system

Abstract

We provide the system. [Solution] A means of querying a generative artificial intelligence, including its areas of expertise, about its specialized fields, A means for receiving answers based on the aforementioned specialized field from the aforementioned generative artificial intelligence, A means of creating the most suitable consultation content based on the aforementioned specialized field, A means for transmitting the consultation content to the generative artificial intelligence and receiving a response, A means for analyzing the aforementioned response and identifying areas for improvement, A means of executing the next cycle based on the aforementioned improvements, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Generative artificial intelligence (AI) has diverse specialized knowledge and can generate responses in various fields, but there is a problem that its utilization method is not fully optimized. In particular, since there is a lack of specific methods for a user to utilize the fields where generative AI excels to obtain the most effective responses, as a result, the potential of generative AI is not maximally utilized. The purpose of this invention is to provide a method for optimizing the process of inquiry and response using generative AI and effectively evaluating and operating the fields where it excels.

Means for Solving the Problems

[0005] The present invention solves the above problems by the following means. First, it provides a means for querying a generative artificial intelligence (AI) about its area of ​​expertise. This means allows the generative AI to identify its area of ​​expertise. Next, it provides a means for receiving a response from the generative AI based on its area of ​​expertise, and includes a means for automatically creating an optimal consultation content based on that response. This consultation content is specialized in the generative AI's area of ​​expertise. Furthermore, it provides a means for sending the consultation content to the generative AI and receiving its response. It includes a means for analyzing this response, identifying areas for improvement, and providing feedback to improve the consultation content in the next cycle. This provides a process for maximizing the generative AI's area of ​​expertise and obtaining an optimal response.

[0006] "Generative artificial intelligence" refers to artificial intelligence that has the ability to learn from diverse data and generate new information and responses.

[0007] "Specialized fields" refer to specific areas of knowledge or technology in which generative artificial intelligence is considered to excel.

[0008] "Means of inquiry" refers to methods and processes for asking and confirming the areas of expertise of a generative artificial intelligence.

[0009] "Means of receiving responses" refers to methods and systems for obtaining responses from generative artificial intelligence regarding specialized fields.

[0010] "Means for creating consultation content" refers to methods and processes for designing and generating optimal consultation content based on the strengths of generative artificial intelligence.

[0011] "Means of receiving responses" refers to methods and systems for receiving answers and information provided by generative artificial intelligence.

[0012] "Means of analyzing responses to identify areas for improvement" refers to methods and processes for analyzing responses received from generative artificial intelligence to identify areas for improvement and useful feedback for the next cycle.

[0013] "Means of executing the next cycle" refers to the methods and processes for making the next inquiry or consultation to the generative artificial intelligence based on the previous response and analysis results. [Brief explanation of the drawing]

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

Embodiments for Carrying Out the Invention

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

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

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

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

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

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

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

[0022] [First Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0035] This invention is a system utilizing generative artificial intelligence (AI), and its purpose is to implement a PDCA cycle to optimally utilize the strengths of generative AI, which is constantly evolving. The specific configuration, operation, and series of processes of the system are described below.

[0036] System Configuration

[0037] 1. User terminal

[0038] It is a computer or mobile device used by a user to operate a system.

[0039] Inquiries and consultations are sent from the user's terminal to the generative AI.

[0040] 2. Server

[0041] It is a cloud-based or local server that works in conjunction with generative AI to analyze inquiries and responses in its area of ​​expertise, and identify areas for improvement.

[0042] The server is equipped with a program to access the generative AI API.

[0043] Program processing

[0044] 1. Initialization

[0045] The user creates an instance of the AI ​​assistant and sets the necessary API key.

[0046] 2. Selection of areas of expertise

[0047] The server sends a query to the generative AI asking about its areas of expertise.

[0048] The generative AI responds by returning a response related to its area of ​​expertise (for example, "natural language processing").

[0049] The server records this response and uses it in the next step.

[0050] 3. Refine the details of the consultation.

[0051] The server automatically generates appropriate consultation content for the generative AI based on its area of ​​expertise.

[0052] For example, if your area of ​​expertise is "natural language processing," you would create a consultation request such as, "What is the optimal technique for natural language processing?"

[0053] 4. Implementing the content of the consultation

[0054] The user terminal sends the generated consultation content to the generative AI.

[0055] The generative AI will provide a response to this inquiry.

[0056] The server receives and records the response.

[0057] 5. Analysis of results and creation of improvement plans

[0058] The server analyzes the response from the generative AI and identifies areas for improvement.

[0059] For example, you could come up with a plan to improve by saying, "Next time, I'll ask questions that include specific technical examples."

[0060] These improvement suggestions will be implemented in the next cycle.

[0061] Specific example

[0062] scenario:

[0063] Users want to use generative AI to find the optimal method for generating text.

[0064] 1. Initialization

[0065] The user initializes the AI ​​assistant and sets the API key.

[0066] ai_assistant = AIAssistant(api_key="your_api_key_here")

[0067] 2. Selection of areas of expertise

[0068] The server sends a query to the generative AI: "What are your specializations?"

[0069] The generative AI responded, "I'm good at natural language processing."

[0070] The server records its areas of expertise and moves on to the next step.

[0071] 3. Refine the details of the consultation.

[0072] The server generates a question based on "natural language processing": "What is the optimal text generation method in natural language processing?"

[0073] 4. Implementing the content of the consultation

[0074] The user sends their consultation request to the generative AI from their terminal.

[0075] The generative AI responded, "Methods using GPT-3 (registered trademark) or Transformers are optimal."

[0076] The server receives and records the response.

[0077] 5. Analysis of results and creation of improvement plans

[0078] The server analyzes the response and identifies a suggestion for improvement: "Next time, please provide specific technical examples."

[0079] We will utilize this improvement plan in the next cycle.

[0080] By repeating this process, it is possible to optimally utilize the strengths of generative AI and continuously improve it to obtain effective responses.

[0081] The following describes the processing flow.

[0082] Step 1:

[0083] The user creates an instance of the AI ​​assistant and sets the necessary API keys. This prepares it to communicate with the generative AI.

[0084] python

[0085] ai_assistant = AIAssistant(api_key="your_api_key_here")

[0086] Step 2:

[0087] The server sends a query to the generative AI asking about its areas of expertise. This query is in the format of "What are your specializations?".

[0088] python

[0089] specialty = ai_assistant.get_specialty()

[0090] Specifically, the server calls an AI API and sends a question related to its area of ​​expertise.

[0091] Step 3:

[0092] The server receives a response from the generative AI and identifies its area of ​​expertise. For example, it might receive a response such as "natural language processing."

[0093] python

[0094] Specialty = "Natural Language Processing"

[0095] The server records the response and uses it in the next step.

[0096] Step 4:

[0097] The server creates the most suitable consultation content based on its identified area of ​​expertise. For example, based on "natural language processing," it might generate a question such as, "What is the best text generation method in natural language processing?"

[0098] python

[0099] consultation = ai_assistant.refine_consultation()

[0100] In terms of specific operations, the server automatically generates consultation content based on its areas of expertise.

[0101] Step 5:

[0102] The user sends the generated consultation content from their terminal to the generative AI. For example, they might send a question such as, "What is the optimal text generation method in natural language processing?"

[0103] python

[0104] response = ai_assistant.consult_ai(consultation)

[0105] In terms of specific operations, the user's terminal sends a question to the generative AI via the server.

[0106] Step 6:

[0107] The server receives a response from the generative AI. For example, it might receive a response such as, "Methods using GPT-3 or Transformers are optimal."

[0108] python

[0109] response = "GPT-3 and Transformers"

[0110] The server will record this response.

[0111] Step 7:

[0112] The server analyzes the response from the generative AI and identifies areas for improvement. For example, it might formulate improvement suggestions for the next cycle, such as "requesting more specific technical examples."

[0113] python

[0114] ai_assistant.implement_and_improve(response)

[0115] Specifically, the server analyzes the received response in detail to identify areas for improvement for the next operation.

[0116] Step 8:

[0117] Users repeat these steps, continuously running the PDCA cycle. This allows them to maximize the strengths of generative AI.

[0118] python

[0119] ai_assistant.run_pdca_cycle()

[0120] Specifically, the server continuously executes a series of steps from get_specialty to implement_and_improve to optimize the performance of the generative AI.

[0121] As described above, the system of the present invention utilizes generative AI and can effectively implement the PDCA cycle to obtain the optimal response in a specialized field.

[0122] (Example 1)

[0123] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0124] In recent years, advancements in generative artificial intelligence (AI) have led to its effective use in various fields. However, it remains challenging to predict which fields generative AI will function most appropriately, requiring significant effort to optimize the content of consultations. Furthermore, there is a need to effectively analyze responses from generative AI and incorporate them into the next cycle, but methods for doing so have not yet been established.

[0125] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0126] In this invention, the server includes means for querying a generative artificial intelligence (AI) about its area of ​​expertise, including its area of ​​specialization; means for receiving a response from the AI ​​based on its area of ​​expertise; means for automatically generating the optimal consultation content based on its area of ​​expertise; means for transmitting the consultation content to the AI ​​and receiving a response; means for analyzing the response and identifying areas for improvement in the next cycle; and means for executing the next cycle incorporating the areas for improvement. This makes it possible to automate the PDCA cycle to optimally utilize the AI's area of ​​expertise and obtain effective responses.

[0127] A "specialized field" refers to a specialized area in which generative artificial intelligence exhibits particularly high performance.

[0128] "Generative artificial intelligence" refers to an artificial intelligence system that has the ability to generate text and data in response to user questions and requests.

[0129] A "specialized field" refers to a specialized area that requires specific knowledge or skills.

[0130] "Consultation content" refers to the questions or requests that users make to the generative artificial intelligence.

[0131] "Response" refers to the information that generative artificial intelligence provides in response to the user's inquiry.

[0132] A "server" refers to a computer system that works in conjunction with generative artificial intelligence to process and manage data.

[0133] "Analysis" refers to the act of examining in detail the responses obtained from generative artificial intelligence and evaluating their content and quality.

[0134] "The next cycle" refers to a new PDCA cycle that begins after the current PDCA cycle is completed.

[0135] The "PDCA cycle" refers to a management cycle consisting of four steps—Plan, Do, Check, and Act—with the aim of improving processes.

[0136] This invention is a system that uses generative artificial intelligence to automatically generate optimal consultation content in specialized fields, and then executes and improves the PDCA cycle based on that content. The system primarily operates through the coordinated operation of server, terminal, and user components.

[0137] System Configuration

[0138] 1. User terminal

[0139] It is a computer or mobile device used by a user to operate a system.

[0140] The user terminal can send inquiries and consultation requests to the generative artificial intelligence.

[0141] 2. Server

[0142] It is a cloud-based or local server that works in conjunction with generative artificial intelligence to perform tasks such as answering inquiries in specialized fields, analyzing responses, and identifying areas for improvement.

[0143] The server is equipped with a program for accessing the API of generative artificial intelligence.

[0144] Program processing

[0145] When a user uses the system, they first create an instance of the AI ​​assistant and configure the necessary API keys. This allows them to access generative artificial intelligence.

[0146] The server sends a query to the generative artificial intelligence (AI) asking about its areas of expertise. The AI ​​responds by listing its areas of expertise, and the server records this response.

[0147] The server automatically generates appropriate consultation questions based on its area of ​​expertise. For example, if its area of ​​expertise is "natural language processing," it will create a consultation question such as, "What is the optimal technique for natural language processing?"

[0148] The terminal sends the generated consultation content to the generative artificial intelligence, which then returns a response to this consultation. The server receives and records this response.

[0149] The server analyzes the response from the generative artificial intelligence and identifies areas for improvement. For example, it might create improvement suggestions such as, "Next time, I will ask questions that include specific technical examples." These improvement suggestions will be reflected in the next PDCA cycle.

[0150] Specific example

[0151] Initialization example

[0152] Example of a user initializing an AI assistant and setting an API key:

[0153] python

[0154] ai_assistant = AIAssistant(api_key="your_api_key_here")

[0155] Examples of selecting areas of expertise

[0156] The server sends the query "What are your specializations?" to the generative AI, and the generative AI responds "I specialize in natural language processing."

[0157] Examples of refining the content of the consultation

[0158] The server generates a question based on "natural language processing": "What is the optimal text generation method in natural language processing?"

[0159] Examples of implementing the consultation content

[0160] The terminal sends the consultation request to the generative artificial intelligence, which responds with "A method using GPT-3 or Transformers is optimal." The server receives and records this response.

[0161] This will allow for continuous improvement to optimally utilize the strengths of generative artificial intelligence and obtain effective responses.

[0162] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0163] Step 1:

[0164] Initialization

[0165] The user creates an instance of the AI ​​assistant and sets up an API key.

[0166] Input: API key from the user.

[0167] Data processing: Creating an instance of the AI ​​assistant, setting up the API key.

[0168] Output: An initialized instance of the AI ​​assistant.

[0169] Specific operation: The user enters `ai_assistant = AIAssistant(api_key="your_api_key_here")` to initialize the AI ​​assistant.

[0170] Step 2:

[0171] Selection of areas of expertise

[0172] The server sends a query to the generative artificial intelligence asking about its areas of expertise.

[0173] Input: Query "What are your specializations?".

[0174] Data processing: Sending queries and receiving responses from generative artificial intelligence.

[0175] Output: Responses related to areas of expertise (e.g., "natural language processing").

[0176] Specific operation: The server sends a query to the generative artificial intelligence and receives a response related to its area of ​​expertise.

[0177] Step 3:

[0178] Refinement of the consultation content

[0179] The server automatically generates appropriate consultation content for the generative artificial intelligence based on its area of ​​expertise.

[0180] Input: Area of ​​expertise (e.g., "Natural Language Processing").

[0181] Data processing: Generating consultation content based on areas of expertise.

[0182] Output: Generated question content (e.g., "What is the optimal text generation method in natural language processing?").

[0183] Specific operation: The server generates the consultation content based on its area of ​​expertise, "natural language processing."

[0184] Step 4:

[0185] Implementation of the consultation

[0186] The terminal sends the generated consultation content to a generative artificial intelligence and receives a response.

[0187] Input: Generated question (e.g., "What is the optimal text generation method in natural language processing?").

[0188] Data processing: Sending consultation content to a generative artificial intelligence and receiving responses.

[0189] Output: Response from generative artificial intelligence (e.g., "Methods using GPT-3 or Transformers are optimal").

[0190] Specific operation: The terminal sends the consultation content to a generative artificial intelligence, receives a response, and records it on the server.

[0191] Step 5:

[0192] Analysis of results and creation of improvement plans

[0193] The server analyzes the response from the generative artificial intelligence and identifies areas for improvement.

[0194] Input: Response from a generative artificial intelligence (e.g., "Methods using GPT-3 or Transformers are optimal").

[0195] Data processing: Response analysis, identification of areas for improvement.

[0196] Output: Suggestions for improvement (e.g., "Next time, I will ask questions including specific technical examples").

[0197] Specific operation: The server analyzes the response from the generative artificial intelligence and creates improvement suggestions to be implemented in the next cycle.

[0198] By executing these steps in sequence, it is possible to optimally utilize the strengths of generative artificial intelligence and realize a PDCA cycle to obtain effective responses.

[0199] (Application Example 1)

[0200] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0201] Currently, optimizing advertising campaigns is time-consuming and labor-intensive, and developing effective storytelling and targeting strategies requires specialized knowledge. Traditional methods, while utilizing generative artificial intelligence, lack a mechanism to effectively leverage its strengths while analyzing large amounts of data simultaneously, making it difficult to create optimal advertising campaigns. Therefore, there is a need for a system that leverages the strengths of generative AI to automatically optimize the storytelling and targeting strategies of advertising campaigns.

[0202] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0203] In this invention, the server includes means for querying a generative artificial intelligence (AI) about its areas of expertise, including its areas of specialization; means for receiving a response from the AI ​​based on its areas of specialization; means for creating an optimal consultation based on its areas of specialization; means for transmitting the consultation to the AI ​​and receiving a response; means for analyzing the response to identify areas for improvement; means for executing the next cycle based on the areas for improvement; means for creating a consultation regarding the optimization of an advertising campaign and analyzing the response from the AI; and means for improving the storytelling and targeting strategies of the advertising campaign based on the response. This enables effective utilization of the AI's areas of expertise and optimizes advertising campaigns.

[0204] "Generative artificial intelligence with a specialized field" refers to generative artificial intelligence that possesses advanced capabilities in a specific field.

[0205] "Means of inquiring about specialized fields" refers to methods or functions for asking generative artificial intelligence which fields it is proficient in.

[0206] "Means of receiving responses" refers to methods or functions for obtaining responses from generative artificial intelligence.

[0207] "Means for creating consultation content" refers to methods and functions for creating appropriate questions and requests based on specialized fields obtained from generative artificial intelligence.

[0208] "Means for sending consultation content and receiving responses" refers to methods and functions for sending created consultation content to generative artificial intelligence and obtaining its responses.

[0209] "Means for analyzing responses and identifying areas for improvement" refers to methods and functions for analyzing responses from generative artificial intelligence and finding areas that need improvement.

[0210] "Means for executing the next cycle" refers to the methods and functions for executing the next process, taking into account the improvements that have been made.

[0211] "Advertising campaign optimization" is the process of improving the content and strategy of an advertisement in order to maximize its effectiveness.

[0212] "Storytelling" is an advertising technique that uses stories and episodes to attract customer interest and effectively convey a message.

[0213] A "targeting strategy" is a method or plan for effectively delivering advertisements to a specific consumer group.

[0214] This invention is a system that optimizes advertising campaigns using generative artificial intelligence. Users utilize user devices such as smartphones and interact with the generative artificial intelligence to achieve effective advertising campaigns. This system operates with the following configuration and configuration.

[0215] System Configuration

[0216] 1. User terminal

[0217] It is a computer or mobile device operated by a user.

[0218] For example, the system can be accessed through a smartphone application.

[0219] 2. Server

[0220] It works in conjunction with generative artificial intelligence and operates in a cloud-based or local data center.

[0221] The server is equipped with a program for accessing the API of generative artificial intelligence.

[0222] Processing flow

[0223] 1. Initialization

[0224] The user initializes the application and sets the necessary API keys.

[0225] Specific example: A user launches a smartphone app and enters an API key.

[0226] 2. Selection of areas of expertise

[0227] The server sends a query to the generative artificial intelligence asking about its area of ​​expertise.

[0228] The server receives the response and records its areas of expertise.

[0229] Specific example: The server asks the generative AI, "What is your area of ​​expertise in advertising?" and the generative AI responds, "I'm good at targeted advertising."

[0230] 3. Refine the details of the consultation.

[0231] The server automatically generates appropriate consultation content for the generative artificial intelligence based on its area of ​​expertise.

[0232] Specific example: A question is generated asking, "What are the optimal content and strategies for targeted advertising?"

[0233] 4. Implementing the content of the consultation

[0234] The user sends their inquiry to a generative artificial intelligence from their terminal and receives a response.

[0235] Specific example: A user's device sends a question to a generative artificial intelligence, and receives a response such as, "Storytelling and personalized advertising relevant to your target audience would be effective."

[0236] 5. Analysis of results and creation of improvement plans

[0237] The server analyzes the response from the generative artificial intelligence and identifies areas for improvement.

[0238] Based on the improvements identified, we will execute the next cycle.

[0239] Specific example: Analyze the response and formulate an improvement plan for the next consultation, such as "asking for specific examples of storytelling."

[0240] Hardware and software to be used

[0241] Hardware:

[0242] User devices: Smartphones, tablets, PCs, etc.

[0243] Servers: Cloud-based data centers, local servers

[0244] software:

[0245] APIs for generative artificial intelligence (e.g., OpenAI® API)

[0246] Data collection and analysis tools (e.g., Python®-based scripts)

[0247] Example of a prompt

[0248] "Could you give me some specific examples of storytelling in targeted advertising?"

[0249] This invention makes it possible to effectively utilize the strengths of generative artificial intelligence to automatically optimize the storytelling and targeting strategies of advertising campaigns.

[0250] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0251] Step 1:

[0252] Initialization

[0253] Subject: User

[0254] Specific operation: The user launches the smartphone application and enters the required API key.

[0255] Input: API key

[0256] Output: API key setup complete

[0257] Processing details: Store the API key within the application and prepare for integration with generative artificial intelligence.

[0258] Step 2:

[0259] Selection of areas of expertise

[0260] Subject: Server

[0261] Specific operation: The server sends a query to the generative artificial intelligence: "What is your expertise in the advertising field?"

[0262] Input: Query "What is your area of ​​expertise in advertising?"

[0263] Output: Response from generative artificial intelligence (e.g., "I'm good at targeted advertising")

[0264] Processing details: Receive and record responses related to the generative artificial intelligence's area of ​​expertise.

[0265] Step 3:

[0266] Refinement of the consultation content

[0267] Subject: Server

[0268] Specific operation: The server automatically generates appropriate consultation content based on its area of ​​expertise.

[0269] Input: Response indicating your area of ​​expertise (e.g., "I specialize in targeted advertising.")

[0270] Output: Consultation content (Example: "What are the optimal content and strategies for targeted advertising?")

[0271] Processing details: Based on the area of ​​expertise, construct more detailed questions for the generative artificial intelligence.

[0272] Step 4:

[0273] Implementation of the consultation

[0274] Subject: terminal

[0275] Specific operation: The user sends the consultation content from their terminal to a generative artificial intelligence and retrieves the results.

[0276] Input: Question (Example: "What are the optimal content and strategies for targeted advertising?")

[0277] Output: Response from generative artificial intelligence (e.g., "Storytelling and personalized advertising relevant to your target audience are effective")

[0278] Processing details: The consultation content is sent, and the received response is saved within the application.

[0279] Step 5:

[0280] Analysis of results and creation of improvement plans

[0281] Subject: Server

[0282] Specific operation: The server analyzes the response from the generative artificial intelligence and identifies areas for improvement.

[0283] Input: Response from generative artificial intelligence (e.g., "Storytelling and personalized advertising relevant to your target audience are effective")

[0284] Output: Improvement plan to be reflected in the next consultation content (e.g., "Request for specific storytelling examples")

[0285] Processing content: Analyze the response and identify what aspects should be improved in the next consultation.

[0286] Step 6:

[0287] Execution of the next cycle

[0288] Subject: Server and terminal

[0289] Specific operation: The server refines the content of the next consultation based on the improvement plan and makes a new inquiry to the generative artificial intelligence on the user terminal.

[0290] Input: Improvement plan (e.g., "Request for specific storytelling examples")

[0291] Output: New consultation content (e.g., "Please provide examples of specific storytelling in targeted advertising")

[0292] Processing content: Generate new consultation content based on the improvement plan and continuously optimize the advertising campaign by repeating this process.

[0293] Furthermore, an emotion engine for estimating the user's emotions may be combined. That is, the specific processing unit 290 may estimate the user's emotions using the emotion recognition model 59 and perform specific processing using the user's emotions.

[0294] This invention is a system using generative artificial intelligence (AI), which executes a PDCA cycle to generate and continuously improve optimal consultation content based on the user's area of expertise by combining the recognition of the user's emotions. The specific configuration, operation, and series of processes of the system are described below.

[0295] Configuration of the system

[0296] 1. User terminal

[0297] It is a computer or mobile device for a user to operate the system.

[0298] Queries and consultations regarding generative AI are sent from the user terminal.

[0299] 2. Server

[0300] It is a cloud-based or local server that collaborates with generative AI to conduct inquiries in areas of expertise, analyze responses, recognize emotions, identify areas for improvement, etc.

[0301] The server is equipped with a program for accessing the API of generative AI and an emotion engine.

[0302] 3. Emotion engine

[0303] It is an engine for recognizing the emotions of users and optimizing the responses and consultation content of generative AI according to the emotional state of users.

[0304] Program processing

[0305] 1. Initialization

[0306] The user creates an instance of the AI assistant and sets the necessary API key.

[0307] 2. Selection of area of expertise

[0308] The server sends a query to generative AI to inquire about a specialized field.

[0309] Generative AI returns the area of expertise as a response (e.g., "Natural language processing").

[0310] The server records this response and uses it in the next step.

[0311] 3. Refine the details of the consultation.

[0312] The server automatically creates the most suitable consultation content based on its area of ​​expertise.

[0313] Furthermore, an emotion engine is used to analyze the user's current emotional state and adjust the consultation content accordingly.

[0314] For example, if a user is feeling stressed, the content of their consultation will be adjusted to be concise and easy to understand.

[0315] 4. Implementing the content of the consultation

[0316] The user terminal sends the generated consultation content to the generative AI.

[0317] The generative AI will provide a response to this inquiry.

[0318] The server receives and records the response.

[0319] 5. Analysis of results and creation of improvement plans

[0320] The server analyzes the response from the generative AI and identifies areas for improvement.

[0321] An emotion engine is used to consider the user's emotional state during response analysis. For example, if the user was not satisfied with the previous response, an improvement plan will be developed that provides more specific information for the next response.

[0322] These improvement suggestions will be implemented in the next cycle.

[0323] Specific example

[0324] scenario:

[0325] Users want to use generative AI to find the optimal method for generating text.

[0326] 1. Initialization

[0327] The user initializes the AI ​​assistant and sets the API key.

[0328] 2. Selection of areas of expertise

[0329] The server sends a query to the generative AI: "What are your specializations?"

[0330] The generative AI responded, "I'm good at natural language processing."

[0331] The server records its areas of expertise and moves on to the next step.

[0332] 3. Refine the details of the consultation.

[0333] The server generates the question, "What is the optimal text generation method in natural language processing?" based on "natural language processing."

[0334] The emotion engine analyzes the user's emotional state to determine whether the user is particularly interested, relaxed, etc.

[0335] When the user is relaxed, the information is adjusted to be more detailed.

[0336] 4. Implementing the content of the consultation

[0337] The user sends their consultation request to the generative AI from their terminal.

[0338] The generative AI responded, "Methods using GPT-3 or Transformers are optimal."

[0339] The server receives and records the response.

[0340] 5. Analysis of results and creation of improvement plans

[0341] The server analyzes the response and identifies the following areas for improvement.

[0342] The user's emotional state will be re-analyzed, and the content of the next consultation and the method of providing responses will be adjusted accordingly.

[0343] For example, in the next cycle, we could formulate questions that ask for specific implementation examples.

[0344] Thus, the system of the present invention, by using generative AI and an emotion engine, can generate optimal consultation content that takes into account the user's emotional state, continuously improve it, and make maximum use of the strengths of generative AI.

[0345] The following describes the processing flow.

[0346] Step 1:

[0347] The user creates an instance of the AI ​​assistant and sets the necessary API keys. This prepares them to utilize the generative AI and emotion engine.

[0348] python

[0349] ai_assistant = AIAssistant(api_key="your_api_key_here")

[0350] Step 2:

[0351] The server sends a query to the generative AI asking about its areas of expertise. This query is in the form of "What are your specializations?". The generative AI responds by returning its area of ​​expertise (for example, "natural language processing").

[0352] python

[0353] specialty = ai_assistant.get_specialty()

[0354] The server calls a generative AI API, sends questions related to its area of ​​expertise, and receives and records the responses.

[0355] Step 3:

[0356] The server creates the most suitable consultation content based on its identified areas of expertise. During this process, an emotion engine is used to analyze the user's emotional state and adjust the consultation content accordingly.

[0357] python

[0358] consultation = ai_assistant.refine_consultation()

[0359] The server automatically generates consultation content based on its area of ​​expertise, and the emotion engine analyzes the user's emotional state to adjust the consultation content. For example, if the user is feeling stressed, the consultation content will be adjusted to be concise and easy to understand.

[0360] Step 4:

[0361] The user's terminal sends the generated consultation content to the generative AI. For example, it might send the question, "What is the optimal text generation method in natural language processing?"

[0362] python

[0363] response = ai_assistant.consult_ai(consultation)

[0364] The user terminal sends questions to the generative AI via the server.

[0365] Step 5:

[0366] The server receives a response from the generative AI. For example, it might receive a response such as, "Methods using GPT-3 or Transformers are optimal."

[0367] python

[0368] response = "GPT-3 and Transformers"

[0369] The server will record this response.

[0370] Step 6:

[0371] The server analyzes the response from the generative AI and identifies areas for improvement. At this time, it uses an emotion engine to re-analyze the user's emotional state and determine areas for improvement in the next cycle.

[0372] python

[0373] ai_assistant.implement_and_improve(response)

[0374] The server analyzes the response in detail, and the emotion engine analyzes the user's emotional state to identify areas for improvement. For example, if the user was not satisfied with the previous response, the system will develop an improvement plan that provides more specific information next time.

[0375] Step 7:

[0376] The user repeats these steps, continuously running the PDCA cycle. This allows the system to continuously generate consultation content that maximizes the strengths of generative AI and the user's emotional state.

[0377] python

[0378] ai_assistant.run_pdca_cycle()

[0379] The server continuously executes a series of steps from get_specialty to implement_and_improve to optimize the performance of the generative AI.

[0380] As described above, the system of the present invention combines generative AI and an emotion engine to generate optimal consultation content that takes into account the user's emotional state, and can make maximum use of the strengths of generative AI while continuously improving it.

[0381] (Example 2)

[0382] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0383] Existing generative knowledge systems provide information without considering the user's emotional state, making it difficult to generate appropriate consultation content and improve the quality of responses. As a result, users are unable to obtain the information they need, and continuous improvement is not possible.

[0384] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for querying a generative knowledge system that includes areas of expertise for a specialized field; means for receiving a response from the generative knowledge system based on the specialized field; means for generating optimal consultation content based on the specialized field; means for transmitting the consultation content to the generative knowledge system and receiving a response; means for analyzing the response and identifying areas for improvement; means for executing the next cycle based on the areas for improvement; means including an engine for analyzing the user's emotional state; and means for adjusting the consultation content based on the emotional state. This makes it possible to generate optimal consultation content that takes the user's emotional state into consideration and to continuously improve it.

[0385] A "specialized area" refers to a specialized field in which a generative knowledge system excels in terms of knowledge and capabilities.

[0386] A "generative knowledge system" is an artificial intelligence system that generates and provides information based on user inquiries.

[0387] A "specialized field" refers to an area that requires advanced knowledge and skills in a specific area.

[0388] A "response" is the information or answer that a generative knowledge system provides in response to a query from a user or server.

[0389] "Consultation content" refers to the specific questions or requests that a user submits to a generative knowledge system.

[0390] A "cycle" refers to a series of processes involving generating the content of a consultation, obtaining a response, analyzing the response, identifying areas for improvement, and implementing improvements for the next session.

[0391] An "emotion engine" is a component that analyzes the user's emotional state and adjusts the information and responses generated based on the results.

[0392] "Emotional state" refers to the emotions and psychological state a user is experiencing at a given point in time.

[0393] "Analysis" refers to the information processing used to evaluate responses from generative knowledge systems and identify areas for improvement.

[0394] "Improvements" refer to changes or enhancements identified to improve the response from a generative knowledge system.

[0395] This invention is a system that utilizes a generative knowledge system and an emotion engine. It considers the user's emotional state, generates optimal consultation content based on their areas of expertise, and implements a PDCA cycle for continuous improvement. The specific configuration and operation of this system will be described below.

[0396] System Configuration

[0397] 1. User terminal:

[0398] This is a computer or mobile device used by users to operate the system. Inquiries and consultations are sent from the user terminal to the generative knowledge system.

[0399] 2. Server:

[0400] It is a cloud-based or local server that works in conjunction with generative knowledge systems to perform tasks such as analyzing inquiries and responses in its area of ​​expertise, recognizing sentiment, and identifying areas for improvement. The server is equipped with programs and a sentiment engine to access the generative knowledge system's API.

[0401] 3. Emotional Engine:

[0402] This engine recognizes user emotions and optimizes the responses and consultation content of generative knowledge systems according to the user's emotional state.

[0403] Specific examples of actions

[0404] scenario:

[0405] Let's take the example of a user who wants to use a generative knowledge system to find the optimal method for generating text.

[0406] 1. Initialization:

[0407] The user initializes the AI ​​assistant and sets the necessary API keys.

[0408] For example, a user might open an application on their device and go through the steps of setting up an API key for a generative knowledge system.

[0409] 2. Selecting your area of ​​expertise:

[0410] The server sends the prompt "What are your specializations?" to the generative knowledge system. The generative knowledge system responds "I specialize in natural language processing," and the server records the area of ​​expertise.

[0411] 3. Refine the details of the consultation:

[0412] The server generates a consultation question based on its area of ​​expertise, asking "What is the optimal text generation method in natural language processing?" Furthermore, the emotion engine analyzes the user's emotional state, and if, for example, the user is feeling stressed, it adjusts the consultation question to be concise and easy to understand.

[0413] 4. Implementing the plan discussed:

[0414] The user terminal sends the generated consultation content to the generative knowledge system. The generative knowledge system responds with "A method using GPT-3 or Transformers is optimal," and the server receives and records the response.

[0415] 5. Analysis of results and development of improvement plans:

[0416] The server analyzes the response and identifies areas for improvement. For example, it re-analyzes the user's emotional state, and if the user was not satisfied with the previous response, it develops an improvement plan to provide more specific information next time. This improvement plan will be implemented in the next PDCA cycle.

[0417] Hardware and software to be used

[0418] Hardware: Computers, mobile devices, cloud-based or local servers

[0419] Software: APIs for generative knowledge systems (e.g., OpenAI), emotion engines, user interfaces

[0420] Examples of prompt statements

[0421] Prompt for selecting your area of ​​specialization: "What are your specializations?"

[0422] Prompt for generating consultation content: "What is the optimal text generation method in natural language processing?"

[0423] By implementing this invention, users can generate optimal consultation content that takes their emotional state into consideration and obtain high-quality responses by making full use of the strengths of generative knowledge systems. Furthermore, continuous improvement can be expected, leading to an enhanced user experience.

[0424] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0425] Step 1:

[0426] Initialization

[0427] The user starts up their device and opens a dedicated application. Next, the user enters the API key for the generative knowledge system within the application. This establishes a connection to the generative knowledge system, enabling subsequent data processing. The input is the API key, and the output is the connection status with the generative knowledge system.

[0428] Step 2:

[0429] Selection of areas of expertise

[0430] The server sends the prompt "What are your specializations?" to the generative knowledge system. Based on this prompt, the generative knowledge system responds with its area of ​​expertise (for example, "natural language processing"). The input is the prompt "What are your specializations?", and the output is the response from the generative knowledge system. The server records this response.

[0431] Step 3:

[0432] Refinement of the consultation content

[0433] The server generates consultation content based on its areas of expertise obtained in the previous step. For example, based on "natural language processing," it generates the question, "What is the optimal text generation method in natural language processing?" Next, the emotion engine analyzes the user's emotional state. For example, if it determines that the user is feeling stressed, it reorganizes the generated question to be concise and easy to understand. The input consists of prompt sentences based on the areas of expertise and data on the emotional state, and the output is the optimized consultation content.

[0434] Step 4:

[0435] Implementation of the consultation

[0436] The user terminal sends the generated inquiry content to the generative knowledge system. The generative knowledge system returns a specific response to this inquiry content. For example, if the inquiry content is "What is the optimal text generation method in natural language processing?", the response would be "Methods using GPT-3 or Transformers are optimal." The input is the optimized inquiry content, and the output is the response from the generative knowledge system. The server records this response.

[0437] Step 5:

[0438] Analysis of results and creation of improvement plans

[0439] The server analyzes the response from the generative knowledge system and evaluates its quality. Furthermore, it uses an emotion engine to re-analyze the user's emotional state and determine whether the user was satisfied with the response. For example, if the user was not satisfied with the response, the server develops improvement suggestions to make the next consultation more specific and detailed. The input is the previous response and the user's emotional data, and the output is improvement suggestions for the next cycle.

[0440] Through the specific processing steps described above, the system can generate optimal consultation content while considering the user's emotional state, utilizing the strengths of generative knowledge systems, and continuously improve its process.

[0441] (Application Example 2)

[0442] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0443] Many modern content delivery systems provide users with uniform content, making it difficult to suggest content that is optimal for each user's emotional state and preferences. This degrades the quality of the user experience and reduces their willingness to consume content. Furthermore, the lack of mechanisms to improve future suggestions based on feedback on the content provided prevents continuous personalization.

[0444] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for querying a generative artificial intelligence, including its areas of expertise, for its areas of expertise; means for receiving a response from the generative artificial intelligence based on the areas of expertise; means for creating optimal consultation content based on the areas of expertise; means for recognizing the user's emotions and optimizing the consultation content according to the recognized emotional state; means for transmitting the consultation content to the generative artificial intelligence and receiving a response; means for analyzing the response and identifying areas for improvement; and means for executing the next cycle based on the areas for improvement. This enables optimal content suggestions based on the user's emotional state and areas of expertise, as well as continuous improvement based on feedback.

[0445] "Generative artificial intelligence" is an artificial intelligence technology that uses specialized knowledge and information in a particular field to provide optimal answers and suggestions to user inquiries.

[0446] A "user terminal" is a computer or mobile device used by a user to operate the system and send inquiries and consultations to the generative artificial intelligence.

[0447] A "server" is a network-based computer system that works in conjunction with generative artificial intelligence to conduct research in specialized fields, recognize emotions, analyze responses, and identify improvement suggestions.

[0448] An "emotion engine" is software that recognizes the user's emotions and optimizes the responses and consultation content of generative artificial intelligence based on that emotional state.

[0449] A "specialized field" refers to an area of ​​technology or knowledge in which generative artificial intelligence excels, and is a field in which it possesses a deep understanding.

[0450] "Consultation content" refers to the specific questions or concerns that the user submits to the generative artificial intelligence.

[0451] "Response" refers to the answers or suggestions that generative artificial intelligence provides in response to a user's inquiry.

[0452] A "specialty area" refers to a specific field in which generative artificial intelligence possesses particularly specialized knowledge or skills.

[0453] "Optimization" refers to the process of adjusting and improving the responses and consultation content of generative artificial intelligence to the best possible form, based on the user's emotional state and area of ​​expertise.

[0454] "Areas for improvement" refers to points of modification or adjustment identified to improve the quality of the generative artificial intelligence's responses.

[0455] "Feedback" refers to evaluations and impressions of responses provided by users, and serves as information to improve future responses.

[0456] This invention is a system that uses generative artificial intelligence combined with user emotion recognition to suggest optimal content. The specific configuration, operation, and process of the system are described below.

[0457] System Configuration

[0458] 1. User terminal

[0459] It is a computer or mobile device used by the user to operate the system and send inquiries and consultations to generative artificial intelligence.

[0460] 2. Server

[0461] It is a networked computer system that works in conjunction with generative artificial intelligence to conduct research in specialized fields, recognize emotions, analyze responses, and identify improvement suggestions.

[0462] 3. Emotional Engine

[0463] This software recognizes the user's emotions and optimizes the responses and consultation content of generative artificial intelligence based on that emotional state.

[0464] Program processing

[0465] This system will be implemented using the following hardware and software:

[0466] Hardware:

[0467] Smartphones (iPhone® and Android® devices)

[0468] Network Server

[0469] software:

[0470] EmotionRecognizer: A library for recognizing user emotions. In this case, it uses OpenCV or Dlib to analyze facial expressions.

[0471] ContentSelector: A library for suggesting content. It utilizes APIs from generative artificial intelligence (such as GPT-3).

[0472] FeedbackAnalyzer: A library for analyzing user feedback and incorporating it into future suggestions.

[0473] Specific implementation methods

[0474] 1. Recognizing user emotions:

[0475] The user uses their smartphone's camera and microphone to send their facial expressions and voice to the system, which EmotionRecognizer analyzes to recognize emotions.

[0476] 2. Selection of a field of specialization:

[0477] The ContentSelector on the server queries the generative artificial intelligence (AI) for its area of ​​expertise, identifying its strengths. For example, it might ask the AI, "What are your specializations?"

[0478] 3. Content proposals:

[0479] The server suggests the most suitable content based on the user's perceived emotional state and areas of expertise. For example, if the user is relaxed, it might suggest a "comedy movie."

[0480] 4. Gathering and analyzing feedback:

[0481] FeedbackAnalyzer collects feedback from users who have viewed the suggested content and uses this feedback to improve future suggestions.

[0482] Specific example

[0483] Example of a prompt

[0484] "You seem relaxed right now. What's the best movie to watch next?"

[0485] Usage Scenarios

[0486] The user opens the app and points their face in front of the camera.

[0487] The app analyzes the user's facial expressions and identifies the emotion of "relaxation."

[0488] I've chosen "comedy films" as my area of ​​expertise.

[0489] The app recommends the movie "The Grand Budapest Hotel".

[0490] Users provide "satisfied" feedback after watching a movie.

[0491] Next time, the app will enhance its recommendations for more relaxing comedy movies.

[0492] Thus, the system of the present invention enables optimal content suggestions based on the user's emotional state and areas of expertise, as well as continuous improvement based on feedback.

[0493] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0494] Step 1:

[0495] The user launches the application on their smartphone and records their current state via the camera or microphone. The input consists of the user's facial expressions and voice data. EmotionRecognizer analyzes this data and recognizes emotions from the facial expressions and voice. The output is the emotional state (e.g., relaxed, stressed).

[0496] Step 2:

[0497] The server queries a generative artificial intelligence (AI) about its areas of expertise. The input is a query about areas of expertise (e.g., "What are your specializations?"). The generative AI responds by returning its areas of expertise. This response is analyzed by the server to identify its areas of expertise (e.g., comedy films). The output is information about its areas of expertise.

[0498] Step 3:

[0499] The server creates the most suitable consultation content based on the emotional state and areas of expertise it recognizes. The input is the emotional state and areas of expertise. The server generates a prompt based on this (e.g., "You seem relaxed now. What movie would be best to watch next?"). The output is the generated prompt.

[0500] Step 4:

[0501] The server sends a generated prompt to the generative artificial intelligence (AI). The input is the generated prompt. The generative AI generates a response to this prompt and returns the most suitable content suggestion (e.g., a suggestion for the movie "The Grand Budapest Hotel"). The output is the response from the generative AI.

[0502] Step 5:

[0503] The user terminal displays the response received from the server and provides content suggestions to the user. The input is the response from the generative artificial intelligence. The user terminal receives this and displays it on the screen. The output is the content suggestions displayed to the user.

[0504] Step 6:

[0505] Users view the provided content and then provide feedback. The input is the user's feedback (e.g., "satisfied" or "dissatisfied"). The feedback is sent to the server via the user's device. The output is the user's feedback data.

[0506] Step 7:

[0507] The server analyzes user feedback and generates instructions to improve future suggestions. The input consists of user feedback data and suggested content information. The server's FeedbackAnalyzer analyzes this data and identifies areas for improvement in the response. The output is a list of improvements for the next cycle.

[0508] As described above, by clearly defining the specific actions, inputs, and outputs at each step, the system's processing flow can be explained in detail. This enables the system to provide optimal content suggestions based on the user's emotional state and areas of expertise.

[0509] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0510] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0511] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0512] [Second Embodiment]

[0513] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0514] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0515] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0516] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0517] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0518] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0519] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0520] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0521] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0522] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0523] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0524] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0525] This invention is a system utilizing generative artificial intelligence (AI), and its purpose is to implement a PDCA cycle to optimally utilize the strengths of generative AI, which is constantly evolving. The specific configuration, operation, and series of processes of the system are described below.

[0526] System Configuration

[0527] 1. User terminal

[0528] It is a computer or mobile device used by a user to operate a system.

[0529] Inquiries and consultations are sent from the user's terminal to the generative AI.

[0530] 2. Server

[0531] It is a cloud-based or local server that works in conjunction with generative AI to analyze inquiries and responses in its area of ​​expertise, and identify areas for improvement.

[0532] The server is equipped with a program to access the generative AI API.

[0533] Program processing

[0534] 1. Initialization

[0535] The user creates an instance of the AI ​​assistant and sets the necessary API key.

[0536] 2. Selection of areas of expertise

[0537] The server sends a query to the generative AI asking about its areas of expertise.

[0538] The generative AI responds by returning a response related to its area of ​​expertise (for example, "natural language processing").

[0539] The server records this response and uses it in the next step.

[0540] 3. Refine the details of the consultation.

[0541] The server automatically generates appropriate consultation content for the generative AI based on its area of ​​expertise.

[0542] For example, if your area of ​​expertise is "natural language processing," you would create a consultation request such as, "What is the optimal technique for natural language processing?"

[0543] 4. Implementing the content of the consultation

[0544] The user terminal sends the generated consultation content to the generative AI.

[0545] The generative AI will provide a response to this inquiry.

[0546] The server receives and records the response.

[0547] 5. Analysis of results and creation of improvement plans

[0548] The server analyzes the response from the generative AI and identifies areas for improvement.

[0549] For example, you could come up with a plan to improve by saying, "Next time, I'll ask questions that include specific technical examples."

[0550] These improvement suggestions will be implemented in the next cycle.

[0551] Specific example

[0552] scenario:

[0553] Users want to use generative AI to find the optimal method for generating text.

[0554] 1. Initialization

[0555] The user initializes the AI ​​assistant and sets the API key.

[0556] ai_assistant = AIAssistant(api_key="your_api_key_here")

[0557] 2. Selection of areas of expertise

[0558] The server sends a query to the generative AI: "What are your specializations?"

[0559] The generative AI responded, "I'm good at natural language processing."

[0560] The server records its areas of expertise and moves on to the next step.

[0561] 3. Refine the details of the consultation.

[0562] The server generates a question based on "natural language processing": "What is the optimal text generation method in natural language processing?"

[0563] 4. Implementing the content of the consultation

[0564] The user sends their consultation request to the generative AI from their terminal.

[0565] The generative AI responded, "Methods using GPT-3 or Transformers are optimal."

[0566] The server receives and records the response.

[0567] 5. Analysis of results and creation of improvement plans

[0568] The server analyzes the response and identifies a suggestion for improvement: "Next time, please provide specific technical examples."

[0569] We will utilize this improvement plan in the next cycle.

[0570] By repeating this process, it is possible to optimally utilize the strengths of generative AI and continuously improve it to obtain effective responses.

[0571] The following describes the processing flow.

[0572] Step 1:

[0573] The user creates an instance of the AI ​​assistant and sets the necessary API keys. This prepares it to communicate with the generative AI.

[0574] python

[0575] ai_assistant = AIAssistant(api_key="your_api_key_here")

[0576] Step 2:

[0577] The server sends a query to the generative AI asking about its areas of expertise. This query is in the format of "What are your specializations?".

[0578] python

[0579] specialty = ai_assistant.get_specialty()

[0580] Specifically, the server calls an AI API and sends a question related to its area of ​​expertise.

[0581] Step 3:

[0582] The server receives a response from the generative AI and identifies its area of ​​expertise. For example, it might receive a response such as "natural language processing."

[0583] python

[0584] Specialty = "Natural Language Processing"

[0585] The server records the response and uses it in the next step.

[0586] Step 4:

[0587] The server creates the most suitable consultation content based on its identified area of ​​expertise. For example, based on "natural language processing," it might generate a question such as, "What is the best text generation method in natural language processing?"

[0588] python

[0589] consultation = ai_assistant.refine_consultation()

[0590] In terms of specific operations, the server automatically generates consultation content based on its areas of expertise.

[0591] Step 5:

[0592] The user sends the generated consultation content from their terminal to the generative AI. For example, they might send a question such as, "What is the optimal text generation method in natural language processing?"

[0593] python

[0594] response = ai_assistant.consult_ai(consultation)

[0595] In terms of specific operations, the user's terminal sends a question to the generative AI via the server.

[0596] Step 6:

[0597] The server receives a response from the generative AI. For example, it might receive a response such as, "Methods using GPT-3 or Transformers are optimal."

[0598] python

[0599] response = "GPT-3 and Transformers"

[0600] The server will record this response.

[0601] Step 7:

[0602] The server analyzes the response from the generative AI and identifies areas for improvement. For example, it might formulate improvement suggestions for the next cycle, such as "requesting more specific technical examples."

[0603] python

[0604] ai_assistant.implement_and_improve(response)

[0605] Specifically, the server analyzes the received response in detail to identify areas for improvement for the next operation.

[0606] Step 8:

[0607] Users repeat these steps, continuously running the PDCA cycle. This allows them to maximize the strengths of generative AI.

[0608] python

[0609] ai_assistant.run_pdca_cycle()

[0610] Specifically, the server continuously executes a series of steps from get_specialty to implement_and_improve to optimize the performance of the generative AI.

[0611] As described above, the system of the present invention utilizes generative AI and can effectively implement the PDCA cycle to obtain the optimal response in a specialized field.

[0612] (Example 1)

[0613] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0614] In recent years, advancements in generative artificial intelligence (AI) have led to its effective use in various fields. However, it remains challenging to predict which fields generative AI will function most appropriately, requiring significant effort to optimize the content of consultations. Furthermore, there is a need to effectively analyze responses from generative AI and incorporate them into the next cycle, but methods for doing so have not yet been established.

[0615] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0616] In this invention, the server includes means for querying a generative artificial intelligence (AI) about its area of ​​expertise, including its area of ​​specialization; means for receiving a response from the AI ​​based on its area of ​​expertise; means for automatically generating the optimal consultation content based on its area of ​​expertise; means for transmitting the consultation content to the AI ​​and receiving a response; means for analyzing the response and identifying areas for improvement in the next cycle; and means for executing the next cycle incorporating the areas for improvement. This makes it possible to automate the PDCA cycle to optimally utilize the AI's area of ​​expertise and obtain effective responses.

[0617] A "specialized field" refers to a specialized area in which generative artificial intelligence exhibits particularly high performance.

[0618] "Generative artificial intelligence" refers to an artificial intelligence system that has the ability to generate text and data in response to user questions and requests.

[0619] A "specialized field" refers to a specialized area that requires specific knowledge or skills.

[0620] "Consultation content" refers to the questions or requests that users make to the generative artificial intelligence.

[0621] "Response" refers to the information that generative artificial intelligence provides in response to the user's inquiry.

[0622] A "server" refers to a computer system that works in conjunction with generative artificial intelligence to process and manage data.

[0623] "Analysis" refers to the act of examining in detail the responses obtained from generative artificial intelligence and evaluating their content and quality.

[0624] "The next cycle" refers to a new PDCA cycle that begins after the current PDCA cycle is completed.

[0625] The "PDCA cycle" refers to a management cycle consisting of four steps—Plan, Do, Check, and Act—with the aim of improving processes.

[0626] This invention is a system that uses generative artificial intelligence to automatically generate optimal consultation content in specialized fields, and then executes and improves the PDCA cycle based on that content. The system primarily operates through the coordinated operation of server, terminal, and user components.

[0627] System Configuration

[0628] 1. User terminal

[0629] It is a computer or mobile device used by a user to operate a system.

[0630] The user terminal can send inquiries and consultation requests to the generative artificial intelligence.

[0631] 2. Server

[0632] It is a cloud-based or local server that works in conjunction with generative artificial intelligence to perform tasks such as answering inquiries in specialized fields, analyzing responses, and identifying areas for improvement.

[0633] The server is equipped with a program for accessing the API of generative artificial intelligence.

[0634] Program processing

[0635] When a user uses the system, they first create an instance of the AI ​​assistant and configure the necessary API keys. This allows them to access generative artificial intelligence.

[0636] The server sends a query to the generative artificial intelligence (AI) asking about its areas of expertise. The AI ​​responds by listing its areas of expertise, and the server records this response.

[0637] The server automatically generates appropriate consultation questions based on its area of ​​expertise. For example, if its area of ​​expertise is "natural language processing," it will create a consultation question such as, "What is the optimal technique for natural language processing?"

[0638] The terminal sends the generated consultation content to the generative artificial intelligence, which then returns a response to this consultation. The server receives and records this response.

[0639] The server analyzes the response from the generative artificial intelligence and identifies areas for improvement. For example, it might create improvement suggestions such as, "Next time, I will ask questions that include specific technical examples." These improvement suggestions will be reflected in the next PDCA cycle.

[0640] Specific example

[0641] Initialization example

[0642] Example of a user initializing an AI assistant and setting an API key:

[0643] python

[0644] ai_assistant = AIAssistant(api_key="your_api_key_here")

[0645] Examples of selecting areas of expertise

[0646] The server sends the query "What are your specializations?" to the generative AI, and the generative AI responds "I specialize in natural language processing."

[0647] Examples of refining the content of the consultation

[0648] The server generates a question based on "natural language processing": "What is the optimal text generation method in natural language processing?"

[0649] Examples of implementing the consultation content

[0650] The terminal sends the consultation request to the generative artificial intelligence, which responds with "A method using GPT-3 or Transformers is optimal." The server receives and records this response.

[0651] This will allow for continuous improvement to optimally utilize the strengths of generative artificial intelligence and obtain effective responses.

[0652] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0653] Step 1:

[0654] Initialization

[0655] The user creates an instance of the AI ​​assistant and sets up an API key.

[0656] Input: API key from the user.

[0657] Data processing: Creating an instance of the AI ​​assistant, setting up the API key.

[0658] Output: An initialized instance of the AI ​​assistant.

[0659] Specific operation: The user enters `ai_assistant = AIAssistant(api_key="your_api_key_here")` to initialize the AI ​​assistant.

[0660] Step 2:

[0661] Selection of areas of expertise

[0662] The server sends a query to the generative artificial intelligence asking about its areas of expertise.

[0663] Input: Query "What are your specializations?".

[0664] Data processing: Sending queries and receiving responses from generative artificial intelligence.

[0665] Output: Responses related to areas of expertise (e.g., "natural language processing").

[0666] Specific operation: The server sends a query to the generative artificial intelligence and receives a response related to its area of ​​expertise.

[0667] Step 3:

[0668] Refinement of the consultation content

[0669] The server automatically generates appropriate consultation content for the generative artificial intelligence based on its area of ​​expertise.

[0670] Input: Area of ​​expertise (e.g., "Natural Language Processing").

[0671] Data processing: Generating consultation content based on areas of expertise.

[0672] Output: Generated question content (e.g., "What is the optimal text generation method in natural language processing?").

[0673] Specific operation: The server generates the consultation content based on its area of ​​expertise, "natural language processing."

[0674] Step 4:

[0675] Implementation of the consultation

[0676] The terminal sends the generated consultation content to a generative artificial intelligence and receives a response.

[0677] Input: Generated question (e.g., "What is the optimal text generation method in natural language processing?").

[0678] Data processing: Sending consultation content to a generative artificial intelligence and receiving responses.

[0679] Output: Response from generative artificial intelligence (e.g., "Methods using GPT-3 or Transformers are optimal").

[0680] Specific operation: The terminal sends the consultation content to a generative artificial intelligence, receives a response, and records it on the server.

[0681] Step 5:

[0682] Analysis of results and creation of improvement plans

[0683] The server analyzes the response from the generative artificial intelligence and identifies areas for improvement.

[0684] Input: Response from a generative artificial intelligence (e.g., "Methods using GPT-3 or Transformers are optimal").

[0685] Data processing: Response analysis, identification of areas for improvement.

[0686] Output: Suggestions for improvement (e.g., "Next time, I will ask questions including specific technical examples").

[0687] Specific operation: The server analyzes the response from the generative artificial intelligence and creates improvement suggestions to be implemented in the next cycle.

[0688] By executing these steps in sequence, it is possible to optimally utilize the strengths of generative artificial intelligence and realize a PDCA cycle to obtain effective responses.

[0689] (Application Example 1)

[0690] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0691] Currently, optimizing advertising campaigns is time-consuming and labor-intensive, and developing effective storytelling and targeting strategies requires specialized knowledge. Traditional methods, while utilizing generative artificial intelligence, lack a mechanism to effectively leverage its strengths while analyzing large amounts of data simultaneously, making it difficult to create optimal advertising campaigns. Therefore, there is a need for a system that leverages the strengths of generative AI to automatically optimize the storytelling and targeting strategies of advertising campaigns.

[0692] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0693] In this invention, the server includes means for querying a generative artificial intelligence (AI) about its areas of expertise, including its areas of specialization; means for receiving a response from the AI ​​based on its areas of specialization; means for creating an optimal consultation based on its areas of specialization; means for transmitting the consultation to the AI ​​and receiving a response; means for analyzing the response to identify areas for improvement; means for executing the next cycle based on the areas for improvement; means for creating a consultation regarding the optimization of an advertising campaign and analyzing the response from the AI; and means for improving the storytelling and targeting strategies of the advertising campaign based on the response. This enables effective utilization of the AI's areas of expertise and optimizes advertising campaigns.

[0694] "Generative artificial intelligence with a specialized field" refers to generative artificial intelligence that possesses advanced capabilities in a specific field.

[0695] "Means of inquiring about specialized fields" refers to methods or functions for asking generative artificial intelligence which fields it is proficient in.

[0696] "Means of receiving responses" refers to methods or functions for obtaining responses from generative artificial intelligence.

[0697] "Means for creating consultation content" refers to methods and functions for creating appropriate questions and requests based on specialized fields obtained from generative artificial intelligence.

[0698] "Means for sending consultation content and receiving responses" refers to methods and functions for sending created consultation content to generative artificial intelligence and obtaining its responses.

[0699] "Means for analyzing responses and identifying areas for improvement" refers to methods and functions for analyzing responses from generative artificial intelligence and finding areas that need improvement.

[0700] "Means for executing the next cycle" refers to the methods and functions for executing the next process, taking into account the improvements that have been made.

[0701] "Advertising campaign optimization" is the process of improving the content and strategy of an advertisement in order to maximize its effectiveness.

[0702] "Storytelling" is an advertising technique that uses stories and episodes to attract customer interest and effectively convey a message.

[0703] A "targeting strategy" is a method or plan for effectively delivering advertisements to a specific consumer group.

[0704] This invention is a system that optimizes advertising campaigns using generative artificial intelligence. Users utilize user devices such as smartphones and interact with the generative artificial intelligence to achieve effective advertising campaigns. This system operates with the following configuration and configuration.

[0705] System Configuration

[0706] 1. User terminal

[0707] It is a computer or mobile device operated by a user.

[0708] For example, the system can be accessed through a smartphone application.

[0709] 2. Server

[0710] It works in conjunction with generative artificial intelligence and operates in a cloud-based or local data center.

[0711] The server is equipped with a program for accessing the API of generative artificial intelligence.

[0712] Processing flow

[0713] 1. Initialization

[0714] The user initializes the application and sets the necessary API keys.

[0715] Specific example: A user launches a smartphone app and enters an API key.

[0716] 2. Selection of areas of expertise

[0717] The server sends a query to the generative artificial intelligence asking about its area of ​​expertise.

[0718] The server receives the response and records its areas of expertise.

[0719] Specific example: The server asks the generative AI, "What is your area of ​​expertise in advertising?" and the generative AI responds, "I'm good at targeted advertising."

[0720] 3. Refine the details of the consultation.

[0721] The server automatically generates appropriate consultation content for the generative artificial intelligence based on its area of ​​expertise.

[0722] Specific example: A question is generated asking, "What are the optimal content and strategies for targeted advertising?"

[0723] 4. Implementing the content of the consultation

[0724] The user sends their inquiry to a generative artificial intelligence from their terminal and receives a response.

[0725] Specific example: A user's device sends a question to a generative artificial intelligence, and receives a response such as, "Storytelling and personalized advertising relevant to your target audience would be effective."

[0726] 5. Analysis of results and creation of improvement plans

[0727] The server analyzes the response from the generative artificial intelligence and identifies areas for improvement.

[0728] Based on the improvements identified, we will execute the next cycle.

[0729] Specific example: Analyze the response and formulate an improvement plan for the next consultation, such as "asking for specific examples of storytelling."

[0730] Hardware and software to be used

[0731] Hardware:

[0732] User devices: Smartphones, tablets, PCs, etc.

[0733] Servers: Cloud-based data centers, local servers

[0734] software:

[0735] APIs for generative artificial intelligence (e.g., OpenAI API)

[0736] Data collection and analysis tools (e.g., Python-based scripts)

[0737] Example of a prompt

[0738] "Could you give me some specific examples of storytelling in targeted advertising?"

[0739] This invention makes it possible to effectively utilize the strengths of generative artificial intelligence to automatically optimize the storytelling and targeting strategies of advertising campaigns.

[0740] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0741] Step 1:

[0742] Initialization

[0743] Subject: User

[0744] Specific operation: The user launches the smartphone application and enters the required API key.

[0745] Input: API key

[0746] Output: API key setup complete

[0747] Processing details: Store the API key within the application and prepare for integration with generative artificial intelligence.

[0748] Step 2:

[0749] Selection of areas of expertise

[0750] Subject: Server

[0751] Specific operation: The server sends a query to the generative artificial intelligence: "What is your expertise in the advertising field?"

[0752] Input: Query "What is your area of ​​expertise in advertising?"

[0753] Output: Response from generative artificial intelligence (e.g., "I'm good at targeted advertising")

[0754] Processing details: Receive and record responses related to the generative artificial intelligence's area of ​​expertise.

[0755] Step 3:

[0756] Refinement of the consultation content

[0757] Subject: Server

[0758] Specific operation: The server automatically generates appropriate consultation content based on its area of ​​expertise.

[0759] Input: Response indicating your area of ​​expertise (e.g., "I specialize in targeted advertising.")

[0760] Output: Consultation content (Example: "What are the optimal content and strategies for targeted advertising?")

[0761] Processing details: Based on the area of ​​expertise, construct more detailed questions for the generative artificial intelligence.

[0762] Step 4:

[0763] Implementation of the consultation

[0764] Subject: terminal

[0765] Specific operation: The user sends the consultation content from their terminal to a generative artificial intelligence and retrieves the results.

[0766] Input: Question (Example: "What are the optimal content and strategies for targeted advertising?")

[0767] Output: Response from generative artificial intelligence (e.g., "Storytelling and personalized advertising relevant to your target audience are effective")

[0768] Processing details: The consultation content is sent, and the received response is saved within the application.

[0769] Step 5:

[0770] Analysis of results and creation of improvement plans

[0771] Subject: Server

[0772] Specific operation: The server analyzes the response from the generative artificial intelligence and identifies areas for improvement.

[0773] Input: Response from generative artificial intelligence (e.g., "Storytelling and personalized advertising relevant to your target audience are effective")

[0774] Output: Suggestions for improvement to be reflected in the next consultation (e.g., "Request specific examples of storytelling")

[0775] Processing details: Analyze the response and identify areas for improvement in the next consultation.

[0776] Step 6:

[0777] Execute the next cycle

[0778] Subject: Server and terminal

[0779] Specific operation: The server refines the content of the next consultation based on the improvement suggestions, and then the user terminal queries the generative artificial intelligence again.

[0780] Input: Suggestion for improvement (Example: "Please provide specific examples of storytelling.")

[0781] Output: New inquiry topic (Example: "Please provide specific examples of storytelling in targeted advertising.")

[0782] Processing details: Based on the improvement suggestions, new consultation topics are generated, and this process is repeated to continuously optimize the advertising campaign.

[0783] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0784] This invention is a system that utilizes generative artificial intelligence (AI) and, by combining it with user emotion recognition, generates optimal consultation content based on the user's area of ​​expertise and implements a PDCA cycle for continuous improvement. The specific configuration, operation, and series of processes of the system are described below.

[0785] System Configuration

[0786] 1. User terminal

[0787] It is a computer or mobile device used by a user to operate a system.

[0788] Inquiries and consultations are sent from the user's terminal to the generative AI.

[0789] 2. Server

[0790] It is a cloud-based or local server that works in conjunction with generative AI to perform tasks such as analyzing inquiries and responses in its area of ​​expertise, recognizing emotions, and identifying areas for improvement.

[0791] The server is equipped with a program and emotion engine for accessing the generative AI API.

[0792] 3. Emotional Engine

[0793] This engine recognizes user emotions and optimizes the responses and consultation content of generative AI according to the user's emotional state.

[0794] Program processing

[0795] 1. Initialization

[0796] The user creates an instance of the AI ​​assistant and sets the necessary API key.

[0797] 2. Selection of areas of expertise

[0798] The server sends a query to the generative AI, asking about its area of ​​expertise.

[0799] Generative AI responds by returning its area of ​​expertise (for example, "natural language processing").

[0800] The server records this response and uses it in the next step.

[0801] 3. Refine the details of the consultation.

[0802] The server automatically creates the most suitable consultation content based on its area of ​​expertise.

[0803] Furthermore, an emotion engine is used to analyze the user's current emotional state and adjust the consultation content accordingly.

[0804] For example, if a user is feeling stressed, the content of their consultation will be adjusted to be concise and easy to understand.

[0805] 4. Implementing the content of the consultation

[0806] The user terminal sends the generated consultation content to the generative AI.

[0807] The generative AI will provide a response to this inquiry.

[0808] The server receives and records the response.

[0809] 5. Analysis of results and creation of improvement plans

[0810] The server analyzes the response from the generative AI and identifies areas for improvement.

[0811] An emotion engine is used to consider the user's emotional state during response analysis. For example, if the user was not satisfied with the previous response, an improvement plan will be developed that provides more specific information for the next response.

[0812] These improvement suggestions will be implemented in the next cycle.

[0813] Specific example

[0814] scenario:

[0815] Users want to use generative AI to find the optimal method for generating text.

[0816] 1. Initialization

[0817] The user initializes the AI ​​assistant and sets the API key.

[0818] 2. Selection of areas of expertise

[0819] The server sends a query to the generative AI: "What are your specializations?"

[0820] The generative AI responded, "I'm good at natural language processing."

[0821] The server records its areas of expertise and moves on to the next step.

[0822] 3. Refine the details of the consultation.

[0823] The server generates the question, "What is the optimal text generation method in natural language processing?" based on "natural language processing."

[0824] The emotion engine analyzes the user's emotional state to determine whether the user is particularly interested, relaxed, etc.

[0825] When the user is relaxed, the information is adjusted to be more detailed.

[0826] 4. Implementing the content of the consultation

[0827] The user sends their consultation request to the generative AI from their terminal.

[0828] The generative AI responded, "Methods using GPT-3 or Transformers are optimal."

[0829] The server receives and records the response.

[0830] 5. Analysis of results and creation of improvement plans

[0831] The server analyzes the response and identifies the following areas for improvement.

[0832] The user's emotional state will be re-analyzed, and the content of the next consultation and the method of providing responses will be adjusted accordingly.

[0833] For example, in the next cycle, we could formulate questions that ask for specific implementation examples.

[0834] Thus, the system of the present invention, by using generative AI and an emotion engine, can generate optimal consultation content that takes into account the user's emotional state, continuously improve it, and make maximum use of the strengths of generative AI.

[0835] The following describes the processing flow.

[0836] Step 1:

[0837] The user creates an instance of the AI ​​assistant and sets the necessary API keys. This prepares them to utilize the generative AI and emotion engine.

[0838] python

[0839] ai_assistant = AIAssistant(api_key="your_api_key_here")

[0840] Step 2:

[0841] The server sends a query to the generative AI asking about its areas of expertise. This query is in the form of "What are your specializations?". The generative AI responds by returning its area of ​​expertise (for example, "natural language processing").

[0842] python

[0843] specialty = ai_assistant.get_specialty()

[0844] The server calls a generative AI API, sends questions related to its area of ​​expertise, and receives and records the responses.

[0845] Step 3:

[0846] The server creates the most suitable consultation content based on its identified areas of expertise. During this process, an emotion engine is used to analyze the user's emotional state and adjust the consultation content accordingly.

[0847] python

[0848] consultation = ai_assistant.refine_consultation()

[0849] The server automatically generates consultation content based on its area of ​​expertise, and the emotion engine analyzes the user's emotional state to adjust the consultation content. For example, if the user is feeling stressed, the consultation content will be adjusted to be concise and easy to understand.

[0850] Step 4:

[0851] The user's terminal sends the generated consultation content to the generative AI. For example, it might send the question, "What is the optimal text generation method in natural language processing?"

[0852] python

[0853] response = ai_assistant.consult_ai(consultation)

[0854] The user terminal sends questions to the generative AI via the server.

[0855] Step 5:

[0856] The server receives a response from the generative AI. For example, it might receive a response such as, "Methods using GPT-3 or Transformers are optimal."

[0857] python

[0858] response = "GPT-3 and Transformers"

[0859] The server will record this response.

[0860] Step 6:

[0861] The server analyzes the response from the generative AI and identifies areas for improvement. At this time, it uses an emotion engine to re-analyze the user's emotional state and determine areas for improvement in the next cycle.

[0862] python

[0863] ai_assistant.implement_and_improve(response)

[0864] The server analyzes the response in detail, and the emotion engine analyzes the user's emotional state to identify areas for improvement. For example, if the user was not satisfied with the previous response, the system will develop an improvement plan that provides more specific information next time.

[0865] Step 7:

[0866] The user repeats these steps, continuously running the PDCA cycle. This allows the system to continuously generate consultation content that maximizes the strengths of generative AI and the user's emotional state.

[0867] python

[0868] ai_assistant.run_pdca_cycle()

[0869] The server continuously executes a series of steps from get_specialty to implement_and_improve to optimize the performance of the generative AI.

[0870] As described above, the system of the present invention combines generative AI and an emotion engine to generate optimal consultation content that takes into account the user's emotional state, and can make maximum use of the strengths of generative AI while continuously improving it.

[0871] (Example 2)

[0872] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0873] Existing generative knowledge systems provide information without considering the user's emotional state, making it difficult to generate appropriate consultation content and improve the quality of responses. As a result, users are unable to obtain the information they need, and continuous improvement is not possible.

[0874] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for querying a generative knowledge system that includes areas of expertise for a specialized field; means for receiving a response from the generative knowledge system based on the specialized field; means for generating optimal consultation content based on the specialized field; means for transmitting the consultation content to the generative knowledge system and receiving a response; means for analyzing the response and identifying areas for improvement; means for executing the next cycle based on the areas for improvement; means including an engine for analyzing the user's emotional state; and means for adjusting the consultation content based on the emotional state. This makes it possible to generate optimal consultation content that takes the user's emotional state into consideration and to continuously improve it.

[0875] A "specialized area" refers to a specialized field in which a generative knowledge system excels in terms of knowledge and capabilities.

[0876] A "generative knowledge system" is an artificial intelligence system that generates and provides information based on user inquiries.

[0877] A "specialized field" refers to an area that requires advanced knowledge and skills in a specific area.

[0878] A "response" is the information or answer that a generative knowledge system provides in response to a query from a user or server.

[0879] "Consultation content" refers to the specific questions or requests that a user submits to a generative knowledge system.

[0880] A "cycle" refers to a series of processes involving generating the content of a consultation, obtaining a response, analyzing the response, identifying areas for improvement, and implementing improvements for the next session.

[0881] An "emotion engine" is a component that analyzes the user's emotional state and adjusts the information and responses generated based on the results.

[0882] "Emotional state" refers to the emotions and psychological state a user is experiencing at a given point in time.

[0883] "Analysis" refers to the information processing used to evaluate responses from generative knowledge systems and identify areas for improvement.

[0884] "Improvements" refer to changes or enhancements identified to improve the response from a generative knowledge system.

[0885] This invention is a system that utilizes a generative knowledge system and an emotion engine. It considers the user's emotional state, generates optimal consultation content based on their areas of expertise, and implements a PDCA cycle for continuous improvement. The specific configuration and operation of this system will be described below.

[0886] System Configuration

[0887] 1. User terminal:

[0888] This is a computer or mobile device used by users to operate the system. Inquiries and consultations are sent from the user terminal to the generative knowledge system.

[0889] 2. Server:

[0890] It is a cloud-based or local server that works in conjunction with generative knowledge systems to perform tasks such as analyzing inquiries and responses in its area of ​​expertise, recognizing sentiment, and identifying areas for improvement. The server is equipped with programs and a sentiment engine to access the generative knowledge system's API.

[0891] 3. Emotional Engine:

[0892] This engine recognizes user emotions and optimizes the responses and consultation content of generative knowledge systems according to the user's emotional state.

[0893] Specific examples of actions

[0894] scenario:

[0895] Let's take the example of a user who wants to use a generative knowledge system to find the optimal method for generating text.

[0896] 1. Initialization:

[0897] The user initializes the AI ​​assistant and sets the necessary API keys.

[0898] For example, a user might open an application on their device and go through the steps of setting up an API key for a generative knowledge system.

[0899] 2. Selecting your area of ​​expertise:

[0900] The server sends the prompt "What are your specializations?" to the generative knowledge system. The generative knowledge system responds "I specialize in natural language processing," and the server records the area of ​​expertise.

[0901] 3. Refine the details of the consultation:

[0902] The server generates a consultation question based on its area of ​​expertise, asking "What is the optimal text generation method in natural language processing?" Furthermore, the emotion engine analyzes the user's emotional state, and if, for example, the user is feeling stressed, it adjusts the consultation question to be concise and easy to understand.

[0903] 4. Implementing the plan discussed:

[0904] The user terminal sends the generated consultation content to the generative knowledge system. The generative knowledge system responds with "A method using GPT-3 or Transformers is optimal," and the server receives and records the response.

[0905] 5. Analysis of results and development of improvement plans:

[0906] The server analyzes the response and identifies areas for improvement. For example, it re-analyzes the user's emotional state, and if the user was not satisfied with the previous response, it develops an improvement plan to provide more specific information next time. This improvement plan will be implemented in the next PDCA cycle.

[0907] Hardware and software to be used

[0908] Hardware: Computers, mobile devices, cloud-based or local servers

[0909] Software: APIs for generative knowledge systems (e.g., OpenAI), emotion engines, user interfaces

[0910] Examples of prompt statements

[0911] Prompt for selecting your area of ​​specialization: "What are your specializations?"

[0912] Prompt for generating consultation content: "What is the optimal text generation method in natural language processing?"

[0913] By implementing this invention, users can generate optimal consultation content that takes their emotional state into consideration and obtain high-quality responses by making full use of the strengths of generative knowledge systems. Furthermore, continuous improvement can be expected, leading to an enhanced user experience.

[0914] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0915] Step 1:

[0916] Initialization

[0917] The user starts up their device and opens a dedicated application. Next, the user enters the API key for the generative knowledge system within the application. This establishes a connection to the generative knowledge system, enabling subsequent data processing. The input is the API key, and the output is the connection status with the generative knowledge system.

[0918] Step 2:

[0919] Selection of areas of expertise

[0920] The server sends the prompt "What are your specializations?" to the generative knowledge system. Based on this prompt, the generative knowledge system responds with its area of ​​expertise (for example, "natural language processing"). The input is the prompt "What are your specializations?", and the output is the response from the generative knowledge system. The server records this response.

[0921] Step 3:

[0922] Refinement of the consultation content

[0923] The server generates consultation content based on its areas of expertise obtained in the previous step. For example, based on "natural language processing," it generates the question, "What is the optimal text generation method in natural language processing?" Next, the emotion engine analyzes the user's emotional state. For example, if it determines that the user is feeling stressed, it reorganizes the generated question to be concise and easy to understand. The input consists of prompt sentences based on the areas of expertise and data on the emotional state, and the output is the optimized consultation content.

[0924] Step 4:

[0925] Implementation of the consultation

[0926] The user terminal sends the generated inquiry content to the generative knowledge system. The generative knowledge system returns a specific response to this inquiry content. For example, if the inquiry content is "What is the optimal text generation method in natural language processing?", the response would be "Methods using GPT-3 or Transformers are optimal." The input is the optimized inquiry content, and the output is the response from the generative knowledge system. The server records this response.

[0927] Step 5:

[0928] Analysis of results and creation of improvement plans

[0929] The server analyzes the response from the generative knowledge system and evaluates its quality. Furthermore, it uses an emotion engine to re-analyze the user's emotional state and determine whether the user was satisfied with the response. For example, if the user was not satisfied with the response, the server develops improvement suggestions to make the next consultation more specific and detailed. The input is the previous response and the user's emotional data, and the output is improvement suggestions for the next cycle.

[0930] Through the specific processing steps described above, the system can generate optimal consultation content while considering the user's emotional state, utilizing the strengths of generative knowledge systems, and continuously improve its process.

[0931] (Application Example 2)

[0932] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0933] Many modern content delivery systems provide users with uniform content, making it difficult to suggest content that is optimal for each user's emotional state and preferences. This degrades the quality of the user experience and reduces their willingness to consume content. Furthermore, the lack of mechanisms to improve future suggestions based on feedback on the content provided prevents continuous personalization.

[0934] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for querying a generative artificial intelligence, including its areas of expertise, for its areas of expertise; means for receiving a response from the generative artificial intelligence based on the areas of expertise; means for creating optimal consultation content based on the areas of expertise; means for recognizing the user's emotions and optimizing the consultation content according to the recognized emotional state; means for transmitting the consultation content to the generative artificial intelligence and receiving a response; means for analyzing the response and identifying areas for improvement; and means for executing the next cycle based on the areas for improvement. This enables optimal content suggestions based on the user's emotional state and areas of expertise, as well as continuous improvement based on feedback.

[0935] "Generative artificial intelligence" is an artificial intelligence technology that uses specialized knowledge and information in a particular field to provide optimal answers and suggestions to user inquiries.

[0936] A "user terminal" is a computer or mobile device used by a user to operate the system and send inquiries and consultations to the generative artificial intelligence.

[0937] A "server" is a network-based computer system that works in conjunction with generative artificial intelligence to conduct research in specialized fields, recognize emotions, analyze responses, and identify improvement suggestions.

[0938] An "emotion engine" is software that recognizes the user's emotions and optimizes the responses and consultation content of generative artificial intelligence based on that emotional state.

[0939] A "specialized field" refers to an area of ​​technology or knowledge in which generative artificial intelligence excels, and is a field in which it possesses a deep understanding.

[0940] "Consultation content" refers to the specific questions or concerns that the user submits to the generative artificial intelligence.

[0941] "Response" refers to the answers or suggestions that generative artificial intelligence provides in response to a user's inquiry.

[0942] A "specialty area" refers to a specific field in which generative artificial intelligence possesses particularly specialized knowledge or skills.

[0943] "Optimization" refers to the process of adjusting and improving the responses and consultation content of generative artificial intelligence to the best possible form, based on the user's emotional state and area of ​​expertise.

[0944] "Areas for improvement" refers to points of modification or adjustment identified to improve the quality of the generative artificial intelligence's responses.

[0945] "Feedback" refers to evaluations and impressions of responses provided by users, and serves as information to improve future responses.

[0946] This invention is a system that uses generative artificial intelligence combined with user emotion recognition to suggest optimal content. The specific configuration, operation, and process of the system are described below.

[0947] System Configuration

[0948] 1. User terminal

[0949] It is a computer or mobile device used by the user to operate the system and send inquiries and consultations to generative artificial intelligence.

[0950] 2. Server

[0951] It is a networked computer system that works in conjunction with generative artificial intelligence to conduct research in specialized fields, recognize emotions, analyze responses, and identify improvement suggestions.

[0952] 3. Emotional Engine

[0953] This software recognizes the user's emotions and optimizes the responses and consultation content of generative artificial intelligence based on that emotional state.

[0954] Program processing

[0955] This system will be implemented using the following hardware and software:

[0956] Hardware:

[0957] Smartphones (iPhone and Android devices)

[0958] Network Server

[0959] software:

[0960] EmotionRecognizer: A library for recognizing user emotions. In this case, it uses OpenCV or Dlib to analyze facial expressions.

[0961] ContentSelector: A library for suggesting content. It utilizes APIs from generative artificial intelligence (such as GPT-3).

[0962] FeedbackAnalyzer: A library for analyzing user feedback and incorporating it into future suggestions.

[0963] Specific implementation methods

[0964] 1. Recognizing user emotions:

[0965] The user uses their smartphone's camera and microphone to send their facial expressions and voice to the system, which EmotionRecognizer analyzes to recognize emotions.

[0966] 2. Selection of a field of specialization:

[0967] The ContentSelector on the server queries the generative artificial intelligence (AI) for its area of ​​expertise, identifying its strengths. For example, it might ask the AI, "What are your specializations?"

[0968] 3. Content proposals:

[0969] The server suggests the most suitable content based on the user's perceived emotional state and areas of expertise. For example, if the user is relaxed, it might suggest a "comedy movie."

[0970] 4. Gathering and analyzing feedback:

[0971] FeedbackAnalyzer collects feedback from users who have viewed the suggested content and uses this feedback to improve future suggestions.

[0972] Specific example

[0973] Example of a prompt

[0974] "You seem relaxed right now. What's the best movie to watch next?"

[0975] Usage Scenarios

[0976] The user opens the app and points their face in front of the camera.

[0977] The app analyzes the user's facial expressions and identifies the emotion of "relaxation."

[0978] I've chosen "comedy films" as my area of ​​expertise.

[0979] The app recommends the movie "The Grand Budapest Hotel".

[0980] Users provide "satisfied" feedback after watching a movie.

[0981] Next time, the app will enhance its recommendations for more relaxing comedy movies.

[0982] Thus, the system of the present invention enables optimal content suggestions based on the user's emotional state and areas of expertise, as well as continuous improvement based on feedback.

[0983] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0984] Step 1:

[0985] The user launches the application on their smartphone and records their current state via the camera or microphone. The input consists of the user's facial expressions and voice data. EmotionRecognizer analyzes this data and recognizes emotions from the facial expressions and voice. The output is the emotional state (e.g., relaxed, stressed).

[0986] Step 2:

[0987] The server queries a generative artificial intelligence (AI) about its areas of expertise. The input is a query about areas of expertise (e.g., "What are your specializations?"). The generative AI responds by returning its areas of expertise. This response is analyzed by the server to identify its areas of expertise (e.g., comedy films). The output is information about its areas of expertise.

[0988] Step 3:

[0989] The server creates the most suitable consultation content based on the emotional state and areas of expertise it recognizes. The input is the emotional state and areas of expertise. The server generates a prompt based on this (e.g., "You seem relaxed now. What movie would be best to watch next?"). The output is the generated prompt.

[0990] Step 4:

[0991] The server sends a generated prompt to the generative artificial intelligence (AI). The input is the generated prompt. The generative AI generates a response to this prompt and returns the most suitable content suggestion (e.g., a suggestion for the movie "The Grand Budapest Hotel"). The output is the response from the generative AI.

[0992] Step 5:

[0993] The user terminal displays the response received from the server and provides content suggestions to the user. The input is the response from the generative artificial intelligence. The user terminal receives this and displays it on the screen. The output is the content suggestions displayed to the user.

[0994] Step 6:

[0995] Users view the provided content and then provide feedback. The input is the user's feedback (e.g., "satisfied" or "dissatisfied"). The feedback is sent to the server via the user's device. The output is the user's feedback data.

[0996] Step 7:

[0997] The server analyzes user feedback and generates instructions to improve future suggestions. The input consists of user feedback data and suggested content information. The server's FeedbackAnalyzer analyzes this data and identifies areas for improvement in the response. The output is a list of improvements for the next cycle.

[0998] As described above, by clearly defining the specific actions, inputs, and outputs at each step, the system's processing flow can be explained in detail. This enables the system to provide optimal content suggestions based on the user's emotional state and areas of expertise.

[0999] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1000] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1001] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[1002] [Third Embodiment]

[1003] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[1004] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1005] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1006] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[1007] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1008] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1009] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1010] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1011] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1012] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1013] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1014] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[1015] This invention is a system utilizing generative artificial intelligence (AI), and its purpose is to implement a PDCA cycle to optimally utilize the strengths of generative AI, which is constantly evolving. The specific configuration, operation, and series of processes of the system are described below.

[1016] System Configuration

[1017] 1. User terminal

[1018] It is a computer or mobile device used by a user to operate a system.

[1019] Inquiries and consultations are sent from the user's terminal to the generative AI.

[1020] 2. Server

[1021] It is a cloud-based or local server that works in conjunction with generative AI to analyze inquiries and responses in its area of ​​expertise, and identify areas for improvement.

[1022] The server is equipped with a program to access the generative AI API.

[1023] Program processing

[1024] 1. Initialization

[1025] The user creates an instance of the AI ​​assistant and sets the necessary API key.

[1026] 2. Selection of areas of expertise

[1027] The server sends a query to the generative AI asking about its areas of expertise.

[1028] The generative AI responds by returning a response related to its area of ​​expertise (for example, "natural language processing").

[1029] The server records this response and uses it in the next step.

[1030] 3. Refine the details of the consultation.

[1031] The server automatically generates appropriate consultation content for the generative AI based on its area of ​​expertise.

[1032] For example, if your area of ​​expertise is "natural language processing," you would create a consultation request such as, "What is the optimal technique for natural language processing?"

[1033] 4. Implementing the content of the consultation

[1034] The user terminal sends the generated consultation content to the generative AI.

[1035] The generative AI will provide a response to this inquiry.

[1036] The server receives and records the response.

[1037] 5. Analysis of results and creation of improvement plans

[1038] The server analyzes the response from the generative AI and identifies areas for improvement.

[1039] For example, you could come up with a plan to improve by saying, "Next time, I'll ask questions that include specific technical examples."

[1040] These improvement suggestions will be implemented in the next cycle.

[1041] Specific example

[1042] scenario:

[1043] Users want to use generative AI to find the optimal method for generating text.

[1044] 1. Initialization

[1045] The user initializes the AI ​​assistant and sets the API key.

[1046] ai_assistant = AIAssistant(api_key="your_api_key_here")

[1047] 2. Selection of areas of expertise

[1048] The server sends a query to the generative AI: "What are your specializations?"

[1049] The generative AI responded, "I'm good at natural language processing."

[1050] The server records its areas of expertise and moves on to the next step.

[1051] 3. Refine the details of the consultation.

[1052] The server generates a question based on "natural language processing": "What is the optimal text generation method in natural language processing?"

[1053] 4. Implementing the content of the consultation

[1054] The user sends their consultation request to the generative AI from their terminal.

[1055] The generative AI responded, "Methods using GPT-3 or Transformers are optimal."

[1056] The server receives and records the response.

[1057] 5. Analysis of results and creation of improvement plans

[1058] The server analyzes the response and identifies a suggestion for improvement: "Next time, please provide specific technical examples."

[1059] We will utilize this improvement plan in the next cycle.

[1060] By repeating this process, it is possible to optimally utilize the strengths of generative AI and continuously improve it to obtain effective responses.

[1061] The following describes the processing flow.

[1062] Step 1:

[1063] The user creates an instance of the AI ​​assistant and sets the necessary API keys. This prepares it to communicate with the generative AI.

[1064] python

[1065] ai_assistant = AIAssistant(api_key="your_api_key_here")

[1066] Step 2:

[1067] The server sends a query to the generative AI asking about its areas of expertise. This query is in the format of "What are your specializations?".

[1068] python

[1069] specialty = ai_assistant.get_specialty()

[1070] Specifically, the server calls an AI API and sends a question related to its area of ​​expertise.

[1071] Step 3:

[1072] The server receives a response from the generative AI and identifies its area of ​​expertise. For example, it might receive a response such as "natural language processing."

[1073] python

[1074] Specialty = "Natural Language Processing"

[1075] The server records the response and uses it in the next step.

[1076] Step 4:

[1077] The server creates the most suitable consultation content based on its identified area of ​​expertise. For example, based on "natural language processing," it might generate a question such as, "What is the best text generation method in natural language processing?"

[1078] python

[1079] consultation = ai_assistant.refine_consultation()

[1080] In terms of specific operations, the server automatically generates consultation content based on its areas of expertise.

[1081] Step 5:

[1082] The user sends the generated consultation content from their terminal to the generative AI. For example, they might send a question such as, "What is the optimal text generation method in natural language processing?"

[1083] python

[1084] response = ai_assistant.consult_ai(consultation)

[1085] In terms of specific operations, the user's terminal sends a question to the generative AI via the server.

[1086] Step 6:

[1087] The server receives a response from the generative AI. For example, it might receive a response such as, "Methods using GPT-3 or Transformers are optimal."

[1088] python

[1089] response = "GPT-3 and Transformers"

[1090] The server will record this response.

[1091] Step 7:

[1092] The server analyzes the response from the generative AI and identifies areas for improvement. For example, it might formulate improvement suggestions for the next cycle, such as "requesting more specific technical examples."

[1093] python

[1094] ai_assistant.implement_and_improve(response)

[1095] Specifically, the server analyzes the received response in detail to identify areas for improvement for the next operation.

[1096] Step 8:

[1097] Users repeat these steps, continuously running the PDCA cycle. This allows them to maximize the strengths of generative AI.

[1098] python

[1099] ai_assistant.run_pdca_cycle()

[1100] Specifically, the server continuously executes a series of steps from get_specialty to implement_and_improve to optimize the performance of the generative AI.

[1101] As described above, the system of the present invention utilizes generative AI and can effectively implement the PDCA cycle to obtain the optimal response in a specialized field.

[1102] (Example 1)

[1103] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1104] In recent years, advancements in generative artificial intelligence (AI) have led to its effective use in various fields. However, it remains challenging to predict which fields generative AI will function most appropriately, requiring significant effort to optimize the content of consultations. Furthermore, there is a need to effectively analyze responses from generative AI and incorporate them into the next cycle, but methods for doing so have not yet been established.

[1105] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1106] In this invention, the server includes means for querying a generative artificial intelligence (AI) about its area of ​​expertise, including its area of ​​specialization; means for receiving a response from the AI ​​based on its area of ​​expertise; means for automatically generating the optimal consultation content based on its area of ​​expertise; means for transmitting the consultation content to the AI ​​and receiving a response; means for analyzing the response and identifying areas for improvement in the next cycle; and means for executing the next cycle incorporating the areas for improvement. This makes it possible to automate the PDCA cycle to optimally utilize the AI's area of ​​expertise and obtain effective responses.

[1107] A "specialized field" refers to a specialized area in which generative artificial intelligence exhibits particularly high performance.

[1108] "Generative artificial intelligence" refers to an artificial intelligence system that has the ability to generate text and data in response to user questions and requests.

[1109] A "specialized field" refers to a specialized area that requires specific knowledge or skills.

[1110] "Consultation content" refers to the questions or requests that users make to the generative artificial intelligence.

[1111] "Response" refers to the information that generative artificial intelligence provides in response to the user's inquiry.

[1112] A "server" refers to a computer system that works in conjunction with generative artificial intelligence to process and manage data.

[1113] "Analysis" refers to the act of examining in detail the responses obtained from generative artificial intelligence and evaluating their content and quality.

[1114] "The next cycle" refers to a new PDCA cycle that begins after the current PDCA cycle is completed.

[1115] The "PDCA cycle" refers to a management cycle consisting of four steps—Plan, Do, Check, and Act—with the aim of improving processes.

[1116] This invention is a system that uses generative artificial intelligence to automatically generate optimal consultation content in specialized fields, and then executes and improves the PDCA cycle based on that content. The system primarily operates through the coordinated operation of server, terminal, and user components.

[1117] System Configuration

[1118] 1. User terminal

[1119] It is a computer or mobile device used by a user to operate a system.

[1120] The user terminal can send inquiries and consultation requests to the generative artificial intelligence.

[1121] 2. Server

[1122] It is a cloud-based or local server that works in conjunction with generative artificial intelligence to perform tasks such as answering inquiries in specialized fields, analyzing responses, and identifying areas for improvement.

[1123] The server is equipped with a program for accessing the API of generative artificial intelligence.

[1124] Program processing

[1125] When a user uses the system, they first create an instance of the AI ​​assistant and configure the necessary API keys. This allows them to access generative artificial intelligence.

[1126] The server sends a query to the generative artificial intelligence (AI) asking about its areas of expertise. The AI ​​responds by listing its areas of expertise, and the server records this response.

[1127] The server automatically generates appropriate consultation questions based on its area of ​​expertise. For example, if its area of ​​expertise is "natural language processing," it will create a consultation question such as, "What is the optimal technique for natural language processing?"

[1128] The terminal sends the generated consultation content to the generative artificial intelligence, which then returns a response to this consultation. The server receives and records this response.

[1129] The server analyzes the response from the generative artificial intelligence and identifies areas for improvement. For example, it might create improvement suggestions such as, "Next time, I will ask questions that include specific technical examples." These improvement suggestions will be reflected in the next PDCA cycle.

[1130] Specific example

[1131] Initialization example

[1132] Example of a user initializing an AI assistant and setting an API key:

[1133] python

[1134] ai_assistant = AIAssistant(api_key="your_api_key_here")

[1135] Examples of selecting areas of expertise

[1136] The server sends the query "What are your specializations?" to the generative AI, and the generative AI responds "I specialize in natural language processing."

[1137] Examples of refining the content of the consultation

[1138] The server generates a question based on "natural language processing": "What is the optimal text generation method in natural language processing?"

[1139] Examples of implementing the consultation content

[1140] The terminal sends the consultation request to the generative artificial intelligence, which responds with "A method using GPT-3 or Transformers is optimal." The server receives and records this response.

[1141] This will allow for continuous improvement to optimally utilize the strengths of generative artificial intelligence and obtain effective responses.

[1142] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1143] Step 1:

[1144] Initialization

[1145] The user creates an instance of the AI ​​assistant and sets up an API key.

[1146] Input: API key from the user.

[1147] Data processing: Creating an instance of the AI ​​assistant, setting up the API key.

[1148] Output: An initialized instance of the AI ​​assistant.

[1149] Specific operation: The user enters `ai_assistant = AIAssistant(api_key="your_api_key_here")` to initialize the AI ​​assistant.

[1150] Step 2:

[1151] Selection of areas of expertise

[1152] The server sends a query to the generative artificial intelligence asking about its areas of expertise.

[1153] Input: Query "What are your specializations?".

[1154] Data processing: Sending queries and receiving responses from generative artificial intelligence.

[1155] Output: Responses related to areas of expertise (e.g., "natural language processing").

[1156] Specific operation: The server sends a query to the generative artificial intelligence and receives a response related to its area of ​​expertise.

[1157] Step 3:

[1158] Refinement of the consultation content

[1159] The server automatically generates appropriate consultation content for the generative artificial intelligence based on its area of ​​expertise.

[1160] Input: Area of ​​expertise (e.g., "Natural Language Processing").

[1161] Data processing: Generating consultation content based on areas of expertise.

[1162] Output: Generated question content (e.g., "What is the optimal text generation method in natural language processing?").

[1163] Specific operation: The server generates the consultation content based on its area of ​​expertise, "natural language processing."

[1164] Step 4:

[1165] Implementation of the consultation

[1166] The terminal sends the generated consultation content to a generative artificial intelligence and receives a response.

[1167] Input: Generated question (e.g., "What is the optimal text generation method in natural language processing?").

[1168] Data processing: Sending consultation content to a generative artificial intelligence and receiving responses.

[1169] Output: Response from generative artificial intelligence (e.g., "Methods using GPT-3 or Transformers are optimal").

[1170] Specific operation: The terminal sends the consultation content to a generative artificial intelligence, receives a response, and records it on the server.

[1171] Step 5:

[1172] Analysis of results and creation of improvement plans

[1173] The server analyzes the response from the generative artificial intelligence and identifies areas for improvement.

[1174] Input: Response from a generative artificial intelligence (e.g., "Methods using GPT-3 or Transformers are optimal").

[1175] Data processing: Response analysis, identification of areas for improvement.

[1176] Output: Suggestions for improvement (e.g., "Next time, I will ask questions including specific technical examples").

[1177] Specific operation: The server analyzes the response from the generative artificial intelligence and creates improvement suggestions to be implemented in the next cycle.

[1178] By executing these steps in sequence, it is possible to optimally utilize the strengths of generative artificial intelligence and realize a PDCA cycle to obtain effective responses.

[1179] (Application Example 1)

[1180] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1181] Currently, optimizing advertising campaigns is time-consuming and labor-intensive, and developing effective storytelling and targeting strategies requires specialized knowledge. Traditional methods, while utilizing generative artificial intelligence, lack a mechanism to effectively leverage its strengths while analyzing large amounts of data simultaneously, making it difficult to create optimal advertising campaigns. Therefore, there is a need for a system that leverages the strengths of generative AI to automatically optimize the storytelling and targeting strategies of advertising campaigns.

[1182] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1183] In this invention, the server includes means for querying a generative artificial intelligence (AI) about its areas of expertise, including its areas of specialization; means for receiving a response from the AI ​​based on its areas of specialization; means for creating an optimal consultation based on its areas of specialization; means for transmitting the consultation to the AI ​​and receiving a response; means for analyzing the response to identify areas for improvement; means for executing the next cycle based on the areas for improvement; means for creating a consultation regarding the optimization of an advertising campaign and analyzing the response from the AI; and means for improving the storytelling and targeting strategies of the advertising campaign based on the response. This enables effective utilization of the AI's areas of expertise and optimizes advertising campaigns.

[1184] "Generative artificial intelligence with a specialized field" refers to generative artificial intelligence that possesses advanced capabilities in a specific field.

[1185] "Means of inquiring about specialized fields" refers to methods or functions for asking generative artificial intelligence which fields it is proficient in.

[1186] "Means of receiving responses" refers to methods or functions for obtaining responses from generative artificial intelligence.

[1187] "Means for creating consultation content" refers to methods and functions for creating appropriate questions and requests based on specialized fields obtained from generative artificial intelligence.

[1188] "Means for sending consultation content and receiving responses" refers to methods and functions for sending created consultation content to generative artificial intelligence and obtaining its responses.

[1189] "Means for analyzing responses and identifying areas for improvement" refers to methods and functions for analyzing responses from generative artificial intelligence and finding areas that need improvement.

[1190] "Means for executing the next cycle" refers to the methods and functions for executing the next process, taking into account the improvements that have been made.

[1191] "Advertising campaign optimization" is the process of improving the content and strategy of an advertisement in order to maximize its effectiveness.

[1192] "Storytelling" is an advertising technique that uses stories and episodes to attract customer interest and effectively convey a message.

[1193] A "targeting strategy" is a method or plan for effectively delivering advertisements to a specific consumer group.

[1194] This invention is a system that optimizes advertising campaigns using generative artificial intelligence. Users utilize user devices such as smartphones and interact with the generative artificial intelligence to achieve effective advertising campaigns. This system operates with the following configuration and configuration.

[1195] System Configuration

[1196] 1. User terminal

[1197] It is a computer or mobile device operated by a user.

[1198] For example, the system can be accessed through a smartphone application.

[1199] 2. Server

[1200] It works in conjunction with generative artificial intelligence and operates in a cloud-based or local data center.

[1201] The server is equipped with a program for accessing the API of generative artificial intelligence.

[1202] Processing flow

[1203] 1. Initialization

[1204] The user initializes the application and sets the necessary API keys.

[1205] Specific example: A user launches a smartphone app and enters an API key.

[1206] 2. Selection of areas of expertise

[1207] The server sends a query to the generative artificial intelligence asking about its area of ​​expertise.

[1208] The server receives the response and records its areas of expertise.

[1209] Specific example: The server asks the generative AI, "What is your area of ​​expertise in advertising?" and the generative AI responds, "I'm good at targeted advertising."

[1210] 3. Refine the details of the consultation.

[1211] The server automatically generates appropriate consultation content for the generative artificial intelligence based on its area of ​​expertise.

[1212] Specific example: A question is generated asking, "What are the optimal content and strategies for targeted advertising?"

[1213] 4. Implementing the content of the consultation

[1214] The user sends their inquiry to a generative artificial intelligence from their terminal and receives a response.

[1215] Specific example: A user's device sends a question to a generative artificial intelligence, and receives a response such as, "Storytelling and personalized advertising relevant to your target audience would be effective."

[1216] 5. Analysis of results and creation of improvement plans

[1217] The server analyzes the response from the generative artificial intelligence and identifies areas for improvement.

[1218] Based on the improvements identified, we will execute the next cycle.

[1219] Specific example: Analyze the response and formulate an improvement plan for the next consultation, such as "asking for specific examples of storytelling."

[1220] Hardware and software to be used

[1221] Hardware:

[1222] User devices: Smartphones, tablets, PCs, etc.

[1223] Servers: Cloud-based data centers, local servers

[1224] software:

[1225] APIs for generative artificial intelligence (e.g., OpenAI API)

[1226] Data collection and analysis tools (e.g., Python-based scripts)

[1227] Example of a prompt

[1228] "Could you give me some specific examples of storytelling in targeted advertising?"

[1229] This invention makes it possible to effectively utilize the strengths of generative artificial intelligence to automatically optimize the storytelling and targeting strategies of advertising campaigns.

[1230] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1231] Step 1:

[1232] Initialization

[1233] Subject: User

[1234] Specific operation: The user launches the smartphone application and enters the required API key.

[1235] Input: API key

[1236] Output: API key setup complete

[1237] Processing details: Store the API key within the application and prepare for integration with generative artificial intelligence.

[1238] Step 2:

[1239] Selection of areas of expertise

[1240] Subject: Server

[1241] Specific operation: The server sends a query to the generative artificial intelligence: "What is your expertise in the advertising field?"

[1242] Input: Query "What is your area of ​​expertise in advertising?"

[1243] Output: Response from generative artificial intelligence (e.g., "I'm good at targeted advertising")

[1244] Processing details: Receive and record responses related to the generative artificial intelligence's area of ​​expertise.

[1245] Step 3:

[1246] Refinement of the consultation content

[1247] Subject: Server

[1248] Specific operation: The server automatically generates appropriate consultation content based on its area of ​​expertise.

[1249] Input: Response indicating your area of ​​expertise (e.g., "I specialize in targeted advertising.")

[1250] Output: Consultation content (Example: "What are the optimal content and strategies for targeted advertising?")

[1251] Processing details: Based on the area of ​​expertise, construct more detailed questions for the generative artificial intelligence.

[1252] Step 4:

[1253] Implementation of the consultation

[1254] Subject: terminal

[1255] Specific operation: The user sends the consultation content from their terminal to a generative artificial intelligence and retrieves the results.

[1256] Input: Question (Example: "What are the optimal content and strategies for targeted advertising?")

[1257] Output: Response from generative artificial intelligence (e.g., "Storytelling and personalized advertising relevant to your target audience are effective")

[1258] Processing details: The consultation content is sent, and the received response is saved within the application.

[1259] Step 5:

[1260] Analysis of results and creation of improvement plans

[1261] Subject: Server

[1262] Specific operation: The server analyzes the response from the generative artificial intelligence and identifies areas for improvement.

[1263] Input: Response from generative artificial intelligence (e.g., "Storytelling and personalized advertising relevant to your target audience are effective")

[1264] Output: Suggestions for improvement to be reflected in the next consultation (e.g., "Request specific examples of storytelling")

[1265] Processing details: Analyze the response and identify areas for improvement in the next consultation.

[1266] Step 6:

[1267] Execute the next cycle

[1268] Subject: Server and terminal

[1269] Specific operation: The server refines the content of the next consultation based on the improvement suggestions, and then the user terminal queries the generative artificial intelligence again.

[1270] Input: Suggestion for improvement (Example: "Please provide specific examples of storytelling.")

[1271] Output: New inquiry topic (Example: "Please provide specific examples of storytelling in targeted advertising.")

[1272] Processing details: Based on the improvement suggestions, new consultation topics are generated, and this process is repeated to continuously optimize the advertising campaign.

[1273] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1274] This invention is a system that utilizes generative artificial intelligence (AI) and, by combining it with user emotion recognition, generates optimal consultation content based on the user's area of ​​expertise and implements a PDCA cycle for continuous improvement. The specific configuration, operation, and series of processes of the system are described below.

[1275] System Configuration

[1276] 1. User terminal

[1277] It is a computer or mobile device used by a user to operate a system.

[1278] Inquiries and consultations are sent from the user's terminal to the generative AI.

[1279] 2. Server

[1280] It is a cloud-based or local server that works in conjunction with generative AI to perform tasks such as analyzing inquiries and responses in its area of ​​expertise, recognizing emotions, and identifying areas for improvement.

[1281] The server is equipped with a program and emotion engine for accessing the generative AI API.

[1282] 3. Emotional Engine

[1283] This engine recognizes user emotions and optimizes the responses and consultation content of generative AI according to the user's emotional state.

[1284] Program processing

[1285] 1. Initialization

[1286] The user creates an instance of the AI ​​assistant and sets the necessary API key.

[1287] 2. Selection of areas of expertise

[1288] The server sends a query to the generative AI, asking about its area of ​​expertise.

[1289] Generative AI responds by returning its area of ​​expertise (for example, "natural language processing").

[1290] The server records this response and uses it in the next step.

[1291] 3. Refine the details of the consultation.

[1292] The server automatically creates the most suitable consultation content based on its area of ​​expertise.

[1293] Furthermore, an emotion engine is used to analyze the user's current emotional state and adjust the consultation content accordingly.

[1294] For example, if a user is feeling stressed, the content of their consultation will be adjusted to be concise and easy to understand.

[1295] 4. Implementing the content of the consultation

[1296] The user terminal sends the generated consultation content to the generative AI.

[1297] The generative AI will provide a response to this inquiry.

[1298] The server receives and records the response.

[1299] 5. Analysis of results and creation of improvement plans

[1300] The server analyzes the response from the generative AI and identifies areas for improvement.

[1301] An emotion engine is used to consider the user's emotional state during response analysis. For example, if the user was not satisfied with the previous response, an improvement plan will be developed that provides more specific information for the next response.

[1302] These improvement suggestions will be implemented in the next cycle.

[1303] Specific example

[1304] scenario:

[1305] Users want to use generative AI to find the optimal method for generating text.

[1306] 1. Initialization

[1307] The user initializes the AI ​​assistant and sets the API key.

[1308] 2. Selection of areas of expertise

[1309] The server sends a query to the generative AI: "What are your specializations?"

[1310] The generative AI responded, "I'm good at natural language processing."

[1311] The server records its areas of expertise and moves on to the next step.

[1312] 3. Refine the details of the consultation.

[1313] The server generates the question, "What is the optimal text generation method in natural language processing?" based on "natural language processing."

[1314] The emotion engine analyzes the user's emotional state to determine whether the user is particularly interested, relaxed, etc.

[1315] When the user is relaxed, the information is adjusted to be more detailed.

[1316] 4. Implementing the content of the consultation

[1317] The user sends their consultation request to the generative AI from their terminal.

[1318] The generative AI responded, "Methods using GPT-3 or Transformers are optimal."

[1319] The server receives and records the response.

[1320] 5. Analysis of results and creation of improvement plans

[1321] The server analyzes the response and identifies the following areas for improvement.

[1322] The user's emotional state will be re-analyzed, and the content of the next consultation and the method of providing responses will be adjusted accordingly.

[1323] For example, in the next cycle, we could formulate questions that ask for specific implementation examples.

[1324] Thus, the system of the present invention, by using generative AI and an emotion engine, can generate optimal consultation content that takes into account the user's emotional state, continuously improve it, and make maximum use of the strengths of generative AI.

[1325] The following describes the processing flow.

[1326] Step 1:

[1327] The user creates an instance of the AI ​​assistant and sets the necessary API keys. This prepares them to utilize the generative AI and emotion engine.

[1328] python

[1329] ai_assistant = AIAssistant(api_key="your_api_key_here")

[1330] Step 2:

[1331] The server sends a query to the generative AI asking about its areas of expertise. This query is in the form of "What are your specializations?". The generative AI responds by returning its area of ​​expertise (for example, "natural language processing").

[1332] python

[1333] specialty = ai_assistant.get_specialty()

[1334] The server calls a generative AI API, sends questions related to its area of ​​expertise, and receives and records the responses.

[1335] Step 3:

[1336] The server creates the most suitable consultation content based on its identified areas of expertise. During this process, an emotion engine is used to analyze the user's emotional state and adjust the consultation content accordingly.

[1337] python

[1338] consultation = ai_assistant.refine_consultation()

[1339] The server automatically generates consultation content based on its area of ​​expertise, and the emotion engine analyzes the user's emotional state to adjust the consultation content. For example, if the user is feeling stressed, the consultation content will be adjusted to be concise and easy to understand.

[1340] Step 4:

[1341] The user's terminal sends the generated consultation content to the generative AI. For example, it might send the question, "What is the optimal text generation method in natural language processing?"

[1342] python

[1343] response = ai_assistant.consult_ai(consultation)

[1344] The user terminal sends questions to the generative AI via the server.

[1345] Step 5:

[1346] The server receives a response from the generative AI. For example, it might receive a response such as, "Methods using GPT-3 or Transformers are optimal."

[1347] python

[1348] response = "GPT-3 and Transformers"

[1349] The server will record this response.

[1350] Step 6:

[1351] The server analyzes the response from the generative AI and identifies areas for improvement. At this time, it uses an emotion engine to re-analyze the user's emotional state and determine areas for improvement in the next cycle.

[1352] python

[1353] ai_assistant.implement_and_improve(response)

[1354] The server analyzes the response in detail, and the emotion engine analyzes the user's emotional state to identify areas for improvement. For example, if the user was not satisfied with the previous response, the system will develop an improvement plan that provides more specific information next time.

[1355] Step 7:

[1356] The user repeats these steps, continuously running the PDCA cycle. This allows the system to continuously generate consultation content that maximizes the strengths of generative AI and the user's emotional state.

[1357] python

[1358] ai_assistant.run_pdca_cycle()

[1359] The server continuously executes a series of steps from get_specialty to implement_and_improve to optimize the performance of the generative AI.

[1360] As described above, the system of the present invention combines generative AI and an emotion engine to generate optimal consultation content that takes into account the user's emotional state, and can make maximum use of the strengths of generative AI while continuously improving it.

[1361] (Example 2)

[1362] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1363] Existing generative knowledge systems provide information without considering the user's emotional state, making it difficult to generate appropriate consultation content and improve the quality of responses. As a result, users are unable to obtain the information they need, and continuous improvement is not possible.

[1364] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for querying a generative knowledge system that includes areas of expertise for a specialized field; means for receiving a response from the generative knowledge system based on the specialized field; means for generating optimal consultation content based on the specialized field; means for transmitting the consultation content to the generative knowledge system and receiving a response; means for analyzing the response and identifying areas for improvement; means for executing the next cycle based on the areas for improvement; means including an engine for analyzing the user's emotional state; and means for adjusting the consultation content based on the emotional state. This makes it possible to generate optimal consultation content that takes the user's emotional state into consideration and to continuously improve it.

[1365] A "specialized area" refers to a specialized field in which a generative knowledge system excels in terms of knowledge and capabilities.

[1366] A "generative knowledge system" is an artificial intelligence system that generates and provides information based on user inquiries.

[1367] A "specialized field" refers to an area that requires advanced knowledge and skills in a specific area.

[1368] A "response" is the information or answer that a generative knowledge system provides in response to a query from a user or server.

[1369] "Consultation content" refers to the specific questions or requests that a user submits to a generative knowledge system.

[1370] A "cycle" refers to a series of processes involving generating the content of a consultation, obtaining a response, analyzing the response, identifying areas for improvement, and implementing improvements for the next session.

[1371] An "emotion engine" is a component that analyzes the user's emotional state and adjusts the information and responses generated based on the results.

[1372] "Emotional state" refers to the emotions and psychological state a user is experiencing at a given point in time.

[1373] "Analysis" refers to the information processing used to evaluate responses from generative knowledge systems and identify areas for improvement.

[1374] "Improvements" refer to changes or enhancements identified to improve the response from a generative knowledge system.

[1375] This invention is a system that utilizes a generative knowledge system and an emotion engine. It considers the user's emotional state, generates optimal consultation content based on their areas of expertise, and implements a PDCA cycle for continuous improvement. The specific configuration and operation of this system will be described below.

[1376] System Configuration

[1377] 1. User terminal:

[1378] This is a computer or mobile device used by users to operate the system. Inquiries and consultations are sent from the user terminal to the generative knowledge system.

[1379] 2. Server:

[1380] It is a cloud-based or local server that works in conjunction with generative knowledge systems to perform tasks such as analyzing inquiries and responses in its area of ​​expertise, recognizing sentiment, and identifying areas for improvement. The server is equipped with programs and a sentiment engine to access the generative knowledge system's API.

[1381] 3. Emotional Engine:

[1382] This engine recognizes user emotions and optimizes the responses and consultation content of generative knowledge systems according to the user's emotional state.

[1383] Specific examples of actions

[1384] scenario:

[1385] Let's take the example of a user who wants to use a generative knowledge system to find the optimal method for generating text.

[1386] 1. Initialization:

[1387] The user initializes the AI ​​assistant and sets the necessary API keys.

[1388] For example, a user might open an application on their device and go through the steps of setting up an API key for a generative knowledge system.

[1389] 2. Selecting your area of ​​expertise:

[1390] The server sends the prompt "What are your specializations?" to the generative knowledge system. The generative knowledge system responds "I specialize in natural language processing," and the server records the area of ​​expertise.

[1391] 3. Refine the details of the consultation:

[1392] The server generates a consultation question based on its area of ​​expertise, asking "What is the optimal text generation method in natural language processing?" Furthermore, the emotion engine analyzes the user's emotional state, and if, for example, the user is feeling stressed, it adjusts the consultation question to be concise and easy to understand.

[1393] 4. Implementing the plan discussed:

[1394] The user terminal sends the generated consultation content to the generative knowledge system. The generative knowledge system responds with "A method using GPT-3 or Transformers is optimal," and the server receives and records the response.

[1395] 5. Analysis of results and development of improvement plans:

[1396] The server analyzes the response and identifies areas for improvement. For example, it re-analyzes the user's emotional state, and if the user was not satisfied with the previous response, it develops an improvement plan to provide more specific information next time. This improvement plan will be implemented in the next PDCA cycle.

[1397] Hardware and software to be used

[1398] Hardware: Computers, mobile devices, cloud-based or local servers

[1399] Software: APIs for generative knowledge systems (e.g., OpenAI), emotion engines, user interfaces

[1400] Examples of prompt statements

[1401] Prompt for selecting your area of ​​specialization: "What are your specializations?"

[1402] Prompt for generating consultation content: "What is the optimal text generation method in natural language processing?"

[1403] By implementing this invention, users can generate optimal consultation content that takes their emotional state into consideration and obtain high-quality responses by making full use of the strengths of generative knowledge systems. Furthermore, continuous improvement can be expected, leading to an enhanced user experience.

[1404] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1405] Step 1:

[1406] Initialization

[1407] The user starts up their device and opens a dedicated application. Next, the user enters the API key for the generative knowledge system within the application. This establishes a connection to the generative knowledge system, enabling subsequent data processing. The input is the API key, and the output is the connection status with the generative knowledge system.

[1408] Step 2:

[1409] Selection of areas of expertise

[1410] The server sends the prompt "What are your specializations?" to the generative knowledge system. Based on this prompt, the generative knowledge system responds with its area of ​​expertise (for example, "natural language processing"). The input is the prompt "What are your specializations?", and the output is the response from the generative knowledge system. The server records this response.

[1411] Step 3:

[1412] Refinement of the consultation content

[1413] The server generates consultation content based on its areas of expertise obtained in the previous step. For example, based on "natural language processing," it generates the question, "What is the optimal text generation method in natural language processing?" Next, the emotion engine analyzes the user's emotional state. For example, if it determines that the user is feeling stressed, it reorganizes the generated question to be concise and easy to understand. The input consists of prompt sentences based on the areas of expertise and data on the emotional state, and the output is the optimized consultation content.

[1414] Step 4:

[1415] Implementation of the consultation

[1416] The user terminal sends the generated inquiry content to the generative knowledge system. The generative knowledge system returns a specific response to this inquiry content. For example, if the inquiry content is "What is the optimal text generation method in natural language processing?", the response would be "Methods using GPT-3 or Transformers are optimal." The input is the optimized inquiry content, and the output is the response from the generative knowledge system. The server records this response.

[1417] Step 5:

[1418] Analysis of results and creation of improvement plans

[1419] The server analyzes the response from the generative knowledge system and evaluates its quality. Furthermore, it uses an emotion engine to re-analyze the user's emotional state and determine whether the user was satisfied with the response. For example, if the user was not satisfied with the response, the server develops improvement suggestions to make the next consultation more specific and detailed. The input is the previous response and the user's emotional data, and the output is improvement suggestions for the next cycle.

[1420] Through the specific processing steps described above, the system can generate optimal consultation content while considering the user's emotional state, utilizing the strengths of generative knowledge systems, and continuously improve its process.

[1421] (Application Example 2)

[1422] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1423] Many modern content delivery systems provide users with uniform content, making it difficult to suggest content that is optimal for each user's emotional state and preferences. This degrades the quality of the user experience and reduces their willingness to consume content. Furthermore, the lack of mechanisms to improve future suggestions based on feedback on the content provided prevents continuous personalization.

[1424] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for querying a generative artificial intelligence, including its areas of expertise, for its areas of expertise; means for receiving a response from the generative artificial intelligence based on the areas of expertise; means for creating optimal consultation content based on the areas of expertise; means for recognizing the user's emotions and optimizing the consultation content according to the recognized emotional state; means for transmitting the consultation content to the generative artificial intelligence and receiving a response; means for analyzing the response and identifying areas for improvement; and means for executing the next cycle based on the areas for improvement. This enables optimal content suggestions based on the user's emotional state and areas of expertise, as well as continuous improvement based on feedback.

[1425] "Generative artificial intelligence" is an artificial intelligence technology that uses specialized knowledge and information in a particular field to provide optimal answers and suggestions to user inquiries.

[1426] A "user terminal" is a computer or mobile device used by a user to operate the system and send inquiries and consultations to the generative artificial intelligence.

[1427] A "server" is a network-based computer system that works in conjunction with generative artificial intelligence to conduct research in specialized fields, recognize emotions, analyze responses, and identify improvement suggestions.

[1428] An "emotion engine" is software that recognizes the user's emotions and optimizes the responses and consultation content of generative artificial intelligence based on that emotional state.

[1429] A "specialized field" refers to an area of ​​technology or knowledge in which generative artificial intelligence excels, and is a field in which it possesses a deep understanding.

[1430] "Consultation content" refers to the specific questions or concerns that the user submits to the generative artificial intelligence.

[1431] "Response" refers to the answers or suggestions that generative artificial intelligence provides in response to a user's inquiry.

[1432] A "specialty area" refers to a specific field in which generative artificial intelligence possesses particularly specialized knowledge or skills.

[1433] "Optimization" refers to the process of adjusting and improving the responses and consultation content of generative artificial intelligence to the best possible form, based on the user's emotional state and area of ​​expertise.

[1434] "Areas for improvement" refers to points of modification or adjustment identified to improve the quality of the generative artificial intelligence's responses.

[1435] "Feedback" refers to evaluations and impressions of responses provided by users, and serves as information to improve future responses.

[1436] This invention is a system that uses generative artificial intelligence combined with user emotion recognition to suggest optimal content. The specific configuration, operation, and process of the system are described below.

[1437] System Configuration

[1438] 1. User terminal

[1439] It is a computer or mobile device used by the user to operate the system and send inquiries and consultations to generative artificial intelligence.

[1440] 2. Server

[1441] It is a networked computer system that works in conjunction with generative artificial intelligence to conduct research in specialized fields, recognize emotions, analyze responses, and identify improvement suggestions.

[1442] 3. Emotional Engine

[1443] This software recognizes the user's emotions and optimizes the responses and consultation content of generative artificial intelligence based on that emotional state.

[1444] Program processing

[1445] This system will be implemented using the following hardware and software:

[1446] Hardware:

[1447] Smartphones (iPhone and Android devices)

[1448] Network Server

[1449] software:

[1450] EmotionRecognizer: A library for recognizing user emotions. In this case, it uses OpenCV or Dlib to analyze facial expressions.

[1451] ContentSelector: A library for suggesting content. It utilizes APIs from generative artificial intelligence (such as GPT-3).

[1452] FeedbackAnalyzer: A library for analyzing user feedback and incorporating it into future suggestions.

[1453] Specific implementation methods

[1454] 1. Recognizing user emotions:

[1455] The user uses their smartphone's camera and microphone to send their facial expressions and voice to the system, which EmotionRecognizer analyzes to recognize emotions.

[1456] 2. Selection of a field of specialization:

[1457] The ContentSelector on the server queries the generative artificial intelligence (AI) for its area of ​​expertise, identifying its strengths. For example, it might ask the AI, "What are your specializations?"

[1458] 3. Content proposals:

[1459] The server suggests the most suitable content based on the user's perceived emotional state and areas of expertise. For example, if the user is relaxed, it might suggest a "comedy movie."

[1460] 4. Gathering and analyzing feedback:

[1461] FeedbackAnalyzer collects feedback from users who have viewed the suggested content and uses this feedback to improve future suggestions.

[1462] Specific example

[1463] Example of a prompt

[1464] "You seem relaxed right now. What's the best movie to watch next?"

[1465] Usage Scenarios

[1466] The user opens the app and points their face in front of the camera.

[1467] The app analyzes the user's facial expressions and identifies the emotion of "relaxation."

[1468] I've chosen "comedy films" as my area of ​​expertise.

[1469] The app recommends the movie "The Grand Budapest Hotel".

[1470] Users provide "satisfied" feedback after watching a movie.

[1471] Next time, the app will enhance its recommendations for more relaxing comedy movies.

[1472] Thus, the system of the present invention enables optimal content suggestions based on the user's emotional state and areas of expertise, as well as continuous improvement based on feedback.

[1473] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1474] Step 1:

[1475] The user launches the application on their smartphone and records their current state via the camera or microphone. The input consists of the user's facial expressions and voice data. EmotionRecognizer analyzes this data and recognizes emotions from the facial expressions and voice. The output is the emotional state (e.g., relaxed, stressed).

[1476] Step 2:

[1477] The server queries a generative artificial intelligence (AI) about its areas of expertise. The input is a query about areas of expertise (e.g., "What are your specializations?"). The generative AI responds by returning its areas of expertise. This response is analyzed by the server to identify its areas of expertise (e.g., comedy films). The output is information about its areas of expertise.

[1478] Step 3:

[1479] The server creates the most suitable consultation content based on the emotional state and areas of expertise it recognizes. The input is the emotional state and areas of expertise. The server generates a prompt based on this (e.g., "You seem relaxed now. What movie would be best to watch next?"). The output is the generated prompt.

[1480] Step 4:

[1481] The server sends a generated prompt to the generative artificial intelligence (AI). The input is the generated prompt. The generative AI generates a response to this prompt and returns the most suitable content suggestion (e.g., a suggestion for the movie "The Grand Budapest Hotel"). The output is the response from the generative AI.

[1482] Step 5:

[1483] The user terminal displays the response received from the server and provides content suggestions to the user. The input is the response from the generative artificial intelligence. The user terminal receives this and displays it on the screen. The output is the content suggestions displayed to the user.

[1484] Step 6:

[1485] Users view the provided content and then provide feedback. The input is the user's feedback (e.g., "satisfied" or "dissatisfied"). The feedback is sent to the server via the user's device. The output is the user's feedback data.

[1486] Step 7:

[1487] The server analyzes user feedback and generates instructions to improve future suggestions. The input consists of user feedback data and suggested content information. The server's FeedbackAnalyzer analyzes this data and identifies areas for improvement in the response. The output is a list of improvements for the next cycle.

[1488] As described above, by clearly defining the specific actions, inputs, and outputs at each step, the system's processing flow can be explained in detail. This enables the system to provide optimal content suggestions based on the user's emotional state and areas of expertise.

[1489] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1490] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1491] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1492] [Fourth Embodiment]

[1493] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1494] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1495] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1496] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1497] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1498] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1499] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1500] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1501] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1502] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1503] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1504] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1505] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1506] This invention is a system utilizing generative artificial intelligence (AI), and its purpose is to implement a PDCA cycle to optimally utilize the strengths of generative AI, which is constantly evolving. The specific configuration, operation, and series of processes of the system are described below.

[1507] System Configuration

[1508] 1. User terminal

[1509] It is a computer or mobile device used by a user to operate a system.

[1510] Inquiries and consultations are sent from the user's terminal to the generative AI.

[1511] 2. Server

[1512] It is a cloud-based or local server that works in conjunction with generative AI to analyze inquiries and responses in its area of ​​expertise, and identify areas for improvement.

[1513] The server is equipped with a program to access the generative AI API.

[1514] Program processing

[1515] 1. Initialization

[1516] The user creates an instance of the AI ​​assistant and sets the necessary API key.

[1517] 2. Selection of areas of expertise

[1518] The server sends a query to the generative AI asking about its areas of expertise.

[1519] The generative AI responds by returning a response related to its area of ​​expertise (for example, "natural language processing").

[1520] The server records this response and uses it in the next step.

[1521] 3. Refine the details of the consultation.

[1522] The server automatically generates appropriate consultation content for the generative AI based on its area of ​​expertise.

[1523] For example, if your area of ​​expertise is "natural language processing," you would create a consultation request such as, "What is the optimal technique for natural language processing?"

[1524] 4. Implementing the content of the consultation

[1525] The user terminal sends the generated consultation content to the generative AI.

[1526] The generative AI will provide a response to this inquiry.

[1527] The server receives and records the response.

[1528] 5. Analysis of results and creation of improvement plans

[1529] The server analyzes the response from the generative AI and identifies areas for improvement.

[1530] For example, you could come up with a plan to improve by saying, "Next time, I'll ask questions that include specific technical examples."

[1531] These improvement suggestions will be implemented in the next cycle.

[1532] Specific example

[1533] scenario:

[1534] Users want to use generative AI to find the optimal method for generating text.

[1535] 1. Initialization

[1536] The user initializes the AI ​​assistant and sets the API key.

[1537] ai_assistant = AIAssistant(api_key="your_api_key_here")

[1538] 2. Selection of areas of expertise

[1539] The server sends a query to the generative AI: "What are your specializations?"

[1540] The generative AI responded, "I'm good at natural language processing."

[1541] The server records its areas of expertise and moves on to the next step.

[1542] 3. Refine the details of the consultation.

[1543] The server generates a question based on "natural language processing": "What is the optimal text generation method in natural language processing?"

[1544] 4. Implementing the content of the consultation

[1545] The user sends their consultation request to the generative AI from their terminal.

[1546] The generative AI responded, "Methods using GPT-3 or Transformers are optimal."

[1547] The server receives and records the response.

[1548] 5. Analysis of results and creation of improvement plans

[1549] The server analyzes the response and identifies a suggestion for improvement: "Next time, please provide specific technical examples."

[1550] We will utilize this improvement plan in the next cycle.

[1551] By repeating this process, it is possible to optimally utilize the strengths of generative AI and continuously improve it to obtain effective responses.

[1552] The following describes the processing flow.

[1553] Step 1:

[1554] The user creates an instance of the AI ​​assistant and sets the necessary API keys. This prepares it to communicate with the generative AI.

[1555] python

[1556] ai_assistant = AIAssistant(api_key="your_api_key_here")

[1557] Step 2:

[1558] The server sends a query to the generative AI asking about its areas of expertise. This query is in the format of "What are your specializations?".

[1559] python

[1560] specialty = ai_assistant.get_specialty()

[1561] Specifically, the server calls an AI API and sends a question related to its area of ​​expertise.

[1562] Step 3:

[1563] The server receives a response from the generative AI and identifies its area of ​​expertise. For example, it might receive a response such as "natural language processing."

[1564] python

[1565] Specialty = "Natural Language Processing"

[1566] The server records the response and uses it in the next step.

[1567] Step 4:

[1568] The server creates the most suitable consultation content based on its identified area of ​​expertise. For example, based on "natural language processing," it might generate a question such as, "What is the best text generation method in natural language processing?"

[1569] python

[1570] consultation = ai_assistant.refine_consultation()

[1571] In terms of specific operations, the server automatically generates consultation content based on its areas of expertise.

[1572] Step 5:

[1573] The user sends the generated consultation content from their terminal to the generative AI. For example, they might send a question such as, "What is the optimal text generation method in natural language processing?"

[1574] python

[1575] response = ai_assistant.consult_ai(consultation)

[1576] In terms of specific operations, the user's terminal sends a question to the generative AI via the server.

[1577] Step 6:

[1578] The server receives a response from the generative AI. For example, it might receive a response such as, "Methods using GPT-3 or Transformers are optimal."

[1579] python

[1580] response = "GPT-3 and Transformers"

[1581] The server will record this response.

[1582] Step 7:

[1583] The server analyzes the response from the generative AI and identifies areas for improvement. For example, it might formulate improvement suggestions for the next cycle, such as "requesting more specific technical examples."

[1584] python

[1585] ai_assistant.implement_and_improve(response)

[1586] Specifically, the server analyzes the received response in detail to identify areas for improvement for the next operation.

[1587] Step 8:

[1588] Users repeat these steps, continuously running the PDCA cycle. This allows them to maximize the strengths of generative AI.

[1589] python

[1590] ai_assistant.run_pdca_cycle()

[1591] Specifically, the server continuously executes a series of steps from get_specialty to implement_and_improve to optimize the performance of the generative AI.

[1592] As described above, the system of the present invention utilizes generative AI and can effectively implement the PDCA cycle to obtain the optimal response in a specialized field.

[1593] (Example 1)

[1594] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1595] In recent years, advancements in generative artificial intelligence (AI) have led to its effective use in various fields. However, it remains challenging to predict which fields generative AI will function most appropriately, requiring significant effort to optimize the content of consultations. Furthermore, there is a need to effectively analyze responses from generative AI and incorporate them into the next cycle, but methods for doing so have not yet been established.

[1596] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1597] In this invention, the server includes means for querying a generative artificial intelligence (AI) about its area of ​​expertise, including its area of ​​specialization; means for receiving a response from the AI ​​based on its area of ​​expertise; means for automatically generating the optimal consultation content based on its area of ​​expertise; means for transmitting the consultation content to the AI ​​and receiving a response; means for analyzing the response and identifying areas for improvement in the next cycle; and means for executing the next cycle incorporating the areas for improvement. This makes it possible to automate the PDCA cycle to optimally utilize the AI's area of ​​expertise and obtain effective responses.

[1598] A "specialized field" refers to a specialized area in which generative artificial intelligence exhibits particularly high performance.

[1599] "Generative artificial intelligence" refers to an artificial intelligence system that has the ability to generate text and data in response to user questions and requests.

[1600] A "specialized field" refers to a specialized area that requires specific knowledge or skills.

[1601] "Consultation content" refers to the questions or requests that users make to the generative artificial intelligence.

[1602] "Response" refers to the information that generative artificial intelligence provides in response to the user's inquiry.

[1603] A "server" refers to a computer system that works in conjunction with generative artificial intelligence to process and manage data.

[1604] "Analysis" refers to the act of examining in detail the responses obtained from generative artificial intelligence and evaluating their content and quality.

[1605] "The next cycle" refers to a new PDCA cycle that begins after the current PDCA cycle is completed.

[1606] The "PDCA cycle" refers to a management cycle consisting of four steps—Plan, Do, Check, and Act—with the aim of improving processes.

[1607] This invention is a system that uses generative artificial intelligence to automatically generate optimal consultation content in specialized fields, and then executes and improves the PDCA cycle based on that content. The system primarily operates through the coordinated operation of server, terminal, and user components.

[1608] System Configuration

[1609] 1. User terminal

[1610] It is a computer or mobile device used by a user to operate a system.

[1611] The user terminal can send inquiries and consultation requests to the generative artificial intelligence.

[1612] 2. Server

[1613] It is a cloud-based or local server that works in conjunction with generative artificial intelligence to perform tasks such as answering inquiries in specialized fields, analyzing responses, and identifying areas for improvement.

[1614] The server is equipped with a program for accessing the API of generative artificial intelligence.

[1615] Program processing

[1616] When a user uses the system, they first create an instance of the AI ​​assistant and configure the necessary API keys. This allows them to access generative artificial intelligence.

[1617] The server sends a query to the generative artificial intelligence (AI) asking about its areas of expertise. The AI ​​responds by listing its areas of expertise, and the server records this response.

[1618] The server automatically generates appropriate consultation questions based on its area of ​​expertise. For example, if its area of ​​expertise is "natural language processing," it will create a consultation question such as, "What is the optimal technique for natural language processing?"

[1619] The terminal sends the generated consultation content to the generative artificial intelligence, which then returns a response to this consultation. The server receives and records this response.

[1620] The server analyzes the response from the generative artificial intelligence and identifies areas for improvement. For example, it might create improvement suggestions such as, "Next time, I will ask questions that include specific technical examples." These improvement suggestions will be reflected in the next PDCA cycle.

[1621] Specific example

[1622] Initialization example

[1623] Example of a user initializing an AI assistant and setting an API key:

[1624] python

[1625] ai_assistant = AIAssistant(api_key="your_api_key_here")

[1626] Examples of selecting areas of expertise

[1627] The server sends the query "What are your specializations?" to the generative AI, and the generative AI responds "I specialize in natural language processing."

[1628] Examples of refining the content of the consultation

[1629] The server generates a question based on "natural language processing": "What is the optimal text generation method in natural language processing?"

[1630] Examples of implementing the consultation content

[1631] The terminal sends the consultation request to the generative artificial intelligence, which responds with "A method using GPT-3 or Transformers is optimal." The server receives and records this response.

[1632] This will allow for continuous improvement to optimally utilize the strengths of generative artificial intelligence and obtain effective responses.

[1633] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1634] Step 1:

[1635] Initialization

[1636] The user creates an instance of the AI ​​assistant and sets up an API key.

[1637] Input: API key from the user.

[1638] Data processing: Creating an instance of the AI ​​assistant, setting up the API key.

[1639] Output: An initialized instance of the AI ​​assistant.

[1640] Specific operation: The user enters `ai_assistant = AIAssistant(api_key="your_api_key_here")` to initialize the AI ​​assistant.

[1641] Step 2:

[1642] Selection of areas of expertise

[1643] The server sends a query to the generative artificial intelligence asking about its areas of expertise.

[1644] Input: Query "What are your specializations?".

[1645] Data processing: Sending queries and receiving responses from generative artificial intelligence.

[1646] Output: Responses related to areas of expertise (e.g., "natural language processing").

[1647] Specific operation: The server sends a query to the generative artificial intelligence and receives a response related to its area of ​​expertise.

[1648] Step 3:

[1649] Refinement of the consultation content

[1650] The server automatically generates appropriate consultation content for the generative artificial intelligence based on its area of ​​expertise.

[1651] Input: Area of ​​expertise (e.g., "Natural Language Processing").

[1652] Data processing: Generating consultation content based on areas of expertise.

[1653] Output: Generated question content (e.g., "What is the optimal text generation method in natural language processing?").

[1654] Specific operation: The server generates the consultation content based on its area of ​​expertise, "natural language processing."

[1655] Step 4:

[1656] Implementation of the consultation

[1657] The terminal sends the generated consultation content to a generative artificial intelligence and receives a response.

[1658] Input: Generated question (e.g., "What is the optimal text generation method in natural language processing?").

[1659] Data processing: Sending consultation content to a generative artificial intelligence and receiving responses.

[1660] Output: Response from generative artificial intelligence (e.g., "Methods using GPT-3 or Transformers are optimal").

[1661] Specific operation: The terminal sends the consultation content to a generative artificial intelligence, receives a response, and records it on the server.

[1662] Step 5:

[1663] Analysis of results and creation of improvement plans

[1664] The server analyzes the response from the generative artificial intelligence and identifies areas for improvement.

[1665] Input: Response from a generative artificial intelligence (e.g., "Methods using GPT-3 or Transformers are optimal").

[1666] Data processing: Response analysis, identification of areas for improvement.

[1667] Output: Suggestions for improvement (e.g., "Next time, I will ask questions including specific technical examples").

[1668] Specific operation: The server analyzes the response from the generative artificial intelligence and creates improvement suggestions to be implemented in the next cycle.

[1669] By executing these steps in sequence, it is possible to optimally utilize the strengths of generative artificial intelligence and realize a PDCA cycle to obtain effective responses.

[1670] (Application Example 1)

[1671] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1672] Currently, optimizing advertising campaigns is time-consuming and labor-intensive, and developing effective storytelling and targeting strategies requires specialized knowledge. Traditional methods, while utilizing generative artificial intelligence, lack a mechanism to effectively leverage its strengths while analyzing large amounts of data simultaneously, making it difficult to create optimal advertising campaigns. Therefore, there is a need for a system that leverages the strengths of generative AI to automatically optimize the storytelling and targeting strategies of advertising campaigns.

[1673] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1674] In this invention, the server includes means for querying a generative artificial intelligence (AI) about its areas of expertise, including its areas of specialization; means for receiving a response from the AI ​​based on its areas of specialization; means for creating an optimal consultation based on its areas of specialization; means for transmitting the consultation to the AI ​​and receiving a response; means for analyzing the response to identify areas for improvement; means for executing the next cycle based on the areas for improvement; means for creating a consultation regarding the optimization of an advertising campaign and analyzing the response from the AI; and means for improving the storytelling and targeting strategies of the advertising campaign based on the response. This enables effective utilization of the AI's areas of expertise and optimizes advertising campaigns.

[1675] "Generative artificial intelligence with a specialized field" refers to generative artificial intelligence that possesses advanced capabilities in a specific field.

[1676] "Means of inquiring about specialized fields" refers to methods or functions for asking generative artificial intelligence which fields it is proficient in.

[1677] "Means of receiving responses" refers to methods or functions for obtaining responses from generative artificial intelligence.

[1678] "Means for creating consultation content" refers to methods and functions for creating appropriate questions and requests based on specialized fields obtained from generative artificial intelligence.

[1679] "Means for sending consultation content and receiving responses" refers to methods and functions for sending created consultation content to generative artificial intelligence and obtaining its responses.

[1680] "Means for analyzing responses and identifying areas for improvement" refers to methods and functions for analyzing responses from generative artificial intelligence and finding areas that need improvement.

[1681] "Means for executing the next cycle" refers to the methods and functions for executing the next process, taking into account the improvements that have been made.

[1682] "Advertising campaign optimization" is the process of improving the content and strategy of an advertisement in order to maximize its effectiveness.

[1683] "Storytelling" is an advertising technique that uses stories and episodes to attract customer interest and effectively convey a message.

[1684] A "targeting strategy" is a method or plan for effectively delivering advertisements to a specific consumer group.

[1685] This invention is a system that optimizes advertising campaigns using generative artificial intelligence. Users utilize user devices such as smartphones and interact with the generative artificial intelligence to achieve effective advertising campaigns. This system operates with the following configuration and configuration.

[1686] System Configuration

[1687] 1. User terminal

[1688] It is a computer or mobile device operated by a user.

[1689] For example, the system can be accessed through a smartphone application.

[1690] 2. Server

[1691] It works in conjunction with generative artificial intelligence and operates in a cloud-based or local data center.

[1692] The server is equipped with a program for accessing the API of generative artificial intelligence.

[1693] Processing flow

[1694] 1. Initialization

[1695] The user initializes the application and sets the necessary API keys.

[1696] Specific example: A user launches a smartphone app and enters an API key.

[1697] 2. Selection of areas of expertise

[1698] The server sends a query to the generative artificial intelligence asking about its area of ​​expertise.

[1699] The server receives the response and records its areas of expertise.

[1700] Specific example: The server asks the generative AI, "What is your area of ​​expertise in advertising?" and the generative AI responds, "I'm good at targeted advertising."

[1701] 3. Refine the details of the consultation.

[1702] The server automatically generates appropriate consultation content for the generative artificial intelligence based on its area of ​​expertise.

[1703] Specific example: A question is generated asking, "What are the optimal content and strategies for targeted advertising?"

[1704] 4. Implementing the content of the consultation

[1705] The user sends their inquiry to a generative artificial intelligence from their terminal and receives a response.

[1706] Specific example: A user's device sends a question to a generative artificial intelligence, and receives a response such as, "Storytelling and personalized advertising relevant to your target audience would be effective."

[1707] 5. Analysis of results and creation of improvement plans

[1708] The server analyzes the response from the generative artificial intelligence and identifies areas for improvement.

[1709] Based on the improvements identified, we will execute the next cycle.

[1710] Specific example: Analyze the response and formulate an improvement plan for the next consultation, such as "asking for specific examples of storytelling."

[1711] Hardware and software to be used

[1712] Hardware:

[1713] User devices: Smartphones, tablets, PCs, etc.

[1714] Servers: Cloud-based data centers, local servers

[1715] software:

[1716] APIs for generative artificial intelligence (e.g., OpenAI API)

[1717] Data collection and analysis tools (e.g., Python-based scripts)

[1718] Example of a prompt

[1719] "Could you give me some specific examples of storytelling in targeted advertising?"

[1720] This invention makes it possible to effectively utilize the strengths of generative artificial intelligence to automatically optimize the storytelling and targeting strategies of advertising campaigns.

[1721] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1722] Step 1:

[1723] Initialization

[1724] Subject: User

[1725] Specific operation: The user launches the smartphone application and enters the required API key.

[1726] Input: API key

[1727] Output: API key setup complete

[1728] Processing details: Store the API key within the application and prepare for integration with generative artificial intelligence.

[1729] Step 2:

[1730] Selection of areas of expertise

[1731] Subject: Server

[1732] Specific operation: The server sends a query to the generative artificial intelligence: "What is your expertise in the advertising field?"

[1733] Input: Query "What is your area of ​​expertise in advertising?"

[1734] Output: Response from generative artificial intelligence (e.g., "I'm good at targeted advertising")

[1735] Processing details: Receive and record responses related to the generative artificial intelligence's area of ​​expertise.

[1736] Step 3:

[1737] Refinement of the consultation content

[1738] Subject: Server

[1739] Specific operation: The server automatically generates appropriate consultation content based on its area of ​​expertise.

[1740] Input: Response indicating your area of ​​expertise (e.g., "I specialize in targeted advertising.")

[1741] Output: Consultation content (Example: "What are the optimal content and strategies for targeted advertising?")

[1742] Processing details: Based on the area of ​​expertise, construct more detailed questions for the generative artificial intelligence.

[1743] Step 4:

[1744] Implementation of the consultation

[1745] Subject: terminal

[1746] Specific operation: The user sends the consultation content from their terminal to a generative artificial intelligence and retrieves the results.

[1747] Input: Question (Example: "What are the optimal content and strategies for targeted advertising?")

[1748] Output: Response from generative artificial intelligence (e.g., "Storytelling and personalized advertising relevant to your target audience are effective")

[1749] Processing details: The consultation content is sent, and the received response is saved within the application.

[1750] Step 5:

[1751] Analysis of results and creation of improvement plans

[1752] Subject: Server

[1753] Specific operation: The server analyzes the response from the generative artificial intelligence and identifies areas for improvement.

[1754] Input: Response from generative artificial intelligence (e.g., "Storytelling and personalized advertising relevant to your target audience are effective")

[1755] Output: Suggestions for improvement to be reflected in the next consultation (e.g., "Request specific examples of storytelling")

[1756] Processing details: Analyze the response and identify areas for improvement in the next consultation.

[1757] Step 6:

[1758] Execute the next cycle

[1759] Subject: Server and terminal

[1760] Specific operation: The server refines the content of the next consultation based on the improvement suggestions, and then the user terminal queries the generative artificial intelligence again.

[1761] Input: Suggestion for improvement (Example: "Please provide specific examples of storytelling.")

[1762] Output: New inquiry topic (Example: "Please provide specific examples of storytelling in targeted advertising.")

[1763] Processing details: Based on the improvement suggestions, new consultation topics are generated, and this process is repeated to continuously optimize the advertising campaign.

[1764] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1765] This invention is a system that utilizes generative artificial intelligence (AI) and, by combining it with user emotion recognition, generates optimal consultation content based on the user's area of ​​expertise and implements a PDCA cycle for continuous improvement. The specific configuration, operation, and series of processes of the system are described below.

[1766] System Configuration

[1767] 1. User terminal

[1768] It is a computer or mobile device used by a user to operate a system.

[1769] Inquiries and consultations are sent from the user's terminal to the generative AI.

[1770] 2. Server

[1771] It is a cloud-based or local server that works in conjunction with generative AI to perform tasks such as analyzing inquiries and responses in its area of ​​expertise, recognizing emotions, and identifying areas for improvement.

[1772] The server is equipped with a program and emotion engine for accessing the generative AI API.

[1773] 3. Emotional Engine

[1774] This engine recognizes user emotions and optimizes the responses and consultation content of generative AI according to the user's emotional state.

[1775] Program processing

[1776] 1. Initialization

[1777] The user creates an instance of the AI ​​assistant and sets the necessary API key.

[1778] 2. Selection of areas of expertise

[1779] The server sends a query to the generative AI, asking about its area of ​​expertise.

[1780] Generative AI responds by returning its area of ​​expertise (for example, "natural language processing").

[1781] The server records this response and uses it in the next step.

[1782] 3. Refine the details of the consultation.

[1783] The server automatically creates the most suitable consultation content based on its area of ​​expertise.

[1784] Furthermore, an emotion engine is used to analyze the user's current emotional state and adjust the consultation content accordingly.

[1785] For example, if a user is feeling stressed, the content of their consultation will be adjusted to be concise and easy to understand.

[1786] 4. Implementing the content of the consultation

[1787] The user terminal sends the generated consultation content to the generative AI.

[1788] The generative AI will provide a response to this inquiry.

[1789] The server receives and records the response.

[1790] 5. Analysis of results and creation of improvement plans

[1791] The server analyzes the response from the generative AI and identifies areas for improvement.

[1792] An emotion engine is used to consider the user's emotional state during response analysis. For example, if the user was not satisfied with the previous response, an improvement plan will be developed that provides more specific information for the next response.

[1793] These improvement suggestions will be implemented in the next cycle.

[1794] Specific example

[1795] scenario:

[1796] Users want to use generative AI to find the optimal method for generating text.

[1797] 1. Initialization

[1798] The user initializes the AI ​​assistant and sets the API key.

[1799] 2. Selection of areas of expertise

[1800] The server sends a query to the generative AI: "What are your specializations?"

[1801] The generative AI responded, "I'm good at natural language processing."

[1802] The server records its areas of expertise and moves on to the next step.

[1803] 3. Refine the details of the consultation.

[1804] The server generates the question, "What is the optimal text generation method in natural language processing?" based on "natural language processing."

[1805] The emotion engine analyzes the user's emotional state to determine whether the user is particularly interested, relaxed, etc.

[1806] When the user is relaxed, the information is adjusted to be more detailed.

[1807] 4. Implementing the content of the consultation

[1808] The user sends their consultation request to the generative AI from their terminal.

[1809] The generative AI responded, "Methods using GPT-3 or Transformers are optimal."

[1810] The server receives and records the response.

[1811] 5. Analysis of results and creation of improvement plans

[1812] The server analyzes the response and identifies the following areas for improvement.

[1813] The user's emotional state will be re-analyzed, and the content of the next consultation and the method of providing responses will be adjusted accordingly.

[1814] For example, in the next cycle, we could formulate questions that ask for specific implementation examples.

[1815] Thus, the system of the present invention, by using generative AI and an emotion engine, can generate optimal consultation content that takes into account the user's emotional state, continuously improve it, and make maximum use of the strengths of generative AI.

[1816] The following describes the processing flow.

[1817] Step 1:

[1818] The user creates an instance of the AI ​​assistant and sets the necessary API keys. This prepares them to utilize the generative AI and emotion engine.

[1819] python

[1820] ai_assistant = AIAssistant(api_key="your_api_key_here")

[1821] Step 2:

[1822] The server sends a query to the generative AI asking about its areas of expertise. This query is in the form of "What are your specializations?". The generative AI responds by returning its area of ​​expertise (for example, "natural language processing").

[1823] python

[1824] specialty = ai_assistant.get_specialty()

[1825] The server calls a generative AI API, sends questions related to its area of ​​expertise, and receives and records the responses.

[1826] Step 3:

[1827] The server creates the most suitable consultation content based on its identified areas of expertise. During this process, an emotion engine is used to analyze the user's emotional state and adjust the consultation content accordingly.

[1828] python

[1829] consultation = ai_assistant.refine_consultation()

[1830] The server automatically generates consultation content based on its area of ​​expertise, and the emotion engine analyzes the user's emotional state to adjust the consultation content. For example, if the user is feeling stressed, the consultation content will be adjusted to be concise and easy to understand.

[1831] Step 4:

[1832] The user's terminal sends the generated consultation content to the generative AI. For example, it might send the question, "What is the optimal text generation method in natural language processing?"

[1833] python

[1834] response = ai_assistant.consult_ai(consultation)

[1835] The user terminal sends questions to the generative AI via the server.

[1836] Step 5:

[1837] The server receives a response from the generative AI. For example, it might receive a response such as, "Methods using GPT-3 or Transformers are optimal."

[1838] python

[1839] response = "GPT-3 and Transformers"

[1840] The server will record this response.

[1841] Step 6:

[1842] The server analyzes the response from the generative AI and identifies areas for improvement. At this time, it uses an emotion engine to re-analyze the user's emotional state and determine areas for improvement in the next cycle.

[1843] python

[1844] ai_assistant.implement_and_improve(response)

[1845] The server analyzes the response in detail, and the emotion engine analyzes the user's emotional state to identify areas for improvement. For example, if the user was not satisfied with the previous response, the system will develop an improvement plan that provides more specific information next time.

[1846] Step 7:

[1847] The user repeats these steps, continuously running the PDCA cycle. This allows the system to continuously generate consultation content that maximizes the strengths of generative AI and the user's emotional state.

[1848] python

[1849] ai_assistant.run_pdca_cycle()

[1850] The server continuously executes a series of steps from get_specialty to implement_and_improve to optimize the performance of the generative AI.

[1851] As described above, the system of the present invention combines generative AI and an emotion engine to generate optimal consultation content that takes into account the user's emotional state, and can make maximum use of the strengths of generative AI while continuously improving it.

[1852] (Example 2)

[1853] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1854] Existing generative knowledge systems provide information without considering the user's emotional state, making it difficult to generate appropriate consultation content and improve the quality of responses. As a result, users are unable to obtain the information they need, and continuous improvement is not possible.

[1855] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for querying a generative knowledge system that includes areas of expertise for a specialized field; means for receiving a response from the generative knowledge system based on the specialized field; means for generating optimal consultation content based on the specialized field; means for transmitting the consultation content to the generative knowledge system and receiving a response; means for analyzing the response and identifying areas for improvement; means for executing the next cycle based on the areas for improvement; means including an engine for analyzing the user's emotional state; and means for adjusting the consultation content based on the emotional state. This makes it possible to generate optimal consultation content that takes the user's emotional state into consideration and to continuously improve it.

[1856] A "specialized area" refers to a specialized field in which a generative knowledge system excels in terms of knowledge and capabilities.

[1857] A "generative knowledge system" is an artificial intelligence system that generates and provides information based on user inquiries.

[1858] A "specialized field" refers to an area that requires advanced knowledge and skills in a specific area.

[1859] A "response" is the information or answer that a generative knowledge system provides in response to a query from a user or server.

[1860] "Consultation content" refers to the specific questions or requests that a user submits to a generative knowledge system.

[1861] A "cycle" refers to a series of processes involving generating the content of a consultation, obtaining a response, analyzing the response, identifying areas for improvement, and implementing improvements for the next session.

[1862] An "emotion engine" is a component that analyzes the user's emotional state and adjusts the information and responses generated based on the results.

[1863] "Emotional state" refers to the emotions and psychological state a user is experiencing at a given point in time.

[1864] "Analysis" refers to the information processing used to evaluate responses from generative knowledge systems and identify areas for improvement.

[1865] "Improvements" refer to changes or enhancements identified to improve the response from a generative knowledge system.

[1866] This invention is a system that utilizes a generative knowledge system and an emotion engine. It considers the user's emotional state, generates optimal consultation content based on their areas of expertise, and implements a PDCA cycle for continuous improvement. The specific configuration and operation of this system will be described below.

[1867] System Configuration

[1868] 1. User terminal:

[1869] This is a computer or mobile device used by users to operate the system. Inquiries and consultations are sent from the user terminal to the generative knowledge system.

[1870] 2. Server:

[1871] It is a cloud-based or local server that works in conjunction with generative knowledge systems to perform tasks such as analyzing inquiries and responses in its area of ​​expertise, recognizing sentiment, and identifying areas for improvement. The server is equipped with programs and a sentiment engine to access the generative knowledge system's API.

[1872] 3. Emotional Engine:

[1873] This engine recognizes user emotions and optimizes the responses and consultation content of generative knowledge systems according to the user's emotional state.

[1874] Specific examples of actions

[1875] scenario:

[1876] Let's take the example of a user who wants to use a generative knowledge system to find the optimal method for generating text.

[1877] 1. Initialization:

[1878] The user initializes the AI ​​assistant and sets the necessary API keys.

[1879] For example, a user might open an application on their device and go through the steps of setting up an API key for a generative knowledge system.

[1880] 2. Selecting your area of ​​expertise:

[1881] The server sends the prompt "What are your specializations?" to the generative knowledge system. The generative knowledge system responds "I specialize in natural language processing," and the server records the area of ​​expertise.

[1882] 3. Refine the details of the consultation:

[1883] The server generates a consultation question based on its area of ​​expertise, asking "What is the optimal text generation method in natural language processing?" Furthermore, the emotion engine analyzes the user's emotional state, and if, for example, the user is feeling stressed, it adjusts the consultation question to be concise and easy to understand.

[1884] 4. Implementing the plan discussed:

[1885] The user terminal sends the generated consultation content to the generative knowledge system. The generative knowledge system responds with "A method using GPT-3 or Transformers is optimal," and the server receives and records the response.

[1886] 5. Analysis of results and development of improvement plans:

[1887] The server analyzes the response and identifies areas for improvement. For example, it re-analyzes the user's emotional state, and if the user was not satisfied with the previous response, it develops an improvement plan to provide more specific information next time. This improvement plan will be implemented in the next PDCA cycle.

[1888] Hardware and software to be used

[1889] Hardware: Computers, mobile devices, cloud-based or local servers

[1890] Software: APIs for generative knowledge systems (e.g., OpenAI), emotion engines, user interfaces

[1891] Examples of prompt statements

[1892] Prompt for selecting your area of ​​specialization: "What are your specializations?"

[1893] Prompt for generating consultation content: "What is the optimal text generation method in natural language processing?"

[1894] By implementing this invention, users can generate optimal consultation content that takes their emotional state into consideration and obtain high-quality responses by making full use of the strengths of generative knowledge systems. Furthermore, continuous improvement can be expected, leading to an enhanced user experience.

[1895] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1896] Step 1:

[1897] Initialization

[1898] The user starts up their device and opens a dedicated application. Next, the user enters the API key for the generative knowledge system within the application. This establishes a connection to the generative knowledge system, enabling subsequent data processing. The input is the API key, and the output is the connection status with the generative knowledge system.

[1899] Step 2:

[1900] Selection of areas of expertise

[1901] The server sends the prompt "What are your specializations?" to the generative knowledge system. Based on this prompt, the generative knowledge system responds with its area of ​​expertise (for example, "natural language processing"). The input is the prompt "What are your specializations?", and the output is the response from the generative knowledge system. The server records this response.

[1902] Step 3:

[1903] Refinement of the consultation content

[1904] The server generates consultation content based on its areas of expertise obtained in the previous step. For example, based on "natural language processing," it generates the question, "What is the optimal text generation method in natural language processing?" Next, the emotion engine analyzes the user's emotional state. For example, if it determines that the user is feeling stressed, it reorganizes the generated question to be concise and easy to understand. The input consists of prompt sentences based on the areas of expertise and data on the emotional state, and the output is the optimized consultation content.

[1905] Step 4:

[1906] Implementation of the consultation

[1907] The user terminal sends the generated inquiry content to the generative knowledge system. The generative knowledge system returns a specific response to this inquiry content. For example, if the inquiry content is "What is the optimal text generation method in natural language processing?", the response would be "Methods using GPT-3 or Transformers are optimal." The input is the optimized inquiry content, and the output is the response from the generative knowledge system. The server records this response.

[1908] Step 5:

[1909] Analysis of results and creation of improvement plans

[1910] The server analyzes the response from the generative knowledge system and evaluates its quality. Furthermore, it uses an emotion engine to re-analyze the user's emotional state and determine whether the user was satisfied with the response. For example, if the user was not satisfied with the response, the server develops improvement suggestions to make the next consultation more specific and detailed. The input is the previous response and the user's emotional data, and the output is improvement suggestions for the next cycle.

[1911] Through the specific processing steps described above, the system can generate optimal consultation content while considering the user's emotional state, utilizing the strengths of generative knowledge systems, and continuously improve its process.

[1912] (Application Example 2)

[1913] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1914] Many modern content delivery systems provide users with uniform content, making it difficult to suggest content that is optimal for each user's emotional state and preferences. This degrades the quality of the user experience and reduces their willingness to consume content. Furthermore, the lack of mechanisms to improve future suggestions based on feedback on the content provided prevents continuous personalization.

[1915] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for querying a generative artificial intelligence, including its areas of expertise, for its areas of expertise; means for receiving a response from the generative artificial intelligence based on the areas of expertise; means for creating optimal consultation content based on the areas of expertise; means for recognizing the user's emotions and optimizing the consultation content according to the recognized emotional state; means for transmitting the consultation content to the generative artificial intelligence and receiving a response; means for analyzing the response and identifying areas for improvement; and means for executing the next cycle based on the areas for improvement. This enables optimal content suggestions based on the user's emotional state and areas of expertise, as well as continuous improvement based on feedback.

[1916] "Generative artificial intelligence" is an artificial intelligence technology that uses specialized knowledge and information in a particular field to provide optimal answers and suggestions to user inquiries.

[1917] A "user terminal" is a computer or mobile device used by a user to operate the system and send inquiries and consultations to the generative artificial intelligence.

[1918] A "server" is a network-based computer system that works in conjunction with generative artificial intelligence to conduct research in specialized fields, recognize emotions, analyze responses, and identify improvement suggestions.

[1919] An "emotion engine" is software that recognizes the user's emotions and optimizes the responses and consultation content of generative artificial intelligence based on that emotional state.

[1920] A "specialized field" refers to an area of ​​technology or knowledge in which generative artificial intelligence excels, and is a field in which it possesses a deep understanding.

[1921] "Consultation content" refers to the specific questions or concerns that the user submits to the generative artificial intelligence.

[1922] "Response" refers to the answers or suggestions that generative artificial intelligence provides in response to a user's inquiry.

[1923] A "specialty area" refers to a specific field in which generative artificial intelligence possesses particularly specialized knowledge or skills.

[1924] "Optimization" refers to the process of adjusting and improving the responses and consultation content of generative artificial intelligence to the best possible form, based on the user's emotional state and area of ​​expertise.

[1925] "Areas for improvement" refers to points of modification or adjustment identified to improve the quality of the generative artificial intelligence's responses.

[1926] "Feedback" refers to evaluations and impressions of responses provided by users, and serves as information to improve future responses.

[1927] This invention is a system that uses generative artificial intelligence combined with user emotion recognition to suggest optimal content. The specific configuration, operation, and process of the system are described below.

[1928] System Configuration

[1929] 1. User terminal

[1930] It is a computer or mobile device used by the user to operate the system and send inquiries and consultations to generative artificial intelligence.

[1931] 2. Server

[1932] It is a networked computer system that works in conjunction with generative artificial intelligence to conduct research in specialized fields, recognize emotions, analyze responses, and identify improvement suggestions.

[1933] 3. Emotional Engine

[1934] This software recognizes the user's emotions and optimizes the responses and consultation content of generative artificial intelligence based on that emotional state.

[1935] Program processing

[1936] This system will be implemented using the following hardware and software:

[1937] Hardware:

[1938] Smartphones (iPhone and Android devices)

[1939] Network Server

[1940] software:

[1941] EmotionRecognizer: A library for recognizing user emotions. In this case, it uses OpenCV or Dlib to analyze facial expressions.

[1942] ContentSelector: A library for suggesting content. It utilizes APIs from generative artificial intelligence (such as GPT-3).

[1943] FeedbackAnalyzer: A library for analyzing user feedback and incorporating it into future suggestions.

[1944] Specific implementation methods

[1945] 1. Recognizing user emotions:

[1946] The user uses their smartphone's camera and microphone to send their facial expressions and voice to the system, which EmotionRecognizer analyzes to recognize emotions.

[1947] 2. Selection of a field of specialization:

[1948] The ContentSelector on the server queries the generative artificial intelligence (AI) for its area of ​​expertise, identifying its strengths. For example, it might ask the AI, "What are your specializations?"

[1949] 3. Content proposals:

[1950] The server suggests the most suitable content based on the user's perceived emotional state and areas of expertise. For example, if the user is relaxed, it might suggest a "comedy movie."

[1951] 4. Gathering and analyzing feedback:

[1952] FeedbackAnalyzer collects feedback from users who have viewed the suggested content and uses this feedback to improve future suggestions.

[1953] Specific example

[1954] Example of a prompt

[1955] "You seem relaxed right now. What's the best movie to watch next?"

[1956] Usage Scenarios

[1957] The user opens the app and points their face in front of the camera.

[1958] The app analyzes the user's facial expressions and identifies the emotion of "relaxation."

[1959] I've chosen "comedy films" as my area of ​​expertise.

[1960] The app recommends the movie "The Grand Budapest Hotel".

[1961] Users provide "satisfied" feedback after watching a movie.

[1962] Next time, the app will enhance its recommendations for more relaxing comedy movies.

[1963] Thus, the system of the present invention enables optimal content suggestions based on the user's emotional state and areas of expertise, as well as continuous improvement based on feedback.

[1964] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1965] Step 1:

[1966] The user launches the application on their smartphone and records their current state via the camera or microphone. The input consists of the user's facial expressions and voice data. EmotionRecognizer analyzes this data and recognizes emotions from the facial expressions and voice. The output is the emotional state (e.g., relaxed, stressed).

[1967] Step 2:

[1968] The server queries a generative artificial intelligence (AI) about its areas of expertise. The input is a query about areas of expertise (e.g., "What are your specializations?"). The generative AI responds by returning its areas of expertise. This response is analyzed by the server to identify its areas of expertise (e.g., comedy films). The output is information about its areas of expertise.

[1969] Step 3:

[1970] The server creates the most suitable consultation content based on the emotional state and areas of expertise it recognizes. The input is the emotional state and areas of expertise. The server generates a prompt based on this (e.g., "You seem relaxed now. What movie would be best to watch next?"). The output is the generated prompt.

[1971] Step 4:

[1972] The server sends a generated prompt to the generative artificial intelligence (AI). The input is the generated prompt. The generative AI generates a response to this prompt and returns the most suitable content suggestion (e.g., a suggestion for the movie "The Grand Budapest Hotel"). The output is the response from the generative AI.

[1973] Step 5:

[1974] The user terminal displays the response received from the server and provides content suggestions to the user. The input is the response from the generative artificial intelligence. The user terminal receives this and displays it on the screen. The output is the content suggestions displayed to the user.

[1975] Step 6:

[1976] Users view the provided content and then provide feedback. The input is the user's feedback (e.g., "satisfied" or "dissatisfied"). The feedback is sent to the server via the user's device. The output is the user's feedback data.

[1977] Step 7:

[1978] The server analyzes user feedback and generates instructions to improve future suggestions. The input consists of user feedback data and suggested content information. The server's FeedbackAnalyzer analyzes this data and identifies areas for improvement in the response. The output is a list of improvements for the next cycle.

[1979] As described above, by clearly defining the specific actions, inputs, and outputs at each step, the system's processing flow can be explained in detail. This enables the system to provide optimal content suggestions based on the user's emotional state and areas of expertise.

[1980] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1981] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1982] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1983] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1984] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1985] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1986] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1987] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1988] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1989] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1990] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1991] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1992] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1993] 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.

[1994] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1995] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1996] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1997] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1998] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1999] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[2000] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[2001] The following is further disclosed regarding the embodiments described above.

[2002] (Claim 1)

[2003] A means of querying a generative artificial intelligence, including its areas of expertise, about its specialized fields,

[2004] A means for receiving answers based on the aforementioned specialized field from the aforementioned generative artificial intelligence,

[2005] A means of creating the most suitable consultation content based on the aforementioned specialized field,

[2006] A means for transmitting the consultation content to the generative artificial intelligence and receiving a response,

[2007] A means for analyzing the aforementioned response and identifying areas for improvement,

[2008] A means of executing the next cycle based on the aforementioned improvements,

[2009] A system that includes this.

[2010] (Claim 2)

[2011] The system according to claim 1, characterized in that the means for creating consultation content based on the aforementioned specialized field automatically generates consultation content based on information regarding the area of ​​expertise of the generative artificial intelligence.

[2012] (Claim 3)

[2013] The system according to claim 1, characterized in that the means for identifying the areas for improvement includes analyzing the response received from the generative artificial intelligence and providing instructions for improving the content of the consultation in the next cycle.

[2014] "Example 1"

[2015] (Claim 1)

[2016] A means of querying a generative artificial intelligence, including its areas of expertise, about its specialized fields,

[2017] A means for receiving answers based on the aforementioned specialized field from the aforementioned generative artificial intelligence,

[2018] A means for automatically generating the most suitable consultation content based on the aforementioned specialized field,

[2019] A means for transmitting the consultation content to the generative artificial intelligence and receiving a response,

[2020] A means for analyzing the aforementioned response and identifying areas for improvement in the next cycle,

[2021] Means for executing the next cycle that reflects the aforementioned improvements,

[2022] A system that includes this.

[2023] (Claim 2)

[2024] The system according to claim 1, characterized in that the means for generating consultation content based on the aforementioned specialized field automatically generates consultation content based on information regarding the area of ​​expertise of the generative artificial intelligence.

[2025] (Claim 3)

[2026] The system according to claim 1, characterized in that the means for identifying the areas for improvement includes analyzing the response received from generative artificial intelligence and providing instructions for improving the content of the consultation in the next cycle.

[2027] "Application Example 1"

[2028] (Claim 1)

[2029] A means of querying a generative artificial intelligence, including its areas of expertise, about its specialized fields,

[2030] A means for receiving answers based on the aforementioned specialized field from the aforementioned generative artificial intelligence,

[2031] A means of creating the most suitable consultation content based on the aforementioned specialized field,

[2032] A means for transmitting the consultation content to the generative artificial intelligence and receiving a response,

[2033] A means for analyzing the aforementioned response and identifying areas for improvement,

[2034] A means of executing the next cycle based on the aforementioned improvements,

[2035] A means of creating consultation content regarding the optimization of advertising campaigns and analyzing responses based on generative artificial intelligence,

[2036] Based on the above response, means to improve the storytelling and targeting strategies of advertising campaigns,

[2037] A system that includes this.

[2038] (Claim 2)

[2039] The system according to claim 1, characterized in that the means for creating consultation content based on the aforementioned specialized field automatically generates consultation content based on information regarding the area of ​​expertise of the generative artificial intelligence.

[2040] (Claim 3)

[2041] The system according to claim 1, characterized in that the means for identifying the areas for improvement includes analyzing the response received from the generative artificial intelligence and providing instructions for improving the content of the consultation in the next cycle.

[2042] "Example 2 of combining an emotion engine"

[2043] (Claim 1)

[2044] A means of querying a generative knowledge system, including its areas of expertise, for specialized fields,

[2045] Means for receiving responses based on the specialized field from the generative knowledge system,

[2046] A means for generating optimal consultation content based on the aforementioned specialized field,

[2047] A means for transmitting the consultation content to the generative knowledge system and receiving a response,

[2048] A means for analyzing the aforementioned response and identifying areas for improvement,

[2049] A means of executing the next cycle based on the aforementioned improvements,

[2050] A means including an engine for analyzing the user's emotional state,

[2051] Means for adjusting the content of the consultation based on the aforementioned emotional state,

[2052] A system that includes this.

[2053] (Claim 2)

[2054] The system according to claim 1, characterized in that the means for generating consultation content based on the aforementioned specialized field automatically generates consultation content based on information regarding the area of ​​expertise of the generative knowledge system.

[2055] (Claim 3)

[2056] The system according to claim 1, characterized in that the means for identifying the areas for improvement includes analyzing the response received from the generative knowledge system and providing instructions for improving the content of the consultation in the next cycle.

[2057] "Application example 2 when combining with an emotional engine"

[2058] (Claim 1)

[2059] A means of querying a generative artificial intelligence, including its areas of expertise, about its specialized fields,

[2060] A means for receiving answers based on the aforementioned specialized field from the aforementioned generative artificial intelligence,

[2061] A means of creating the most suitable consultation content based on the aforementioned specialized field,

[2062] A means for transmitting the consultation content to the generative artificial intelligence and receiving a response,

[2063] A means for recognizing the user's emotions and optimizing the consultation content according to the recognized emotional state,

[2064] A means for analyzing the aforementioned response and identifying areas for improvement,

[2065] A means of executing the next cycle based on the aforementioned improvements,

[2066] A system that includes this.

[2067] (Claim 2)

[2068] The system according to claim 1, characterized in that the means for creating consultation content based on the aforementioned specialized field automatically generates consultation content based on information regarding the generative artificial intelligence's area of ​​expertise and adjusts it while taking into account the user's emotional state.

[2069] (Claim 3)

[2070] The system according to claim 1, characterized in that the means for identifying the areas for improvement includes analyzing the response received from the generative artificial intelligence and providing instructions to improve the content of the consultation and the method of providing the response thereto in the next cycle. [Explanation of symbols]

[2071] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of querying a generative artificial intelligence, including its areas of expertise, about its specialized fields, A means for receiving answers based on the aforementioned specialized field from the aforementioned generative artificial intelligence, A means of creating the most suitable consultation content based on the aforementioned specialized field, A means for transmitting the consultation content to the generative artificial intelligence and receiving a response, A means for analyzing the aforementioned response and identifying areas for improvement, A means of executing the next cycle based on the aforementioned improvements, A system that includes this.

2. The system according to claim 1, characterized in that the means for creating consultation content based on the aforementioned specialized field automatically generates consultation content based on information regarding the area of ​​expertise of the generative artificial intelligence.

3. The system according to claim 1, characterized in that the means for identifying the areas for improvement includes analyzing the response received from the generative artificial intelligence and providing instructions for improving the content of the consultation in the next cycle.

Images