systems, operators can report incident details and AI can suggest countermeasures, but it is difficult to provide value-added feedback or appropriate countermeasures that take into account the operator's emotional state. Furthermore, there is no system that collects and analyzes operator emotional data and provides filtering or appropriate countermeasures based on that data, so there is a lack of means to reduce operator stress and fatigue. This has led to issues such as a decline in the efficiency and quality of incident response.

[2416] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for inputting a topic from a user's terminal and transmitting the topic to the server; means for storing the topic received by the server in a database; means for sharing the stored topic with multiple artificial intelligences and generating answers based on the topics; means for transmitting the generated answers to the user's terminal; means for collecting and analyzing emotion data from the user's terminal, an emotion engine for analyzing the emotion data; means for filtering the generated answers based on the collected emotion data; and means for providing appropriate feedback based on the operator's emotion data. This enables added-value incident management, such as presenting incident response measures that take the operator's emotional state into consideration and managing operator stress.

[2417] A "user" is someone who uses the system to input questions and receive generated answers.

[2418] A "terminal" is a device used by a user, such as a smartphone or tablet.

[2419] A "topic" is a request or task entered by a user, based on which an answer is generated.

[2420] A "server" is a device or system that receives topics sent from a user's terminal, stores them, and shares them with multiple artificial intelligences.

[2421] A "database" is a storage device for storing questions received by the server and answers generated by the server.

[2422] "Artificial intelligence" is a program or system that generates answers based on input questions.

[2423] An "answer" is the output generated by the artificial intelligence based on the topic.

[2424] The "emotion engine" is a system for collecting and analyzing emotional data such as a user's facial expressions and voice.

[2425] "Filtering" is the process of adjusting the display order and content of generated answers based on collected emotional data.

[2426] "Feedback" refers to information or instructions provided to a user, with appropriate content presented based on their emotional state.

[2427] "Incident" means a security occurrence or problem reported by an Operator.

[2428] To implement this invention, a user inputs a topic from a terminal and sends the topic to a server. The server stores the received topic in a database and shares the stored topics with multiple AIs. Each AI generates an answer based on the topic, and the generated answer is sent back to the user's terminal via the server. This system includes an emotion engine that collects and analyzes emotion data from the user's terminal. Based on the collected emotion data, the generated answers are filtered and appropriate feedback is provided to the user.

[2429] Hardware and software used

[2430] Hardware:

[2431] Smartphone / tablet: A device where users can enter incident information and collect emotional data.

[2432] Camera: Used to collect facial expression data from the user.

[2433] Microphone: Used to collect user voice data.

[2434] software:

[2435] Python: Used as the main programming language.

[2436] EmotionRecognition (facial_emotion_recognition): An emotion recognition library for analyzing user facial expressions.

[2437] TextBlob: A natural language processing library for analyzing sentiment in text data.

[2438] Requests: An HTTP request library for sending and receiving data between the server and the device.

[2439] Data processing and calculation

[2440] The server first receives incident information from the user's device and stores it in a database. The stored questions are then shared with multiple AIs, which then generate answers based on the information. The answers are then sent back to the user's device via the server.

[2441] The emotion engine collects and analyzes the user's facial expressions and voice data in real time. The analyzed emotion data recognizes the user's current emotional state and filters the content and display order of the generated answers based on that. As a result, appropriate feedback can be provided to the user.

[2442] Specific examples

[2443] 1. Incident Reporting:

[2444] Users use their smartphones to report incidents such as "suspicious people loitering around the building."

[2445] 2. Generate answers:

[2446] The server stores reported incident information in a database and shares it with multiple artificial intelligence systems.

[2447] Each AI system generates the answer, "Contact the police and save the surveillance camera footage."

[2448] 3. Applying the Emotion Engine:

[2449] When a user reports an incident, the device's camera and microphone are used to collect the user's emotional data.

[2450] If the emotion engine analyzes and determines that the user is feeling very stressed, filtering will provide feedback such as "take a five-minute break."

[2451] Prompt Sentence Examples

[2452] Think of a name for a new sport.

[2453] "Look at a picture of a cat and say something"

[2454] "A song that evokes a gentle landscape"

[2455] In this way, by effectively utilizing user emotional data, it is possible to provide a more personalized experience and improve the efficiency of stress management for operators.

[2456] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2457] Step 1:

[2458] The user enters details of the incident on their smartphone or tablet, including a description of the incident and its location. For example, a user might enter "a suspicious person is loitering around the building," and this data is sent from the device to the server.

[2459] Step 2:

[2460] The server stores the incident information it receives in a database. Input data includes incident descriptions and location information, which are stored in the database as structured data. This data is then used for analysis and the generation of countermeasures.

[2461] Step 3:

[2462] The server shares the saved incident information with multiple AI systems. The server sends API requests to each AI system to provide the incident information. Each AI system generates countermeasures and advice based on this information.

[2463] Step 4:

[2464] Each AI generates a response to the incident. For example, it generates a specific response such as "contact the police and save the surveillance camera footage" in response to the incident information. This generated data is sent to the server.

[2465] Step 5:

[2466] The server collects the responses from each AI and sends them to the user's device. The server then sends the collected response data to the user's device in an appropriate format, allowing the user to view multiple countermeasures.

[2467] Step 6:

[2468] The user's device collects emotional data using a camera and microphone. While entering incident information, the user's facial expressions and voice data are captured and analyzed by the emotion engine. The emotion engine identifies the user's emotional state from their facial expressions and voice.

[2469] Step 7:

[2470] The emotion engine sends the analysis results to the server. The emotion engine then sends the analyzed user's emotion data (e.g., stress state, relaxed state, etc.) to the server. This data reflects the user's emotional state.

[2471] Step 8:

[2472] The server filters the generated answers based on emotion data and provides appropriate feedback. For example, if the user is feeling extremely stressed, the server displays additional feedback such as "Take a 5-minute break."

[2473] Step 9:

[2474] The server provides filtered answers and feedback to the user, allowing the user to receive not only appropriate responses but also feedback that takes into account their emotional state at the time.

[2475] Step 10:

[2476] The user inputs an evaluation of the generated answer and the provided feedback. The user assigns points based on whether the provided solution was effective or whether the feedback was useful. This evaluation data is sent back to the server.

[2477] Step 11:

[2478] The server collects the evaluation data and stores it in a database, along with additional information such as evaluation points and emotional data, and uses this data to improve the quality of incident response and optimize feedback.

[2479] Through these steps, incident response and effective feedback are achieved that take into account the user's emotional state.

[2480] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[2481] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2482] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[2483] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[2484] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[2485] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[2486] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[2487] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[2488] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[2489] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[2490] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[2491] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[2492] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[2493] 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.

[2494] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[2495] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[2496] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[2497] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[2498] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[2499] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[2500] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[2501] The following is further disclosed regarding the above embodiment.

[2502] (Claim 1)

[2503] A means for inputting a topic from a user's terminal and transmitting the topic to a server;

[2504] A means for storing the received topics in a database;

[2505] A method for sharing saved topics with multiple AIs and generating answers based on them;

[2506] means for transmitting the generated answer to the user's terminal;

[2507] A means for a user to input points for each answer from a terminal and transmit the evaluation to a server;

[2508] a means for the server to aggregate the received ratings and display the results on the user's terminal;

[2509] A system including:

[2510] (Claim 2)

[2511] The system of claim 1 further comprising means for similarly handling other creative tasks such as composing music, painting, and writing haiku.

[2512] (Claim 3)

[2513] 2. The system according to claim 1, further comprising means for storing the evaluation results in a database so that they can be referenced later.

[2514] "Example 1"

[2515] (Claim 1)

[2516] means for inputting a theme from a user's communication device and transmitting the theme to a server device;

[2517] A means for storing the theme received by the server device in a storage device;

[2518] A means for sharing the saved topic with a plurality of information processing devices and generating an answer based on the topic;

[2519] means for transmitting the generated answer to the user's communication device;

[2520] a means for a user to input evaluation points for each answer from a communication device and transmit the evaluation to a server device;

[2521] a means for aggregating the evaluations received by the server device and displaying the results on the user's communication device;

[2522] A system including:

[2523] (Claim 2)

[2524] 10. The system of claim 1, further comprising means for similarly handling other creative tasks such as composing music, painting, and writing.

[2525] (Claim 3)

[2526] 2. The system according to claim 1, further comprising means for storing the evaluation results in a storage device so that they can be referenced later.

[2527] "Application Example 1"

[2528] (Claim 1)

[2529] means for inputting a theme from a user's information processing device and transmitting the theme to a data processing device;

[2530] means for storing the theme received by the data processing device in a storage device;

[2531] means for sharing the stored questions with a plurality of intelligent processing devices and generating answers based thereon;

[2532] means for transmitting the generated answer to the user's information processing device;

[2533] a means for a user to input points for each answer from an information processing device and transmit the evaluation to the data processing device;

[2534] means for aggregating the evaluations received by the data processing device and displaying the results on the user's information processing device;

[2535] a means for storing the generated content together with the evaluation points in a database so that the content can be later referenced by a data processing device;

[2536] means for an intelligent processing device to generate content such as text, images, music, and video based on a theme input by a user;

[2537] A means for users to rate the generated content and transmit rating points from the information processing device to the data processing device;

[2538] a means for the data processing device to compile the evaluation results and display them on the user's information processing device;

[2539] A system including:

[2540] (Claim 2)

[2541] 10. The system of claim 1, further comprising means for similarly handling other creative tasks such as composing music, painting, poetry, etc.

[2542] (Claim 3)

[2543] 2. The system according to claim 1, further comprising means for storing the evaluation results in a storage device so that they can be referenced later.

[2544] "Example 2: Combining Emotion Engines"

[2545] (Claim 1)

[2546] A means for inputting a topic from a user's terminal and transmitting the topic to a server;

[2547] A means for storing the received topics in a database;

[2548] A method for sharing saved topics with multiple AIs and generating answers based on them;

[2549] means for transmitting the generated answer to the user's terminal;

[2550] A means for a user to input points for each answer from a terminal and transmit the evaluation to a server;

[2551] a means for the server to aggregate the received ratings and display the results on the user's terminal;

[2552] means for collecting user emotion data, the emotion engine comprising:

[2553] A means to filter questions and answers based on emotional data,

[2554] A means for correcting evaluation points using emotion data;

[2555] A system including:

[2556] (Claim 2)

[2557] The system of claim 1 further comprising means for similarly handling other creative tasks such as composing music, painting, an...

Claims

1. A means for inputting a topic from a user's terminal and transmitting the topic to a server; A means for storing the received topics in a database; A method for sharing saved topics with multiple AIs and generating answers based on them; means for transmitting the generated answer to the user's terminal; A means for a user to input points for each answer from a terminal and transmit the evaluation to a server; a means for the server to aggregate the received ratings and display the results on the user's terminal; A system including:

2. 2. The system according to claim 1, further comprising means for similarly handling other creative tasks such as composing music, painting, and writing haiku.

3. 2. The system according to claim 1, further comprising means for storing the evaluation results in a database so that they can be referenced later.

Images