System

Abstract

A system is provided.SOLUTION: A system comprising: means for generating a virtual character having various attributes using a generation model; means for adjusting content of a questionnaire based on the virtual character; means for presenting the adjusted questionnaire to a user and collecting answers from the user; means for analyzing the collected answers and obtaining multifaceted insights; and means for generating an analysis result as a report and providing the report to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Traditional market research methods are time-consuming, costly, and often biased toward a specific perspective. This makes it difficult to respond to the diverse needs of today's consumers, limiting product development and marketing activities. This invention aims to gain insights from multiple perspectives by generating virtual characters with different ages, thought patterns, and tastes. This solves the problem of realizing product development that reflects real market feedback more quickly and efficiently. [Means for solving the problem]

[0005] This invention provides a system for generating virtual characters with diverse attributes using a generative model. Specifically, the system adjusts the content of a questionnaire based on the generated character, presents the questionnaire to users, and collects responses. The system also includes a means for analyzing the collected responses and gaining multifaceted insights. Furthermore, the analysis results can be generated as a report and provided to the user, which can be useful for product development. The system's effectiveness and practicality are enhanced by including a means for specifying the attributes of the virtual character and sending instructions to the generative model based on user requests, as well as a means for storing collected response data in a database and generating a report based on the analysis results.

[0006] A "generative model" is an artificial intelligence model that can automatically generate virtual characters with diverse attributes and characteristics.

[0007] A "virtual character" is a fictional character with specific attributes, preferences, and thought patterns, and is used in questionnaires and surveys.

[0008] A "questionnaire" is a means for gathering a subject's thoughts and opinions through specific questions, which in this invention are tailored based on the attributes of the virtual character.

[0009] A "user" is someone who uses this system to conduct questionnaire surveys and use the results to help with product development and marketing activities.

[0010] "Analysis" is the process of evaluating and analyzing the collected survey response data to gain useful insights.

[0011] A "report" is a document or data summarizing the results of an analysis, including specific recommendations and insights that can be useful for product development and marketing activities.

[0012] A "database" is a system that efficiently stores collected data and manages it so that it can be accessed and used as needed.

[0013] "Attributes" refer to specific characteristics, preferences, thought patterns, etc. of a virtual character or user, and are used for survey adjustment and analysis.

[0014] "Insights" are deep understanding and knowledge gained from analysis results, and are important information for product development and marketing strategies. [Brief explanation of the drawings]

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

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

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

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

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

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

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

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

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

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

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

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

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

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

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

[0036] This invention is a system for quickly and efficiently obtaining insights from multiple perspectives during market research and product development. This system operates in cooperation with three parties: a server, a terminal, and a user.

[0037] System Overview

[0038] The core of the system is the server. The server has a unit that uses a generative model to generate virtual characters with various attributes, and adjusts the content of the questionnaire based on the generated characters. The server also collects questionnaire responses submitted by users and analyzes the data. Based on the analysis results, it generates a report and provides it to the user.

[0039] The terminal is a device used by a user to access the system and answer the questionnaire. The user answers the questionnaire provided by the server based on a request and sends the results to the server.

[0040] Program processing

[0041] 1. System startup and initial settings

[0042] The server starts the system and loads the necessary databases and generative models, so the system is ready to operate normally.

[0043] 2. Receiving User Requests

[0044] A user logs into the system using a terminal and inputs a request for character generation related to product development, for example, "generation of a virtual character related to a robot toy for children aged 5 to 10."

[0045] The terminal sends this request to the server.

[0046] 3. Character Generation

[0047] The server analyzes the user's request and sends instructions to the generative model, which then generates a virtual character based on the specified attributes.

[0048] The generative model generates multiple virtual characters based on the request (e.g., an 8-year-old boy who loves sports, a 7-year-old girl who loves reading, etc.) and returns that information to the server.

[0049] 4. Survey generation and adjustment

[0050] The server receives the generated character information and adjusts the questionnaire content based on the character's attributes, constructing specific questions that match each character's interests and preferences.

[0051] The server sends the tailored questionnaire to the terminal for distribution to the user.

[0052] 5. Conducting a survey

[0053] The user uses a terminal to check the questionnaire provided by the server and enters answers from the character's perspective, such as "What kind of robot features are most appealing?"

[0054] The terminal transmits the user's answer to the server.

[0055] 6. Data Collection and Analysis

[0056] The server stores the received response data in a database, and analyzes the stored data to gain multifaceted insights related to the user request.

[0057] The server generates a detailed report based on the insights gained.

[0058] 7. Report generation and provision

[0059] The server generates a report based on the analysis results and provides it to the user, which includes specific recommendations for product development and useful insights based on market needs.

[0060] Specific examples

[0061] For example, if the product development department of a toy manufacturer is planning to develop a "robot toy for children aged 5 to 10," they can use this system as follows:

[0062] 1. A user (a toy manufacturer representative) logs into the system and inputs a request to generate a virtual character.

[0063] 2. The server generates a virtual character with the specified attributes (child aged 5 to 10) based on the generative model.

[0064] 3. The server tailors the survey based on the character and distributes it to the user.

[0065] 4. The user answers the questionnaire and sends the answers to the server.

[0066] 5. The server collects and analyzes the responses to gain multifaceted insights.

[0067] 6. The server generates a report based on the analysis results and provides it to the user.

[0068] This process allows toy manufacturers to efficiently develop products based on market needs and consumer preferences.

[0069] The processing flow will be explained below.

[0070] Step 1:

[0071] The server starts the system and loads the necessary databases and generative models, so the system is ready to operate normally.

[0072] Step 2:

[0073] A user logs in to the system using a terminal. After logging in, the user inputs a request for the generation of a virtual character related to product development. For example, the user requests "generation of a virtual character related to a robot toy for children aged 5 to 10."

[0074] Step 3:

[0075] The device sends this request to the server, which includes the desired character attributes (e.g., age, interests, etc.).

[0076] Step 4:

[0077] The server analyzes the user's request and sends instructions to the generative model, which then generates a virtual character based on the specified attributes.

[0078] Step 5:

[0079] The generative model generates multiple virtual characters based on the request and returns that information to the server, such as an 8-year-old boy who loves sports or a 7-year-old girl who loves reading.

[0080] Step 6:

[0081] The server receives the generated character information and adjusts the questionnaire content based on the character's attributes, constructing specific questions that match each character's interests and preferences.

[0082] Step 7:

[0083] The server sends the tailored questionnaire to the terminal for distribution to the user, the questionnaire including specific questions appropriate for the character.

[0084] Step 8:

[0085] The user uses a terminal to check the questionnaire provided by the server and enters answers from the character's perspective, such as "What kind of robot features are most appealing?"

[0086] Step 9:

[0087] The terminal transmits the user's answers to the server, where the answers are instantly transmitted and recorded.

[0088] Step 10:

[0089] The server stores the received response data in a database, and analyzes the stored data to gain multifaceted insights related to the user request.

[0090] Step 11:

[0091] The server generates a detailed report based on the insights gained, including specific recommendations for product development and useful insights based on market needs.

[0092] Step 12:

[0093] The server generates a report based on the analysis results and provides it to the user, who then uses it as a reference for product development and marketing activities.

[0094] Example 1

[0095] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0096] A lack of methods for quickly and efficiently obtaining insights from diverse perspectives is a challenge in market research and product development. Traditional methods require time-consuming and laborious processes for collecting and analyzing user feedback, making it difficult to obtain accurate market insights. Furthermore, research methods using virtual characters are inadequate, making it difficult to obtain survey results that reflect the diverse needs of users.

[0097] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0098] In this invention, the server includes means for generating virtual characters with various attributes using a generative model, means for adjusting the content of a questionnaire based on the virtual character, means for presenting the adjusted questionnaire to users and collecting responses from them, means for analyzing the collected responses and obtaining multifaceted insights, means for generating a report of the analysis results and providing it to the user, means for loading the necessary database and generative model at system startup and configuring the system for normal operation, means for analyzing the content of user requests before sending instructions to the generative model, and means for saving the responses in a database for collecting them and performing data analysis. This makes it possible to efficiently and accurately obtain market insights from various perspectives.

[0099] A "generative model" is an algorithm that uses machine learning and artificial intelligence techniques to generate data or information based on specific attributes or conditions.

[0100] A "virtual character" refers to a fictional person or entity with specific attributes and conditions created using a generative model.

[0101] "Means for adjusting the content of the survey" refers to a process for changing or optimizing the content of the survey questions based on the attributes of the generated virtual character.

[0102] "Means for collecting responses from users" refers to the process and tools for storing the information users provide in response to the questionnaire in a database or the like.

[0103] "Methods of analyzing responses and gaining multifaceted insights" refers to the process of analyzing collected response data using statistical analysis and machine learning algorithms to extract useful insights from various perspectives.

[0104] "Means for generating a report and providing it to the user" refers to the process of organizing the analysis results, creating a report in the form of a document or graph, etc., and providing it to the user.

[0105] A "database" refers to a system that can efficiently manage, store, and search large amounts of data.

[0106] "Means for configuring the system to operate normally" refers to the process of initializing various data and parameters required when starting the system, and putting the system into a state where it can operate without any problems.

[0107] "Means for analyzing the content of a user's request" refers to a process for analyzing the content of a request entered by a user and determining the necessary processing based on that content.

[0108] This invention is a system in which a server, a terminal, and a user work together. Specifically, it is configured to efficiently obtain insights from various perspectives in market research and product development. The hardware of this system consists of a server and a terminal used by the user. Below, we will explain the details of each component and the program processing method.

[0109] System Components

[0110] 1. Server: This is the central part of the entire system, generating virtual characters using generative models, adjusting survey content, collecting user responses, and analyzing data to gain insights. It uses machine learning frameworks such as TensorFlow and PyTorch, as well as databases such as MongoDB and MySQL.

[0111] 2. Terminal: The device used by the user to access the system and respond to the survey. This includes a variety of devices, such as PCs and smartphones.

[0112] 3. User: Responsible for submitting requests for market research and product development through the system, answering questionnaires and providing data.

[0113] Program processing

[0114] System startup and initial setup

[0115] The server starts the system and loads the necessary databases and generative models, including TensorFlow, PyTorch, MongoDB, and MySQL, to prepare the system for normal operation.

[0116] Receiving user requests

[0117] A user logs into the system using a terminal and submits a request related to product development, for example, "creation of a virtual character for a robot toy for children aged 5 to 10."

[0118] The terminal sends this request to the server, which sends it as an HTTP request.

[0119] Character Generation

[0120] The server analyzes the user's request and sends instructions to a generative model, which is a large-scale language model such as GPT-3 or BERT.

[0121] The generative model generates virtual characters based on the given attributes and returns the character information to the server. For example, it generates an "8-year-old boy who loves sports" and a "7-year-old girl who loves reading."

[0122] Survey generation and coordination

[0123] The server receives the generated character information and adjusts the questionnaire content based on each character's attributes. For example, if a character likes sports, it adds a question such as "Which sport do you like?"

[0124] Conducting a survey

[0125] The user uses a terminal to check the questionnaire provided by the server and enter answers from the character's perspective, such as "What kind of robot features are most appealing?"

[0126] Data collection and analysis

[0127] The server stores the received response data in a database and analyzes it using Python libraries (e.g., Pandas, Scikit-learn).

[0128] Report generation and delivery

[0129] The server generates a detailed report based on the analysis results and provides it to the user. This report is typically generated in PDF format and sent via email.

[0130] Specific examples

[0131] If the product development department of a toy manufacturer were to develop a "robot toy for children aged 5 to 10," they would use this system as follows:

[0132] 1. A user (a toy manufacturer representative) logs into the system and requests the creation of a virtual character for a robot toy for children aged 5 to 10.

[0133] 2. The server analyzes the request and sends instructions to the generative model.

[0134] 3. The server adjusts the questionnaire based on the generated character information and distributes it to the user.

[0135] 4. The user answers the questionnaire and sends the answers to the server.

[0136] 5. The server collects and analyzes the responses to gain multifaceted insights.

[0137] 6. The server generates a report based on the analysis results and provides it to the user.

[0138] Prompt Sentence Examples

[0139] "Generate a virtual character for a robotic toy for children aged 5 to 10. Create a character based on the following attributes: age, gender, interests / preferences (sports, reading, music, science, etc.)."

[0140] By inputting such a specific prompt sentence, it becomes possible to generate a detailed virtual character and conduct a survey based on that character.

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

[0142] Step 1: System startup and initial setup

[0143] The server starts the system and loads the necessary database (e.g., MongoDB or MySQL) and generative model (e.g., GPT-3 or BERT using TensorFlow or PyTorch). Specifically, it loads the database connection information and loads the generative model parameters into memory. This prepares the system for normal operation. The input is the server configuration file and database connection information, and the output is an initialized database connection and the completion of loading the generative model.

[0144] Step 2: Receiving a user request

[0145] A user logs into the system using a terminal and enters a specific request (e.g., "generate a virtual character for a robotic toy for children aged 5 to 10").

[0146] The terminal sends this request to the server as an HTTP request. The input is the request data entered by the user into the terminal (e.g., parameters such as age, interests, etc.), and the output is the request data sent to the server.

[0147] Step 3: Character Generation

[0148] The server analyzes the received user request and sends instructions to the generative model (e.g., GPT-3). API calls are made using Python's requests or flask library. The specific input is the content of the user request, and the output is the generated character information returned by the generative model. For example, data such as an 8-year-old boy who loves sports or a 7-year-old girl who loves reading is generated.

[0149] Step 4: Generate and adjust the survey

[0150] The server receives the character information returned from the generative model and generates a questionnaire based on each character's attributes. It uses a template engine (e.g., Jinja2) to dynamically generate the questionnaire questions. The input is the generated character information, and the output is a tailored questionnaire based on each character's attributes.

[0151] Step 5: Present the survey

[0152] The server sends the adjusted survey to the terminal to distribute it to the user. Specifically, it generates a survey page in HTML format for the terminal's browser and sends it to the terminal. The input is the adjusted survey data, and the output is the survey form displayed on the terminal.

[0153] Step 6: Conduct a survey

[0154] The user answers a questionnaire using the terminal. For example, they answer questions such as "What kind of robot features are attractive?" The input is the response data that the user enters into the terminal, and the output is the response data that the terminal sends to the server.

[0155] Step 7: Data collection and storage

[0156] The server saves the user's answer data in a database. For example, it saves the data in JSON format in MongoDB. The input is the user's answer data, and the output is the answer data stored in the database.

[0157] Step 8: Data analysis

[0158] The server analyzes the response data stored in the database. It uses Python's Pandas and Scikit-learn to reprocess the data and perform statistical and clustering analysis. The input is the response data stored in the database, and the output is the analyzed insight data. It also includes visualizing the results using visualization tools (e.g., Matplotlib and Seaborn).

[0159] Step 9: Generate and serve reports

[0160] The server generates a detailed report based on the analysis results. The report is generated in PDF format and documented using Python's reportlab library. Finally, to provide this report to the user via email, an email module such as smtplib is used. The input is the analyzed insight data, and the output is the generated PDF report and the report sent to the user.

[0161] (Application example 1)

[0162] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0163] In conventional market research and product development, it has been difficult to quickly and efficiently obtain insights from a variety of perspectives. Furthermore, creating advertising strategies tailored to consumer tastes and preferences can be time-consuming and costly. A system that is both efficient and effective is needed to solve these problems.

[0164] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0165] In this invention, the server includes means for generating virtual characters with various attributes using a generative model, means for adjusting a questionnaire or advertising plan based on the virtual character, and means for presenting the adjusted questionnaire or advertising plan to a user and collecting responses and feedback from the user, thereby enabling consumer insights from various perspectives to be obtained quickly and efficiently.

[0166] - "Generative Model" means an artificial intelligence program used to generate the attributes of a virtual character.

[0167] A "virtual character" refers to a virtual person or entity with various attributes, which is generated based on a user's request.

[0168] A "survey" is a survey tool that includes questions for the user, the content of which is tailored based on the attributes of the virtual character.

[0169] "Advertising Plan" means the design of an advertising strategy targeted to a specific target audience and tailored based on the hobbies and preferences of a virtual character.

[0170] "User" refers to an individual or company that uses the system to enter requests and provide responses and feedback.

[0171] "Feedback" refers to answers, reactions, and opinions collected from users, and is information that is useful for improving products and services.

[0172] A "database" is a storage device for storing collected response data and feedback data.

[0173] A "report" is a document summarizing the analysis results and is provided to the user.

[0174] "Insight" refers to new knowledge and understanding gained by analyzing collected data.

[0175] A "means" refers to a method or device used to achieve a particular purpose.

[0176] MODE FOR CARRYING OUT THE INVENTION

[0177] This invention is a system for quickly and efficiently obtaining diverse consumer insights for advertising strategies and market research. This system works in cooperation with three parties: a server, a terminal (such as a smartphone), and a user.

[0178] System Overview

[0179] The center of the system is the server, which has the following main functions:

[0180] 1. Generate a virtual character using a generative model:

[0181] The server uses a generative model based on the user's input request to generate a virtual character with various attributes. The generative model generates the virtual character based on the target demographic information (e.g., age, gender, hobbies, etc.) provided by the user.

[0182] 2. Tailor your advertising plan based on the character:

[0183] The server tailors advertising plans based on the attributes of the generated virtual character, for example, advertising targeted at young people may include advertising messages and visual elements that reflect the character's hobbies and preferences.

[0184] 3. Present the adjusted plan to users and gather feedback:

[0185] The adjusted advertising plan is sent to the user's device (such as a smartphone), and after the user confirms it, they enter their feedback. The server receives and saves this feedback and stores it in a database.

[0186] 4. Analyze the collected data to gain insights:

[0187] The server analyzes the collected feedback data to gain multifaceted insights, which can then be used to improve advertising strategies and make new proposals.

[0188] 5. Generate the report and provide it to the user:

[0189] Finally, a report summarizing the analysis results is generated and provided to the user, detailing the effectiveness of the ad, the target audience's reaction, and suggestions for improvement next time.

[0190] Hardware and software used

[0191] Server: A powerful computer used to host generative models and databases.

[0192] Device: A smartphone, tablet, or computer that allows users to access the system and review advertising plans and provide feedback.

[0193] Generative model: An artificial intelligence-based program used to generate virtual characters (e.g., GPT-3).

[0194] Database: Used to store collected response and feedback data (e.g. MySQL).

[0195] Specific examples

[0196] For example, if a user wants to create a "sneaker ad for young people," the process is as follows:

[0197] 1. Users: Enter details about your target demographic into the app, such as "Young people aged 18-25 who enjoy sports."

[0198] 2. Server: Using the generative model, generate a virtual character (e.g., a 20-year-old college student) based on specified attributes.

[0199] 3. Server: Tailor the messaging and visual elements of sneaker ads based on the attributes of the virtual character.

[0200] 4. Device: Present the adjusted advertising plan to the user's smartphone and collect feedback from the user.

[0201] 5. Server: Analyzes the collected feedback data, gains multifaceted insights, and generates reports.

[0202] 6. Server: Provides the final report to the user.

[0203] Example prompt: "Generate a fictional character for a sneaker advertisement aimed at young people aged 18-25."

[0204] In this way, the system allows users to quickly design and optimize advertising strategies tailored to their target audience.

[0205] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0206] Step 1:

[0207] System startup and initial setup

[0208] The server starts the system and loads the necessary generative model (e.g., GPT-3) and database (e.g., MySQL) on a high-performance computer.

[0209] This process prepares the system for proper operation.

[0210] Input: The generated model and database load commands.

[0211] Output: The model and database are loaded into memory and the system is initialized.

[0212] Step 2:

[0213] Receiving user requests

[0214] A user logs in to the system using a terminal (such as a smartphone).

[0215] Enter target demographic details for your advertising plan (e.g., "Young people aged 18-25 who enjoy sports").

[0216] The terminal sends this request to the server.

[0217] Input: User's request for advertising plan.

[0218] Output: The user request is sent to the server.

[0219] Step 3:

[0220] Character Generation

[0221] The server analyzes the received request and sends instructions to the generative model (e.g., GPT-3).

[0222] The AI ​​model generates a virtual character based on specified attributes.

[0223] For example, a character such as "a 20-year-old college student whose hobby is sports" can be generated.

[0224] Input: Attribute information of the user request.

[0225] Output: Data of the generated virtual character.

[0226] Step 4:

[0227] Creating and adjusting advertising plans

[0228] The server uses the data of the generated virtual character to adjust the advertising plan.

[0229] Advertising messages and visual elements are customized based on each character's hobbies and preferences.

[0230] For example, advertisements aimed at young people who love sports may include visuals of sports equipment and related activities.

[0231] Input: Data of the generated virtual character.

[0232] Output: A tailored advertising plan.

[0233] Step 5:

[0234] Presenting advertising plans and collecting feedback

[0235] The server transmits the adjusted advertising plan to the terminal and presents it to the user.

[0236] The user reviews the advertising plan and enters feedback.

[0237] The terminal sends this feedback to the server.

[0238] Input: Your adjusted advertising plan.

[0239] Output: User feedback data.

[0240] Step 6:

[0241] Data collection and analysis

[0242] The server stores the feedback data in a database and analyzes it.

[0243] In the analysis process, feedback data is statistically analyzed to gain diverse perspectives.

[0244] For example, by aggregating multiple feedback data, the effectiveness of advertising and factors of interest can be identified.

[0245] Input: User feedback data.

[0246] Output: Analysis result data.

[0247] Step 7:

[0248] Report generation and delivery

[0249] The server generates a detailed report based on the analysis results.

[0250] This report includes information such as the effectiveness of the ad, the reaction of the target audience, and areas for improvement next time.

[0251] The generated report is sent to the user's terminal and provided to the user.

[0252] Input: Analysis result data.

[0253] Output: A detailed report provided to the user.

[0254] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0255] This invention is a system that combines a virtual character generation function with an emotion engine that recognizes user emotions to quickly and efficiently obtain multifaceted, emotion-based insights in market research and product development. This system operates in cooperation with four parties: a server, a terminal, an emotion engine, and a user.

[0256] System Overview

[0257] The core of the system is the server. The server has a unit that uses a generative model to generate virtual characters with diverse attributes and adjusts the content of the questionnaire based on the generated characters. The server also collects questionnaire responses submitted by users and analyzes the data. Based on the analysis results, it generates a report and provides it to the user. The system also includes an emotion engine that recognizes the user's emotions in real time and dynamically adjusts the content of the questionnaire.

[0258] The terminal is a device used by users to access the system and answer questionnaires. Based on a user's request, the user answers the questionnaire provided by the server and sends the results to the server. The emotion engine recognizes emotions from the user's facial expressions, tone of voice, etc., and sends that information to the server.

[0259] Program processing

[0260] 1. System startup and initial settings

[0261] The server starts the system and loads the necessary databases, generative models, and emotion engines, so the system is ready to operate normally.

[0262] 2. Receiving User Requests

[0263] A user logs in to the system using a terminal and inputs a request for the generation of a virtual character related to product development, for example, a request for "generation of a virtual character related to a robot toy for children aged 5 to 10."

[0264] The terminal sends this request to the server.

[0265] 3. Character Generation

[0266] The server analyzes the user's request and sends instructions to the generative model, which then generates a virtual character based on the specified attributes.

[0267] The generative model generates multiple virtual characters based on the request and returns that information to the server, such as an 8-year-old boy who loves sports or a 7-year-old girl who loves reading.

[0268] 4. Survey generation and adjustment

[0269] The server receives the generated character information and adjusts the questionnaire content based on the character's attributes, constructing specific questions that match each character's interests and preferences.

[0270] 5. Emotion recognition

[0271] The emotion engine recognizes the user's emotions in real time, analyzing facial expressions and tone of voice while the user is answering the questionnaire, and generates emotion data.

[0272] The emotion engine sends the recognized emotion data to the server.

[0273] 6. Dynamically adjusting surveys

[0274] The server dynamically adjusts the content of the questionnaire based on the emotion data sent from the emotion engine, for example, by determining whether the user is interested in the questions and changing the questions accordingly.

[0275] 7. Conducting a survey

[0276] The user uses a terminal to check the questionnaire provided by the server and enters answers from the character's perspective, such as "What kind of robot features are most appealing?"

[0277] The terminal transmits the user's answer to the server.

[0278] 8. Data Collection and Analysis

[0279] The server stores the received response data in a database, and analyzes the stored data to gain multifaceted insights related to the user request.

[0280] The server generates a detailed report based on the insights gained.

[0281] 9. Report generation and provision

[0282] The server generates a report based on the analysis results and provides it to the user, which includes specific recommendations for product development and useful insights based on market needs.

[0283] Specific examples

[0284] For example, if the product development department of a toy manufacturer is planning to develop a "robot toy for children aged 5 to 10," they can use this system as follows:

[0285] 1. A user (a toy manufacturer representative) logs into the system and inputs a request to generate a virtual character.

[0286] 2. The server generates a virtual character with the specified attributes (child aged 5 to 10) based on the generative model.

[0287] 3. The server tailors the survey based on the character and distributes it to the user.

[0288] 4. While the user answers the questionnaire and sends the answers to the server, the emotion engine recognizes the user's emotions and sends the data to the server in real time.

[0289] 5. The server dynamically adjusts the questionnaire content based on the emotional data and collects the user's responses.

[0290] 6. The server collects and analyzes the responses to gain multifaceted, emotional insights.

[0291] 7. The server generates a report based on the analysis results and provides it to the user.

[0292] This process allows toy manufacturers to efficiently develop products that take into account market needs, consumer preferences, and even emotional responses.

[0293] The processing flow will be explained below.

[0294] Step 1:

[0295] The server starts the system and loads the necessary databases, generative models, and emotion engines, so the system is ready to operate normally.

[0296] Step 2:

[0297] A user logs in to the system using a terminal and inputs a request for the generation of a virtual character related to product development, for example, a request for "generation of a virtual character related to a robot toy for children aged 5 to 10."

[0298] Step 3:

[0299] The device sends this request to the server, which includes the desired character attributes (e.g., age, interests, etc.).

[0300] Step 4:

[0301] The server analyzes the user's request and sends instructions to the generative model, which then generates a virtual character based on the specified attributes.

[0302] Step 5:

[0303] The generative model generates multiple virtual characters based on the request and returns that information to the server, such as an 8-year-old boy who loves sports or a 7-year-old girl who loves reading.

[0304] Step 6:

[0305] The server receives the generated character information and adjusts the questionnaire content based on the character's attributes, constructing specific questions that match each character's interests and preferences.

[0306] Step 7:

[0307] The server sends the tailored questionnaire to the terminal for distribution to the user, the questionnaire including specific questions appropriate for the character.

[0308] Step 8:

[0309] The emotion engine recognizes the user's emotions in real time while they are answering the questionnaire, for example, by using facial expression analysis and voice tone analysis to generate emotion data.

[0310] Step 9:

[0311] The emotion engine transmits the recognized emotion data to the server, where the emotion data includes the user's current emotional state.

[0312] Step 10:

[0313] The server dynamically adjusts the survey content based on the emotion data sent by the emotion engine, for example adding relevant follow-up questions if the user expresses interest in a question.

[0314] Step 11:

[0315] The user continues to answer questionnaires provided by the server using the terminal, and the answers entered by the user are transmitted from the terminal to the server in real time.

[0316] Step 12:

[0317] The server stores the received response data in a database, and analyzes the stored data to gain multifaceted insights related to the user request.

[0318] Step 13:

[0319] The server generates a detailed report based on the insights gained, including specific recommendations for product development and useful insights based on market needs.

[0320] Step 14:

[0321] The server generates a report based on the analysis results and provides it to the user, who then uses it as a reference for product development and marketing activities.

[0322] Specific examples

[0323] For example, if the product development department of a toy manufacturer is planning to develop a "robot toy for children aged 5 to 10," the specific process would be as follows:

[0324] Step 1:

[0325] A user (a toy manufacturer's representative) logs into the system and inputs a request for virtual character generation.

[0326] Step 2:

[0327] The server uses generative models to generate virtual characters for children between the ages of 5 and 10, such as an 8-year-old boy who loves sports or a 7-year-old girl who loves reading.

[0328] Step 3:

[0329] The server then tailors a questionnaire based on the generated character and distributes it to the user. The questionnaire includes questions such as, "What kind of robot features do you find most appealing?"

[0330] Step 4:

[0331] The user answers a questionnaire, while the emotion engine analyzes the user's facial expressions and tone of voice and transmits the emotion data to the server in real time.

[0332] Step 5:

[0333] The server dynamically adjusts the questionnaire content based on the emotion data and collects user responses.

[0334] Step 6:

[0335] The server stores the collected survey responses in a database and analyzes them to gain multifaceted, emotion-based insights.

[0336] Step 7:

[0337] The server generates a report based on the analysis results and provides it to the user, which includes specific recommendations for product development.

[0338] This process allows toy manufacturers to quickly grasp market needs and consumer preferences, and efficiently develop products that also take user emotions into consideration.

[0339] Example 2

[0340] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0341] Traditional market research and product development methods collect data without considering user emotions, resulting in limited insights and a poorly personalized user experience. Furthermore, the survey content is static, making it impossible to dynamically adjust based on user interests. This reduces the accuracy and usefulness of the collected data.

[0342] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0343] In this invention, the server includes means for generating virtual characters with diverse attributes using a generative model, means for adjusting the content of a questionnaire based on the virtual character, means for presenting the adjusted questionnaire to a user and collecting responses from the user, means for recognizing the user's emotions in real time using an emotion recognition engine and dynamically adjusting the content of the questionnaire, means for analyzing the collected responses to gain multifaceted insights, and means for generating a report of the analysis results. This enables the implementation of a questionnaire that reflects the user's emotions, improves the accuracy and usefulness of the collected data, and provides a more personalized user experience.

[0344] A "generative model" is an algorithm for generating virtual characters with diverse attributes based on user requests.

[0345] A "virtual character" is a character with specific attributes created by a generative model, and is used to adjust the content of the questionnaire.

[0346] The "survey content adjustment means" is a process that dynamically changes and adapts the content of the survey questions based on the attributes of the generated virtual character.

[0347] A "tailored questionnaire" is a questionnaire that has been modified and optimized based on the attributes of the virtual character and the user's emotional recognition.

[0348] The "means for collecting responses from users" is a mechanism by which the server receives responses entered by users to the questionnaire and stores them in a database.

[0349] An "emotion recognition engine" is software or hardware that analyzes a user's facial expressions and tone of voice in real time to identify their emotional state.

[0350] "Dynamic adjustment method based on emotion recognition" is a process of adjusting and changing the content of a questionnaire in real time based on information obtained from an emotion recognition engine.

[0351] "Data analysis methods" refers to the process of analyzing collected survey response data using statistical and machine learning techniques to derive multifaceted insights.

[0352] The "report generation means" is a process of creating a report containing useful insights and recommendations for the user based on the analysis results obtained by the data analysis means.

[0353] This invention is a system that uses a generative AI model to generate virtual characters with diverse attributes and dynamically adjusts the content of a survey based on those characters. Furthermore, it combines an emotion recognition engine to recognize users' emotions in real time and dynamically adjust the survey content based on that. This allows for more accurate data collection and insights that reflect users' emotions.

[0354] Hardware and software used

[0355] The system includes the following main components:

[0356] Server: Runs the generative model (e.g., OpenAI's GPT-3) and emotion recognition engine (e.g., Microsoft Azure Emotion API).

[0357] Device: The device through which the user accesses the system and completes the survey, such as a PC, tablet, or smartphone.

[0358] Camera and microphone: Devices used to analyze your facial expressions and tone of voice in real time.

[0359] System operation and concrete examples

[0360] First, the server starts the system and loads the necessary database, generative model, and emotion recognition engine, so the system is ready to operate normally.

[0361] Next, the user logs in to the system using a terminal. A user ID and password are required for login, which are used to verify authorization. The user then inputs a request for the generation of a virtual character related to product development. For example, the user requests "generation of a virtual character related to a robot toy for children aged 5 to 10." The terminal then sends this request to the server.

[0362] The server analyzes the user's request and sends instructions to the generative model, which then generates a virtual character based on the specified attributes. For example, an 8-year-old boy who loves sports or a 7-year-old girl who loves reading might be generated.

[0363] The server then receives the generated character information and adjusts the questionnaire content based on the character's attributes. For example, if a boy likes sports, it might add a question like "What is your favorite sport?", and if a girl likes reading, it might add a question like "What is your favorite genre of book?".

[0364] While the user is answering the survey, an emotion recognition engine analyzes the user's facial expressions and tone of voice to recognize the user's emotions in real time. The recognized emotion data is sent to the server, which then dynamically adjusts the survey content based on that data. For example, if the server determines that the user is interested in a question, it will introduce additional detailed questions.

[0365] Users use their devices to answer the questionnaire, which then transmits the answers to the server, which stores the received data in a database and analyzes it. Based on the analysis results, a report containing useful insights for product development is generated and provided to the user.

[0366] Specific prompt examples

[0367] "Generate a virtual character for children aged 5 to 10, conduct a survey based on the character's attributes, and adjust the survey based on real-time user emotions."

[0368] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0369] Step 1:

[0370] The server starts the system and loads the necessary databases, generative models, and emotion recognition engines.

[0371] Input: System startup command

[0372] Output: Load complete status

[0373] What happens: The server establishes a database connection and loads the generative AI model and emotion recognition software into memory. For example, it connects to an SQL database and initializes the generative AI model (e.g., GPT-3).

[0374] Step 2:

[0375] A user logs in to the system using a terminal. A user ID and password are required to log in, and authorization is confirmed using these.

[0376] Input: User ID, Password

[0377] Output: Login successful message

[0378] Specific operation: The terminal sends the entered user ID and password to the server, which verifies them and, if successful, starts the session.

[0379] Step 3:

[0380] The user inputs a request for the generation of a virtual character related to product development. For example, the user requests "generation of a virtual character related to a robot toy for children aged 5 to 10." The terminal then sends this request to the server.

[0381] Input: Character creation request

[0382] Output: Request receipt confirmation message

[0383] Specific operation: The terminal sends the request content as a prompt to the server, and the server adds it to the queue.

[0384] Step 4:

[0385] The server analyzes the user's request and sends instructions to the generative model, which then generates a virtual character based on the specified attributes.

[0386] Input: Character creation request

[0387] Output: Generated character information

[0388] Specific operation: The server analyzes the request content and sends appropriate prompts to the generative AI model (e.g., GPT-3), which returns multiple character information.

[0389] Step 5:

[0390] The server receives the generated character information and adjusts the content of the questionnaire based on the character's attributes.

[0391] Input: Generated character information

[0392] Output: Adjusted survey

[0393] Specific operation: The server dynamically generates questions based on the character's interests and preferences. For example, for a character who likes sports, the server adds the question "What is your favorite sport?"

[0394] Step 6:

[0395] The emotion recognition engine analyzes the user's facial expressions and tone of voice while they are answering the questionnaire, and recognizes their emotions in real time.

[0396] Input: User's facial expression data, voice data

[0397] Output: Emotion recognition data

[0398] How it works: Data is collected through the camera and microphone connected to the device, and an emotion recognition engine (e.g., Microsoft Azure Emotion API) analyzes it in real time.

[0399] Step 7:

[0400] The server dynamically adjusts the content of the questionnaire based on the emotion recognition data.

[0401] Input: Emotion recognition data

[0402] Output: Dynamically adjusted survey

[0403] Specific operation: The server uses emotion recognition data to change the content of survey questions according to the user's interests and stress level. For example, it changes questions that the user may find difficult to understand into simpler phrases.

[0404] Step 8:

[0405] The user uses the terminal to answer the questionnaire provided by the server.

[0406] Input: Survey Question

[0407] Output: User's answer

[0408] Specific operation: The user fills out a questionnaire and sends the answers to the server. The device then sends the answer data to the server.

[0409] Step 9:

[0410] The server stores the received response data in a database and analyzes the data.

[0411] Input: Answer data

[0412] Output: Analysis results

[0413] Specific operation: The server stores the response data and emotion recognition data in a database and analyzes them using statistical methods and machine learning algorithms.

[0414] Step 10:

[0415] The server generates a detailed report based on the analysis results.

[0416] Input: Analysis results

[0417] Output: Generated report

[0418] Specific operation: The server creates a report containing useful insights based on the analysis results and provides it to the user. For example, a report may be generated that states, "The most popular feature among 8-year-old boys who like sports is the exercise tracker function."

[0419] (Application example 2)

[0420] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0421] Modern advertising delivery systems lack the technology to dynamically adjust advertisements based on user emotions in real time. This results in a lack of timely advertisements that match user interests and preferences, resulting in reduced advertising effectiveness. Furthermore, there is a need for an efficient method to accurately recognize user emotions and instantly adjust advertisement content based on those emotions.

[0422] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0423] In this invention, the server includes means for generating a virtual character with various attributes using a generative model, means for adjusting the content of a questionnaire based on the virtual character, means for presenting the adjusted questionnaire to a user and collecting responses from the user, means for analyzing the collected responses and obtaining multifaceted insights, means for generating a report of the analysis results and providing it to the user, means for recognizing the user's emotions and dynamically adjusting the content of the questionnaire based on the data, means for collecting user emotion data using a sensor attached to the smart device, and means for adjusting and delivering advertisement content based on the emotion data in real time, thereby enabling effective advertisement delivery that responds to the user's emotional state.

[0424] A "generative model" is an algorithm or artificial intelligence mechanism for generating virtual characters.

[0425] A "virtual character" is a character that is generated using digital technology and has a variety of attributes.

[0426] "Means for adjusting the content of the survey" refers to technology or mechanisms for optimizing survey questions based on the attributes of the virtual character.

[0427] "Means for collecting responses from users" refers to the technology and equipment used to collect data from users responding to the questionnaire.

[0428] "Means of gaining multifaceted insights" are methods for analyzing collected data and deriving insights from multiple perspectives.

[0429] "Means for generating a report and providing it to the user" refers to the process or technology for compiling the analysis results in a report format and providing it to the user.

[0430] "Means for recognizing user emotions" refers to technology that infers emotions from the user's facial expressions, tone of voice, etc.

[0431] "Dynamic adjustment means" refers to methods and technologies that change content in real time depending on the state of the data.

[0432] "Smart device" refers to a portable electronic device that can connect to the Internet, including, for example, a smartphone or smart glasses.

[0433] A "sensor" is a device used to collect a user's facial expressions, tone of voice, and other physiological data.

[0434] "Emotion data" is data that indicates the emotional state of the user, and includes, for example, facial expression data and tone of voice data.

[0435] "Means for adjusting and delivering advertising content" refers to a mechanism that changes the content of advertisements based on collected emotional data and displays them to users.

[0436] This invention provides a system that recognizes the user's emotions in real time as they view advertisements using a smart device, and dynamically adjusts and delivers advertisement content. A specific embodiment of this system will be described below.

[0437] System Overview

[0438] The system mainly consists of four components: a server, a terminal, an emotion recognition engine, and a user.

[0439] 1. Server:

[0440] The server is the center of the system, running the generative model and emotion recognition engine. It uses the generative model to generate a virtual character and adjusts the content of the survey based on that character. It also analyzes the response data and emotion data sent by users and adjusts the content of advertisements in real time.

[0441] 2. Terminal:

[0442] The device is the device that the user actually operates, such as smart glasses or a smartphone. The device is equipped with a camera and microphone, which are used to transmit the user's facial expressions and voice to the emotion recognition engine.

[0443] 3. Emotion Recognition Engine:

[0444] The emotion recognition engine analyzes emotions from the user's facial expressions and tone of voice in real time. This engine is built using machine learning frameworks such as TensorFlow. The analyzed emotion data is sent to a server.

[0445] 4. User:

[0446] The user operates the device and is responsible for viewing the advertisements. The user's emotions are recognized in real time, and the advertisements are dynamically adjusted based on that data.

[0447] Data Generation and Processing

[0448] The server uses a generative model to generate a virtual character. The model sets the character's attributes based on a prompt entered by the user. For example, based on a prompt such as "Generate an advertisement for the latest fashion items enjoyed by women in their 20s," the server generates a character that best suits the target user and adjusts the relevant survey.

[0449] Emotion Recognition and Ad Tailoring

[0450] The device (e.g., smart glasses) uses a camera and microphone to capture the user's facial expressions and tone of voice, and then analyzes the data with an emotion recognition engine. This engine predicts the user's emotions based on the collected data and sends the results to a server. The server then dynamically adjusts advertising content based on the received emotional data, enabling more effective ad delivery.

[0451] Specific examples

[0452] For example, imagine a user wearing smart glasses while walking through a shopping mall. When the user views an advertisement displayed on a billboard, the smart glasses' camera and microphone capture the user's facial expressions and tone of voice. This data is analyzed by an emotion recognition engine, and if the user expresses "interest" or "enjoyment," the server adjusts the content displayed on the billboard so that the next relevant product is displayed.

[0453] Hardware and software used

[0454] Hardware: smart glasses, smartphone, camera, microphone

[0455] Software: TensorFlow (machine learning framework), real-time ad server (e.g., AWS, Google Cloud)

[0456] Prompt Sentence Examples

[0457] 1. "Generate ads for the latest fashion items enjoyed by women in their 20s."

[0458] 2. "Show recommended ads based on user interests."

[0459] This allows for effective advertising delivery based on the user's real-time emotional state.

[0460] The above is a specific embodiment of the present invention.

[0461] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0462] Step 1:

[0463] System startup and initial setup

[0464] The server starts the system and loads the necessary database, generative model, and emotion recognition engine. This prepares the system for normal operation. Specifically, the server loads various models and data. The input to this step is an instruction to start the server, and the output is the completion of loading of the model and data.

[0465] Step 2:

[0466] Receiving user requests

[0467] A user logs in to the system using a terminal and inputs a request for generating a virtual character related to product development. For example, the user might input a prompt such as, "Please generate an advertisement for the latest fashion items enjoyed by women in their twenties." The terminal then sends this request to the server. The input is the user request, and the output is the request sent to the server.

[0468] Step 3:

[0469] Character Generation

[0470] The server analyzes the user's request and sends instructions to the generative model. The generative model generates a virtual character based on the specified attributes. The input is the user request, and the output is information about the generated virtual character. The specific operation is to input a prompt to the generative model and generate a character.

[0471] Step 4:

[0472] Survey generation and coordination

[0473] The server receives the generated character information and adjusts the survey content based on the character's attributes. It constructs specific questions that match each character's interests and preferences. The input is virtual character information, and the output is the adjusted survey content. The specific operation is the generation and optimization of survey items.

[0474] Step 5:

[0475] emotion recognition

[0476] The device uses a camera and microphone to capture the user's facial expressions and tone of voice, and sends the data to an emotion recognition engine. The emotion recognition engine recognizes the user's emotions in real time and sends the information to a server. The input is the user's facial and voice data, and the output is recognized emotion data. The specific operations are data capture and emotion recognition.

[0477] Step 6:

[0478] Dynamic survey adjustment

[0479] The server dynamically adjusts the content of the questionnaire based on the emotion data sent from the emotion recognition engine. For example, it determines whether the user is interested in the question and changes the question accordingly. The input is emotion data, and the output is a dynamically adjusted questionnaire. The specific operations are emotion data analysis and questionnaire content adjustment.

[0480] Step 7:

[0481] Conducting a survey

[0482] The user uses the terminal to check the questionnaire provided by the server and input answers from the character's perspective. For example, they answer questions such as "What features of the product are attractive?" The terminal then sends the user's answers to the server. The input is the questionnaire answers, and the output is the sending of the answers to the server. The specific operations are the input and sending of the questionnaire answers.

[0483] Step 8:

[0484] Data collection and analysis

[0485] The server stores the received response data in a database. It then analyzes the stored data to gain multifaceted insights related to the user request. The input is the survey response data, and the output is the analysis results. The specific operations are data storage and analysis.

[0486] Step 9:

[0487] Report generation and delivery

[0488] The server generates a report based on the analysis results and provides it to the user. The report contains specific recommendations that are useful for product development and useful insights based on market needs. The input is the analysis results and the output is the report. The specific operation is generating and providing the report.

[0489] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0490] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0491] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0492] [Second embodiment]

[0493] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0494] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0495] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0496] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0497] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0498] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0499] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0500] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0501] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0502] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0503] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0504] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0505] This invention is a system for quickly and efficiently obtaining insights from multiple perspectives during market research and product development. This system operates in cooperation with three parties: a server, a terminal, and a user.

[0506] System Overview

[0507] The core of the system is the server. The server has a unit that uses a generative model to generate virtual characters with various attributes, and adjusts the content of the questionnaire based on the generated characters. The server also collects questionnaire responses submitted by users and analyzes the data. Based on the analysis results, it generates a report and provides it to the user.

[0508] The terminal is a device used by a user to access the system and answer the questionnaire. The user answers the questionnaire provided by the server based on a request and sends the results to the server.

[0509] Program processing

[0510] 1. System startup and initial settings

[0511] The server starts the system and loads the necessary databases and generative models, so the system is ready to operate normally.

[0512] 2. Receiving User Requests

[0513] A user logs into the system using a terminal and inputs a request for character generation related to product development, for example, "generation of a virtual character related to a robot toy for children aged 5 to 10."

[0514] The terminal sends this request to the server.

[0515] 3. Character Generation

[0516] The server analyzes the user's request and sends instructions to the generative model, which then generates a virtual character based on the specified attributes.

[0517] The generative model generates multiple virtual characters based on the request (e.g., an 8-year-old boy who loves sports, a 7-year-old girl who loves reading, etc.) and returns that information to the server.

[0518] 4. Survey generation and adjustment

[0519] The server receives the generated character information and adjusts the questionnaire content based on the character's attributes, constructing specific questions that match each character's interests and preferences.

[0520] The server sends the tailored questionnaire to the terminal for distribution to the user.

[0521] 5. Conducting a survey

[0522] The user uses a terminal to check the questionnaire provided by the server and enters answers from the character's perspective, such as "What kind of robot features are most appealing?"

[0523] The terminal transmits the user's answer to the server.

[0524] 6. Data Collection and Analysis

[0525] The server stores the received response data in a database, and analyzes the stored data to gain multifaceted insights related to the user request.

[0526] The server generates a detailed report based on the insights gained.

[0527] 7. Report generation and provision

[0528] The server generates a report based on the analysis results and provides it to the user, which includes specific recommendations for product development and useful insights based on market needs.

[0529] Specific examples

[0530] For example, if the product development department of a toy manufacturer is planning to develop a "robot toy for children aged 5 to 10," they can use this system as follows:

[0531] 1. A user (a toy manufacturer representative) logs into the system and inputs a request to generate a virtual character.

[0532] 2. The server generates a virtual character with the specified attributes (child aged 5 to 10) based on the generative model.

[0533] 3. The server tailors the survey based on the character and distributes it to the user.

[0534] 4. The user answers the questionnaire and sends the answers to the server.

[0535] 5. The server collects and analyzes the responses to gain multifaceted insights.

[0536] 6. The server generates a report based on the analysis results and provides it to the user.

[0537] This process allows toy manufacturers to efficiently develop products based on market needs and consumer preferences.

[0538] The processing flow will be explained below.

[0539] Step 1:

[0540] The server starts the system and loads the necessary databases and generative models, so the system is ready to operate normally.

[0541] Step 2:

[0542] A user logs in to the system using a terminal. After logging in, the user inputs a request for the generation of a virtual character related to product development. For example, the user requests "generation of a virtual character related to a robot toy for children aged 5 to 10."

[0543] Step 3:

[0544] The device sends this request to the server, which includes the desired character attributes (e.g., age, interests, etc.).

[0545] Step 4:

[0546] The server analyzes the user's request and sends instructions to the generative model, which then generates a virtual character based on the specified attributes.

[0547] Step 5:

[0548] The generative model generates multiple virtual characters based on the request and returns that information to the server, such as an 8-year-old boy who loves sports or a 7-year-old girl who loves reading.

[0549] Step 6:

[0550] The server receives the generated character information and adjusts the questionnaire content based on the character's attributes, constructing specific questions that match each character's interests and preferences.

[0551] Step 7:

[0552] The server sends the tailored questionnaire to the terminal for distribution to the user, the questionnaire including specific questions appropriate for the character.

[0553] Step 8:

[0554] The user uses a terminal to check the questionnaire provided by the server and enters answers from the character's perspective, such as "What kind of robot features are most appealing?"

[0555] Step 9:

[0556] The terminal transmits the user's answers to the server, where the answers are instantly transmitted and recorded.

[0557] Step 10:

[0558] The server stores the received response data in a database, and analyzes the stored data to gain multifaceted insights related to the user request.

[0559] Step 11:

[0560] The server generates a detailed report based on the insights gained, including specific recommendations for product development and useful insights based on market needs.

[0561] Step 12:

[0562] The server generates a report based on the analysis results and provides it to the user, who then uses it as a reference for product development and marketing activities.

[0563] Example 1

[0564] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0565] A lack of methods for quickly and efficiently obtaining insights from diverse perspectives is a challenge in market research and product development. Traditional methods require time-consuming and laborious processes for collecting and analyzing user feedback, making it difficult to obtain accurate market insights. Furthermore, research methods using virtual characters are inadequate, making it difficult to obtain survey results that reflect the diverse needs of users.

[0566] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0567] In this invention, the server includes means for generating virtual characters with various attributes using a generative model, means for adjusting the content of a questionnaire based on the virtual character, means for presenting the adjusted questionnaire to users and collecting responses from them, means for analyzing the collected responses and obtaining multifaceted insights, means for generating a report of the analysis results and providing it to the user, means for loading the necessary database and generative model at system startup and configuring the system for normal operation, means for analyzing the content of user requests before sending instructions to the generative model, and means for saving the responses in a database for collecting them and performing data analysis. This makes it possible to efficiently and accurately obtain market insights from various perspectives.

[0568] A "generative model" is an algorithm that uses machine learning and artificial intelligence techniques to generate data or information based on specific attributes or conditions.

[0569] A "virtual character" refers to a fictional person or entity with specific attributes and conditions created using a generative model.

[0570] "Means for adjusting the content of the survey" refers to a process for changing or optimizing the content of the survey questions based on the attributes of the generated virtual character.

[0571] "Means for collecting responses from users" refers to the process and tools for storing the information users provide in response to the questionnaire in a database or the like.

[0572] "Methods of analyzing responses and gaining multifaceted insights" refers to the process of analyzing collected response data using statistical analysis and machine learning algorithms to extract useful insights from various perspectives.

[0573] "Means for generating a report and providing it to the user" refers to the process of organizing the analysis results, creating a report in the form of a document or graph, etc., and providing it to the user.

[0574] A "database" refers to a system that can efficiently manage, store, and search large amounts of data.

[0575] "Means for configuring the system to operate normally" refers to the process of initializing various data and parameters required when starting the system, and putting the system into a state where it can operate without any problems.

[0576] "Means for analyzing the content of a user's request" refers to a process for analyzing the content of a request entered by a user and determining the necessary processing based on that content.

[0577] This invention is a system in which a server, a terminal, and a user work together. Specifically, it is configured to efficiently obtain insights from various perspectives in market research and product development. The hardware of this system consists of a server and a terminal used by the user. Below, we will explain the details of each component and the program processing method.

[0578] System Components

[0579] 1. Server: This is the central part of the entire system, generating virtual characters using generative models, adjusting survey content, collecting user responses, and analyzing data to gain insights. It uses machine learning frameworks such as TensorFlow and PyTorch, as well as databases such as MongoDB and MySQL.

[0580] 2. Terminal: The device used by the user to access the system and respond to the survey. This includes a variety of devices, such as PCs and smartphones.

[0581] 3. User: Responsible for submitting requests for market research and product development through the system, answering questionnaires and providing data.

[0582] Program processing

[0583] System startup and initial setup

[0584] The server starts the system and loads the necessary databases and generative models, including TensorFlow, PyTorch, MongoDB, and MySQL, to prepare the system for normal operation.

[0585] Receiving user requests

[0586] A user logs into the system using a terminal and submits a request related to product development, for example, "creation of a virtual character for a robot toy for children aged 5 to 10."

[0587] The terminal sends this request to the server, which sends it as an HTTP request.

[0588] Character Generation

[0589] The server analyzes the user's request and sends instructions to a generative model, which is a large-scale language model such as GPT-3 or BERT.

[0590] The generative model generates virtual characters based on the given attributes and returns the character information to the server. For example, it generates an "8-year-old boy who loves sports" and a "7-year-old girl who loves reading."

[0591] Survey generation and coordination

[0592] The server receives the generated character information and adjusts the questionnaire content based on each character's attributes. For example, if a character likes sports, it adds a question such as "Which sport do you like?"

[0593] Conducting a survey

[0594] The user uses a terminal to check the questionnaire provided by the server and enter answers from the character's perspective, such as "What kind of robot features are most appealing?"

[0595] Data collection and analysis

[0596] The server stores the received response data in a database and analyzes it using Python libraries (e.g., Pandas, Scikit-learn).

[0597] Report generation and delivery

[0598] The server generates a detailed report based on the analysis results and provides it to the user. This report is typically generated in PDF format and sent via email.

[0599] Specific examples

[0600] If the product development department of a toy manufacturer were to develop a "robot toy for children aged 5 to 10," they would use this system as follows:

[0601] 1. A user (a toy manufacturer representative) logs into the system and requests the creation of a virtual character for a robot toy for children aged 5 to 10.

[0602] 2. The server analyzes the request and sends instructions to the generative model.

[0603] 3. The server adjusts the questionnaire based on the generated character information and distributes it to the user.

[0604] 4. The user answers the questionnaire and sends the answers to the server.

[0605] 5. The server collects and analyzes the responses to gain multifaceted insights.

[0606] 6. The server generates a report based on the analysis results and provides it to the user.

[0607] Prompt Sentence Examples

[0608] "Generate a virtual character for a robotic toy for children aged 5 to 10. Create a character based on the following attributes: age, gender, interests / preferences (sports, reading, music, science, etc.)."

[0609] By inputting such a specific prompt sentence, it becomes possible to generate a detailed virtual character and conduct a survey based on that character.

[0610] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0611] Step 1: System startup and initial setup

[0612] The server starts the system and loads the necessary database (e.g., MongoDB or MySQL) and generative model (e.g., GPT-3 or BERT using TensorFlow or PyTorch). Specifically, it loads the database connection information and loads the generative model parameters into memory. This prepares the system for normal operation. The input is the server configuration file and database connection information, and the output is an initialized database connection and the completion of loading the generative model.

[0613] Step 2: Receiving a user request

[0614] A user logs into the system using a terminal and enters a specific request (e.g., "generate a virtual character for a robotic toy for children aged 5 to 10").

[0615] The terminal sends this request to the server as an HTTP request. The input is the request data entered by the user into the terminal (e.g., parameters such as age, interests, etc.), and the output is the request data sent to the server.

[0616] Step 3: Character Generation

[0617] The server analyzes the received user request and sends instructions to the generative model (e.g., GPT-3). API calls are made using Python's requests or flask library. The specific input is the content of the user request, and the output is the generated character information returned by the generative model. For example, data such as an 8-year-old boy who loves sports or a 7-year-old girl who loves reading is generated.

[0618] Step 4: Generate and adjust the survey

[0619] The server receives the character information returned from the generative model and generates a questionnaire based on each character's attributes. It uses a template engine (e.g., Jinja2) to dynamically generate the questionnaire questions. The input is the generated character information, and the output is a tailored questionnaire based on each character's attributes.

[0620] Step 5: Present the survey

[0621] The server sends the adjusted survey to the terminal to distribute it to the user. Specifically, it generates a survey page in HTML format for the terminal's browser and sends it to the terminal. The input is the adjusted survey data, and the output is the survey form displayed on the terminal.

[0622] Step 6: Conduct a survey

[0623] The user answers a questionnaire using the terminal. For example, they answer questions such as "What kind of robot features are attractive?" The input is the response data that the user enters into the terminal, and the output is the response data that the terminal sends to the server.

[0624] Step 7: Data collection and storage

[0625] The server saves the user's answer data in a database. For example, it saves the data in JSON format in MongoDB. The input is the user's answer data, and the output is the answer data stored in the database.

[0626] Step 8: Data analysis

[0627] The server analyzes the response data stored in the database. It uses Python's Pandas and Scikit-learn to reprocess the data and perform statistical and clustering analysis. The input is the response data stored in the database, and the output is the analyzed insight data. It also includes visualizing the results using visualization tools (e.g., Matplotlib and Seaborn).

[0628] Step 9: Generate and serve reports

[0629] The server generates a detailed report based on the analysis results. The report is generated in PDF format and documented using Python's reportlab library. Finally, to provide this report to the user via email, an email module such as smtplib is used. The input is the analyzed insight data, and the output is the generated PDF report and the report sent to the user.

[0630] (Application example 1)

[0631] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0632] In conventional market research and product development, it has been difficult to quickly and efficiently obtain insights from a variety of perspectives. Furthermore, creating advertising strategies tailored to consumer tastes and preferences can be time-consuming and costly. A system that is both efficient and effective is needed to solve these problems.

[0633] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0634] In this invention, the server includes means for generating virtual characters with various attributes using a generative model, means for adjusting a questionnaire or advertising plan based on the virtual character, and means for presenting the adjusted questionnaire or advertising plan to a user and collecting responses and feedback from the user, thereby enabling consumer insights from various perspectives to be obtained quickly and efficiently.

[0635] - "Generative Model" means an artificial intelligence program used to generate the attributes of a virtual character.

[0636] A "virtual character" refers to a virtual person or entity with various attributes, which is generated based on a user's request.

[0637] A "survey" is a survey tool that includes questions for the user, the content of which is tailored based on the attributes of the virtual character.

[0638] "Advertising Plan" means the design of an advertising strategy targeted to a specific target audience and tailored based on the hobbies and preferences of a virtual character.

[0639] "User" refers to an individual or company that uses the system to enter requests and provide responses and feedback.

[0640] "Feedback" refers to answers, reactions, and opinions collected from users, and is information that is useful for improving products and services.

[0641] A "database" is a storage device for storing collected response data and feedback data.

[0642] A "report" is a document summarizing the analysis results and is provided to the user.

[0643] "Insight" refers to new knowledge and understanding gained by analyzing collected data.

[0644] A "means" refers to a method or device used to achieve a particular purpose.

[0645] MODE FOR CARRYING OUT THE INVENTION

[0646] This invention is a system for quickly and efficiently obtaining diverse consumer insights for advertising strategies and market research. This system works in cooperation with three parties: a server, a terminal (such as a smartphone), and a user.

[0647] System Overview

[0648] The center of the system is the server, which has the following main functions:

[0649] 1. Generate a virtual character using a generative model:

[0650] The server uses a generative model based on the user's input request to generate a virtual character with various attributes. The generative model generates the virtual character based on the target demographic information (e.g., age, gender, hobbies, etc.) provided by the user.

[0651] 2. Tailor your advertising plan based on the character:

[0652] The server tailors advertising plans based on the attributes of the generated virtual character, for example, advertising targeted at young people may include advertising messages and visual elements that reflect the character's hobbies and preferences.

[0653] 3. Present the adjusted plan to users and gather feedback:

[0654] The adjusted advertising plan is sent to the user's device (such as a smartphone), and after the user confirms it, they enter their feedback. The server receives and saves this feedback and stores it in a database.

[0655] 4. Analyze the collected data to gain insights:

[0656] The server analyzes the collected feedback data to gain multifaceted insights, which can then be used to improve advertising strategies and make new proposals.

[0657] 5. Generate the report and provide it to the user:

[0658] Finally, a report summarizing the analysis results is generated and provided to the user, detailing the effectiveness of the ad, the target audience's reaction, and suggestions for improvement next time.

[0659] Hardware and software used

[0660] Server: A powerful computer used to host generative models and databases.

[0661] Device: A smartphone, tablet, or computer that allows users to access the system and review advertising plans and provide feedback.

[0662] Generative model: An artificial intelligence-based program used to generate virtual characters (e.g., GPT-3).

[0663] Database: Used to store collected response and feedback data (e.g. MySQL).

[0664] Specific examples

[0665] For example, if a user wants to create a "sneaker ad for young people," the process is as follows:

[0666] 1. Users: Enter details about your target demographic into the app, such as "Young people aged 18-25 who enjoy sports."

[0667] 2. Server: Using the generative model, generate a virtual character (e.g., a 20-year-old college student) based on specified attributes.

[0668] 3. Server: Tailor the messaging and visual elements of sneaker ads based on the attributes of the virtual character.

[0669] 4. Device: Present the adjusted advertising plan to the user's smartphone and collect feedback from the user.

[0670] 5. Server: Analyzes the collected feedback data, gains multifaceted insights, and generates reports.

[0671] 6. Server: Provides the final report to the user.

[0672] Example prompt: "Generate a fictional character for a sneaker advertisement aimed at young people aged 18-25."

[0673] In this way, the system allows users to quickly design and optimize advertising strategies tailored to their target audience.

[0674] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0675] Step 1:

[0676] System startup and initial setup

[0677] The server starts the system and loads the necessary generative model (e.g., GPT-3) and database (e.g., MySQL) on a high-performance computer.

[0678] This process prepares the system for proper operation.

[0679] Input: The generated model and database load commands.

[0680] Output: The model and database are loaded into memory and the system is initialized.

[0681] Step 2:

[0682] Receiving user requests

[0683] A user logs in to the system using a terminal (such as a smartphone).

[0684] Enter target demographic details for your advertising plan (e.g., "Young people aged 18-25 who enjoy sports").

[0685] The terminal sends this request to the server.

[0686] Input: User's request for advertising plan.

[0687] Output: The user request is sent to the server.

[0688] Step 3:

[0689] Character Generation

[0690] The server analyzes the received request and sends instructions to the generative model (e.g., GPT-3).

[0691] The AI ​​model generates a virtual character based on specified attributes.

[0692] For example, a character such as "a 20-year-old college student whose hobby is sports" can be generated.

[0693] Input: Attribute information of the user request.

[0694] Output: Data of the generated virtual character.

[0695] Step 4:

[0696] Creating and adjusting advertising plans

[0697] The server uses the data of the generated virtual character to adjust the advertising plan.

[0698] Advertising messages and visual elements are customized based on each character's hobbies and preferences.

[0699] For example, advertisements aimed at young people who love sports may include visuals of sports equipment and related activities.

[0700] Input: Data of the generated virtual character.

[0701] Output: A tailored advertising plan.

[0702] Step 5:

[0703] Presenting advertising plans and collecting feedback

[0704] The server transmits the adjusted advertising plan to the terminal and presents it to the user.

[0705] The user reviews the advertising plan and enters feedback.

[0706] The terminal sends this feedback to the server.

[0707] Input: Your adjusted advertising plan.

[0708] Output: User feedback data.

[0709] Step 6:

[0710] Data collection and analysis

[0711] The server stores the feedback data in a database and analyzes it.

[0712] In the analysis process, feedback data is statistically analyzed to gain diverse perspectives.

[0713] For example, by aggregating multiple feedback data, the effectiveness of advertising and factors of interest can be identified.

[0714] Input: User feedback data.

[0715] Output: Analysis result data.

[0716] Step 7:

[0717] Report generation and delivery

[0718] The server generates a detailed report based on the analysis results.

[0719] This report includes information such as the effectiveness of the ad, the reaction of the target audience, and areas for improvement next time.

[0720] The generated report is sent to the user's terminal and provided to the user.

[0721] Input: Analysis result data.

[0722] Output: A detailed report provided to the user.

[0723] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0724] This invention is a system that combines a virtual character generation function with an emotion engine that recognizes user emotions to quickly and efficiently obtain multifaceted, emotion-based insights in market research and product development. This system operates in cooperation with four parties: a server, a terminal, an emotion engine, and a user.

[0725] System Overview

[0726] The core of the system is the server. The server has a unit that uses a generative model to generate virtual characters with diverse attributes and adjusts the content of the questionnaire based on the generated characters. The server also collects questionnaire responses submitted by users and analyzes the data. Based on the analysis results, it generates a report and provides it to the user. The system also includes an emotion engine that recognizes the user's emotions in real time and dynamically adjusts the content of the questionnaire.

[0727] The terminal is a device used by users to access the system and answer questionnaires. Based on a user's request, the user answers the questionnaire provided by the server and sends the results to the server. The emotion engine recognizes emotions from the user's facial expressions, tone of voice, etc., and sends that information to the server.

[0728] Program processing

[0729] 1. System startup and initial settings

[0730] The server starts the system and loads the necessary databases, generative models, and emotion engines, so the system is ready to operate normally.

[0731] 2. Receiving User Requests

[0732] A user logs in to the system using a terminal and inputs a request for the generation of a virtual character related to product development, for example, a request for "generation of a virtual character related to a robot toy for children aged 5 to 10."

[0733] The terminal sends this request to the server.

[0734] 3. Character Generation

[0735] The server analyzes the user's request and sends instructions to the generative model, which then generates a virtual character based on the specified attributes.

[0736] The generative model generates multiple virtual characters based on the request and returns that information to the server, such as an 8-year-old boy who loves sports or a 7-year-old girl who loves reading.

[0737] 4. Survey generation and adjustment

[0738] The server receives the generated character information and adjusts the questionnaire content based on the character's attributes, constructing specific questions that match each character's interests and preferences.

[0739] 5. Emotion recognition

[0740] The emotion engine recognizes the user's emotions in real time, analyzing facial expressions and tone of voice while the user is answering the questionnaire, and generates emotion data.

[0741] The emotion engine sends the recognized emotion data to the server.

[0742] 6. Dynamically adjusting surveys

[0743] The server dynamically adjusts the content of the questionnaire based on the emotion data sent from the emotion engine, for example, by determining whether the user is interested in the questions and changing the questions accordingly.

[0744] 7. Conducting a survey

[0745] The user uses a terminal to check the questionnaire provided by the server and enters answers from the character's perspective, such as "What kind of robot features are most appealing?"

[0746] The terminal transmits the user's answer to the server.

[0747] 8. Data Collection and Analysis

[0748] The server stores the received response data in a database, and analyzes the stored data to gain multifaceted insights related to the user request.

[0749] The server generates a detailed report based on the insights gained.

[0750] 9. Report generation and provision

[0751] The server generates a report based on the analysis results and provides it to the user, which includes specific recommendations for product development and useful insights based on market needs.

[0752] Specific examples

[0753] For example, if the product development department of a toy manufacturer is planning to develop a "robot toy for children aged 5 to 10," they can use this system as follows:

[0754] 1. A user (a toy manufacturer representative) logs into the system and inputs a request to generate a virtual character.

[0755] 2. The server generates a virtual character with the specified attributes (child aged 5 to 10) based on the generative model.

[0756] 3. The server tailors the survey based on the character and distributes it to the user.

[0757] 4. While the user answers the questionnaire and sends the answers to the server, the emotion engine recognizes the user's emotions and sends the data to the server in real time.

[0758] 5. The server dynamically adjusts the questionnaire content based on the emotional data and collects the user's responses.

[0759] 6. The server collects and analyzes the responses to gain multifaceted, emotional insights.

[0760] 7. The server generates a report based on the analysis results and provides it to the user.

[0761] This process allows toy manufacturers to efficiently develop products that take into account market needs, consumer preferences, and even emotional responses.

[0762] The processing flow will be explained below.

[0763] Step 1:

[0764] The server starts the system and loads the necessary databases, generative models, and emotion engines, so the system is ready to operate normally.

[0765] Step 2:

[0766] A user logs in to the system using a terminal and inputs a request for the generation of a virtual character related to product development, for example, a request for "generation of a virtual character related to a robot toy for children aged 5 to 10."

[0767] Step 3:

[0768] The device sends this request to the server, which includes the desired character attributes (e.g., age, interests, etc.).

[0769] Step 4:

[0770] The server analyzes the user's request and sends instructions to the generative model, which then generates a virtual character based on the specified attributes.

[0771] Step 5:

[0772] The generative model generates multiple virtual characters based on the request and returns that information to the server, such as an 8-year-old boy who loves sports or a 7-year-old girl who loves reading.

[0773] Step 6:

[0774] The server receives the generated character information and adjusts the questionnaire content based on the character's attributes, constructing specific questions that match each character's interests and preferences.

[0775] Step 7:

[0776] The server sends the tailored questionnaire to the terminal for distribution to the user, the questionnaire including specific questions appropriate for the character.

[0777] Step 8:

[0778] The emotion engine recognizes the user's emotions in real time while they are answering the questionnaire, for example, by using facial expression analysis and voice tone analysis to generate emotion data.

[0779] Step 9:

[0780] The emotion engine transmits the recognized emotion data to the server, where the emotion data includes the user's current emotional state.

[0781] Step 10:

[0782] The server dynamically adjusts the survey content based on the emotion data sent by the emotion engine, for example adding relevant follow-up questions if the user expresses interest in a question.

[0783] Step 11:

[0784] The user continues to answer questionnaires provided by the server using the terminal, and the answers entered by the user are transmitted from the terminal to the server in real time.

[0785] Step 12:

[0786] The server stores the received response data in a database, and analyzes the stored data to gain multifaceted insights related to the user request.

[0787] Step 13:

[0788] The server generates a detailed report based on the insights gained, including specific recommendations for product development and useful insights based on market needs.

[0789] Step 14:

[0790] The server generates a report based on the analysis results and provides it to the user, who then uses it as a reference for product development and marketing activities.

[0791] Specific examples

[0792] For example, if the product development department of a toy manufacturer is planning to develop a "robot toy for children aged 5 to 10," the specific process would be as follows:

[0793] Step 1:

[0794] A user (a toy manufacturer's representative) logs into the system and inputs a request for virtual character generation.

[0795] Step 2:

[0796] The server uses generative models to generate virtual characters for children between the ages of 5 and 10, such as an 8-year-old boy who loves sports or a 7-year-old girl who loves reading.

[0797] Step 3:

[0798] The server then tailors a questionnaire based on the generated character and distributes it to the user. The questionnaire includes questions such as, "What kind of robot features do you find most appealing?"

[0799] Step 4:

[0800] The user answers a questionnaire, while the emotion engine analyzes the user's facial expressions and tone of voice and transmits the emotion data to the server in real time.

[0801] Step 5:

[0802] The server dynamically adjusts the questionnaire content based on the emotion data and collects user responses.

[0803] Step 6:

[0804] The server stores the collected survey responses in a database and analyzes them to gain multifaceted, emotion-based insights.

[0805] Step 7:

[0806] The server generates a report based on the analysis results and provides it to the user, which includes specific recommendations for product development.

[0807] This process allows toy manufacturers to quickly grasp market needs and consumer preferences, and efficiently develop products that also take user emotions into consideration.

[0808] Example 2

[0809] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0810] Traditional market research and product development methods collect data without considering user emotions, resulting in limited insights and a poorly personalized user experience. Furthermore, the survey content is static, making it impossible to dynamically adjust based on user interests. This reduces the accuracy and usefulness of the collected data.

[0811] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0812] In this invention, the server includes means for generating virtual characters with diverse attributes using a generative model, means for adjusting the content of a questionnaire based on the virtual character, means for presenting the adjusted questionnaire to a user and collecting responses from the user, means for recognizing the user's emotions in real time using an emotion recognition engine and dynamically adjusting the content of the questionnaire, means for analyzing the collected responses to gain multifaceted insights, and means for generating a report of the analysis results. This enables the implementation of a questionnaire that reflects the user's emotions, improves the accuracy and usefulness of the collected data, and provides a more personalized user experience.

[0813] A "generative model" is an algorithm for generating virtual characters with diverse attributes based on user requests.

[0814] A "virtual character" is a character with specific attributes created by a generative model, and is used to adjust the content of the questionnaire.

[0815] The "survey content adjustment means" is a process that dynamically changes and adapts the content of the survey questions based on the attributes of the generated virtual character.

[0816] A "tailored questionnaire" is a questionnaire that has been modified and optimized based on the attributes of the virtual character and the user's emotional recognition.

[0817] The "means for collecting responses from users" is a mechanism by which the server receives responses entered by users to the questionnaire and stores them in a database.

[0818] An "emotion recognition engine" is software or hardware that analyzes a user's facial expressions and tone of voice in real time to identify their emotional state.

[0819] "Dynamic adjustment method based on emotion recognition" is a process of adjusting and changing the content of a questionnaire in real time based on information obtained from an emotion recognition engine.

[0820] "Data analysis methods" refers to the process of analyzing collected survey response data using statistical and machine learning techniques to derive multifaceted insights.

[0821] The "report generation means" is a process of creating a report containing useful insights and recommendations for the user based on the analysis results obtained by the data analysis means.

[0822] This invention is a system that uses a generative AI model to generate virtual characters with diverse attributes and dynamically adjusts the content of a survey based on those characters. Furthermore, it combines an emotion recognition engine to recognize users' emotions in real time and dynamically adjust the survey content based on that. This allows for more accurate data collection and insights that reflect users' emotions.

[0823] Hardware and software used

[0824] The system includes the following main components:

[0825] Server: Runs the generative model (e.g., OpenAI's GPT-3) and emotion recognition engine (e.g., Microsoft Azure Emotion API).

[0826] Device: The device through which the user accesses the system and completes the survey, such as a PC, tablet, or smartphone.

[0827] Camera and microphone: Devices used to analyze your facial expressions and tone of voice in real time.

[0828] System operation and concrete examples

[0829] First, the server starts the system and loads the necessary database, generative model, and emotion recognition engine, so the system is ready to operate normally.

[0830] Next, the user logs in to the system using a terminal. A user ID and password are required for login, which are used to verify authorization. The user then inputs a request for the generation of a virtual character related to product development. For example, the user requests "generation of a virtual character related to a robot toy for children aged 5 to 10." The terminal then sends this request to the server.

[0831] The server analyzes the user's request and sends instructions to the generative model, which then generates a virtual character based on the specified attributes. For example, an 8-year-old boy who loves sports or a 7-year-old girl who loves reading might be generated.

[0832] The server then receives the generated character information and adjusts the questionnaire content based on the character's attributes. For example, if a boy likes sports, it might add a question like "What is your favorite sport?", and if a girl likes reading, it might add a question like "What is your favorite genre of book?".

[0833] While the user is answering the survey, an emotion recognition engine analyzes the user's facial expressions and tone of voice to recognize the user's emotions in real time. The recognized emotion data is sent to the server, which then dynamically adjusts the survey content based on that data. For example, if the server determines that the user is interested in a question, it will introduce additional detailed questions.

[0834] Users use their devices to answer the questionnaire, which then transmits the answers to the server, which stores the received data in a database and analyzes it. Based on the analysis results, a report containing useful insights for product development is generated and provided to the user.

[0835] Specific prompt examples

[0836] "Generate a virtual character for children aged 5 to 10, conduct a survey based on the character's attributes, and adjust the survey based on real-time user emotions."

[0837] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0838] Step 1:

[0839] The server starts the system and loads the necessary databases, generative models, and emotion recognition engines.

[0840] Input: System startup command

[0841] Output: Load complete status

[0842] What happens: The server establishes a database connection and loads the generative AI model and emotion recognition software into memory. For example, it connects to an SQL database and initializes the generative AI model (e.g., GPT-3).

[0843] Step 2:

[0844] A user logs in to the system using a terminal. A user ID and password are required to log in, and authorization is confirmed using these.

[0845] Input: User ID, Password

[0846] Output: Login successful message

[0847] Specific operation: The terminal sends the entered user ID and password to the server, which verifies them and, if successful, starts the session.

[0848] Step 3:

[0849] The user inputs a request for the generation of a virtual character related to product development. For example, the user requests "generation of a virtual character related to a robot toy for children aged 5 to 10." The terminal then sends this request to the server.

[0850] Input: Character creation request

[0851] Output: Request receipt confirmation message

[0852] Specific operation: The terminal sends the request content as a prompt to the server, and the server adds it to the queue.

[0853] Step 4:

[0854] The server analyzes the user's request and sends instructions to the generative model, which then generates a virtual character based on the specified attributes.

[0855] Input: Character creation request

[0856] Output: Generated character information

[0857] Specific operation: The server analyzes the request content and sends appropriate prompts to the generative AI model (e.g., GPT-3), which returns multiple character information.

[0858] Step 5:

[0859] The server receives the generated character information and adjusts the content of the questionnaire based on the character's attributes.

[0860] Input: Generated character information

[0861] Output: Adjusted survey

[0862] Specific operation: The server dynamically generates questions based on the character's interests and preferences. For example, for a character who likes sports, the server adds the question "What is your favorite sport?"

[0863] Step 6:

[0864] The emotion recognition engine analyzes the user's facial expressions and tone of voice while they are answering the questionnaire, and recognizes their emotions in real time.

[0865] Input: User's facial expression data, voice data

[0866] Output: Emotion recognition data

[0867] How it works: Data is collected through the camera and microphone connected to the device, and an emotion recognition engine (e.g., Microsoft Azure Emotion API) analyzes it in real time.

[0868] Step 7:

[0869] The server dynamically adjusts the content of the questionnaire based on the emotion recognition data.

[0870] Input: Emotion recognition data

[0871] Output: Dynamically adjusted survey

[0872] Specific operation: The server uses emotion recognition data to change the content of survey questions according to the user's interests and stress level. For example, it changes questions that the user may find difficult to understand into simpler phrases.

[0873] Step 8:

[0874] The user uses the terminal to answer the questionnaire provided by the server.

[0875] Input: Survey Question

[0876] Output: User's answer

[0877] Specific operation: The user fills out a questionnaire and sends the answers to the server. The device then sends the answer data to the server.

[0878] Step 9:

[0879] The server stores the received response data in a database and analyzes the data.

[0880] Input: Answer data

[0881] Output: Analysis results

[0882] Specific operation: The server stores the response data and emotion recognition data in a database and analyzes them using statistical methods and machine learning algorithms.

[0883] Step 10:

[0884] The server generates a detailed report based on the analysis results.

[0885] Input: Analysis results

[0886] Output: Generated report

[0887] Specific operation: The server creates a report containing useful insights based on the analysis results and provides it to the user. For example, a report may be generated that states, "The most popular feature among 8-year-old boys who like sports is the exercise tracker function."

[0888] (Application example 2)

[0889] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0890] Modern advertising delivery systems lack the technology to dynamically adjust advertisements based on user emotions in real time. This results in a lack of timely advertisements that match user interests and preferences, resulting in reduced advertising effectiveness. Furthermore, there is a need for an efficient method to accurately recognize user emotions and instantly adjust advertisement content based on those emotions.

[0891] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0892] In this invention, the server includes means for generating a virtual character with various attributes using a generative model, means for adjusting the content of a questionnaire based on the virtual character, means for presenting the adjusted questionnaire to a user and collecting responses from the user, means for analyzing the collected responses and obtaining multifaceted insights, means for generating a report of the analysis results and providing it to the user, means for recognizing the user's emotions and dynamically adjusting the content of the questionnaire based on the data, means for collecting user emotion data using a sensor attached to the smart device, and means for adjusting and delivering advertisement content based on the emotion data in real time, thereby enabling effective advertisement delivery that responds to the user's emotional state.

[0893] A "generative model" is an algorithm or artificial intelligence mechanism for generating virtual characters.

[0894] A "virtual character" is a character that is generated using digital technology and has a variety of attributes.

[0895] "Means for adjusting the content of the survey" refers to technology or mechanisms for optimizing survey questions based on the attributes of the virtual character.

[0896] "Means for collecting responses from users" refers to the technology and equipment used to collect data from users responding to the questionnaire.

[0897] "Means of gaining multifaceted insights" are methods for analyzing collected data and deriving insights from multiple perspectives.

[0898] "Means for generating a report and providing it to the user" refers to the process or technology for compiling the analysis results in a report format and providing it to the user.

[0899] "Means for recognizing user emotions" refers to technology that infers emotions from the user's facial expressions, tone of voice, etc.

[0900] "Dynamic adjustment means" refers to methods and technologies that change content in real time depending on the state of the data.

[0901] "Smart device" refers to a portable electronic device that can connect to the Internet, including, for example, a smartphone or smart glasses.

[0902] A "sensor" is a device used to collect a user's facial expressions, tone of voice, and other physiological data.

[0903] "Emotion data" is data that indicates the emotional state of the user, and includes, for example, facial expression data and tone of voice data.

[0904] "Means for adjusting and delivering advertising content" refers to a mechanism that changes the content of advertisements based on collected emotional data and displays them to users.

[0905] This invention provides a system that recognizes the user's emotions in real time as they view advertisements using a smart device, and dynamically adjusts and delivers advertisement content. A specific embodiment of this system will be described below.

[0906] System Overview

[0907] The system mainly consists of four components: a server, a terminal, an emotion recognition engine, and a user.

[0908] 1. Server:

[0909] The server is the center of the system, running the generative model and emotion recognition engine. It uses the generative model to generate a virtual character and adjusts the content of the survey based on that character. It also analyzes the response data and emotion data sent by users and adjusts the content of advertisements in real time.

[0910] 2. Terminal:

[0911] The device is the device that the user actually operates, such as smart glasses or a smartphone. The device is equipped with a camera and microphone, which are used to transmit the user's facial expressions and voice to the emotion recognition engine.

[0912] 3. Emotion Recognition Engine:

[0913] The emotion recognition engine analyzes emotions from the user's facial expressions and tone of voice in real time. This engine is built using machine learning frameworks such as TensorFlow. The analyzed emotion data is sent to a server.

[0914] 4. User:

[0915] The user operates the device and is responsible for viewing the advertisements. The user's emotions are recognized in real time, and the advertisements are dynamically adjusted based on that data.

[0916] Data Generation and Processing

[0917] The server uses a generative model to generate a virtual character. The model sets the character's attributes based on a prompt entered by the user. For example, based on a prompt such as "Generate an advertisement for the latest fashion items enjoyed by women in their 20s," the server generates a character that best suits the target user and adjusts the relevant survey.

[0918] Emotion Recognition and Ad Tailoring

[0919] The device (e.g., smart glasses) uses a camera and microphone to capture the user's facial expressions and tone of voice, and then analyzes the data with an emotion recognition engine. This engine predicts the user's emotions based on the collected data and sends the results to a server. The server then dynamically adjusts advertising content based on the received emotional data, enabling more effective ad delivery.

[0920] Specific examples

[0921] For example, imagine a user wearing smart glasses while walking through a shopping mall. When the user views an advertisement displayed on a billboard, the smart glasses' camera and microphone capture the user's facial expressions and tone of voice. This data is analyzed by an emotion recognition engine, and if the user expresses "interest" or "enjoyment," the server adjusts the content displayed on the billboard so that the next relevant product is displayed.

[0922] Hardware and software used

[0923] Hardware: smart glasses, smartphone, camera, microphone

[0924] Software: TensorFlow (machine learning framework), real-time ad server (e.g., AWS, Google Cloud)

[0925] Prompt Sentence Examples

[0926] 1. "Generate ads for the latest fashion items enjoyed by women in their 20s."

[0927] 2. "Show recommended ads based on user interests."

[0928] This allows for effective advertising delivery based on the user's real-time emotional state.

[0929] The above is a specific embodiment of the present invention.

[0930] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0931] Step 1:

[0932] System startup and initial setup

[0933] The server starts the system and loads the necessary database, generative model, and emotion recognition engine. This prepares the system for normal operation. Specifically, the server loads various models and data. The input to this step is an instruction to start the server, and the output is the completion of loading of the model and data.

[0934] Step 2:

[0935] Receiving user requests

[0936] A user logs in to the system using a terminal and inputs a request for generating a virtual character related to product development. For example, the user might input a prompt such as, "Please generate an advertisement for the latest fashion items enjoyed by women in their twenties." The terminal then sends this request to the server. The input is the user request, and the output is the request sent to the server.

[0937] Step 3:

[0938] Character Generation

[0939] The server analyzes the user's request and sends instructions to the generative model. The generative model generates a virtual character based on the specified attributes. The input is the user request, and the output is information about the generated virtual character. The specific operation is to input a prompt to the generative model and generate a character.

[0940] Step 4:

[0941] Survey generation and coordination

[0942] The server receives the generated character information and adjusts the survey content based on the character's attributes. It constructs specific questions that match each character's interests and preferences. The input is virtual character information, and the output is the adjusted survey content. The specific operation is the generation and optimization of survey items.

[0943] Step 5:

[0944] emotion recognition

[0945] The device uses a camera and microphone to capture the user's facial expressions and tone of voice, and sends the data to an emotion recognition engine. The emotion recognition engine recognizes the user's emotions in real time and sends the information to a server. The input is the user's facial and voice data, and the output is recognized emotion data. The specific operations are data capture and emotion recognition.

[0946] Step 6:

[0947] Dynamic survey adjustment

[0948] The server dynamically adjusts the content of the questionnaire based on the emotion data sent from the emotion recognition engine. For example, it determines whether the user is interested in the question and changes the question accordingly. The input is emotion data, and the output is a dynamically adjusted questionnaire. The specific operations are emotion data analysis and questionnaire content adjustment.

[0949] Step 7:

[0950] Conducting a survey

[0951] The user uses the terminal to check the questionnaire provided by the server and input answers from the character's perspective. For example, they answer questions such as "What features of the product are attractive?" The terminal then sends the user's answers to the server. The input is the questionnaire answers, and the output is the sending of the answers to the server. The specific operations are the input and sending of the questionnaire answers.

[0952] Step 8:

[0953] Data collection and analysis

[0954] The server stores the received response data in a database. It then analyzes the stored data to gain multifaceted insights related to the user request. The input is the survey response data, and the output is the analysis results. The specific operations are data storage and analysis.

[0955] Step 9:

[0956] Report generation and delivery

[0957] The server generates a report based on the analysis results and provides it to the user. The report contains specific recommendations that are useful for product development and useful insights based on market needs. The input is the analysis results and the output is the report. The specific operation is generating and providing the report.

[0958] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0959] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0960] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0961] [Third embodiment]

[0962] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0963] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0964] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0965] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0966] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0967] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0968] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0969] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0970] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0971] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0972] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0973] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0974] This invention is a system for quickly and efficiently obtaining insights from multiple perspectives during market research and product development. This system operates in cooperation with three parties: a server, a terminal, and a user.

[0975] System Overview

[0976] The core of the system is the server. The server has a unit that uses a generative model to generate virtual characters with various attributes, and adjusts the content of the questionnaire based on the generated characters. The server also collects questionnaire responses submitted by users and analyzes the data. Based on the analysis results, it generates a report and provides it to the user.

[0977] The terminal is a device used by a user to access the system and answer the questionnaire. The user answers the questionnaire provided by the server based on a request and sends the results to the server.

[0978] Program processing

[0979] 1. System startup and initial settings

[0980] The server starts the system and loads the necessary databases and generative models, so the system is ready to operate normally.

[0981] 2. Receiving User Requests

[0982] A user logs into the system using a terminal and inputs a request for character generation related to product development, for example, "generation of a virtual character related to a robot toy for children aged 5 to 10."

[0983] The terminal sends this request to the server.

[0984] 3. Character Generation

[0985] The server analyzes the user's request and sends instructions to the generative model, which then generates a virtual character based on the specified attributes.

[0986] The generative model generates multiple virtual characters based on the request (e.g., an 8-year-old boy who loves sports, a 7-year-old girl who loves reading, etc.) and returns that information to the server.

[0987] 4. Survey generation and adjustment

[0988] The server receives the generated character information and adjusts the questionnaire content based on the character's attributes, constructing specific questions that match each character's interests and preferences.

[0989] The server sends the tailored questionnaire to the terminal for distribution to the user.

[0990] 5. Conducting a survey

[0991] The user uses a terminal to check the questionnaire provided by the server and enters answers from the character's perspective, such as "What kind of robot features are most appealing?"

[0992] The terminal transmits the user's answer to the server.

[0993] 6. Data Collection and Analysis

[0994] The server stores the received response data in a database, and analyzes the stored data to gain multifaceted insights related to the user request.

[0995] The server generates a detailed report based on the insights gained.

[0996] 7. Report generation and provision

[0997] The server generates a report based on the analysis results and provides it to the user, which includes specific recommendations for product development and useful insights based on market needs.

[0998] Specific examples

[0999] For example, if the product development department of a toy manufacturer is planning to develop a "robot toy for children aged 5 to 10," they can use this system as follows:

[1000] 1. A user (a toy manufacturer representative) logs into the system and inputs a request to generate a virtual character.

[1001] 2. The server generates a virtual character with the specified attributes (child aged 5 to 10) based on the generative model.

[1002] 3. The server tailors the survey based on the character and distributes it to the user.

[1003] 4. The user answers the questionnaire and sends the answers to the server.

[1004] 5. The server collects and analyzes the responses to gain multifaceted insights.

[1005] 6. The server generates a report based on the analysis results and provides it to the user.

[1006] This process allows toy manufacturers to efficiently develop products based on market needs and consumer preferences.

[1007] The processing flow will be explained below.

[1008] Step 1:

[1009] The server starts the system and loads the necessary databases and generative models, so the system is ready to operate normally.

[1010] Step 2:

[1011] A user logs in to the system using a terminal. After logging in, the user inputs a request for the generation of a virtual character related to product development. For example, the user requests "generation of a virtual character related to a robot toy for children aged 5 to 10."

[1012] Step 3:

[1013] The device sends this request to the server, which includes the desired character attributes (e.g., age, interests, etc.).

[1014] Step 4:

[1015] The server analyzes the user's request and sends instructions to the generative model, which then generates a virtual character based on the specified attributes.

[1016] Step 5:

[1017] The generative model generates multiple virtual characters based on the request and returns that information to the server, such as an 8-year-old boy who loves sports or a 7-year-old girl who loves reading.

[1018] Step 6:

[1019] The server receives the generated character information and adjusts the questionnaire content based on the character's attributes, constructing specific questions that match each character's interests and preferences.

[1020] Step 7:

[1021] The server sends the tailored questionnaire to the terminal for distribution to the user, the questionnaire including specific questions appropriate for the character.

[1022] Step 8:

[1023] The user uses a terminal to check the questionnaire provided by the server and enters answers from the character's perspective, such as "What kind of robot features are most appealing?"

[1024] Step 9:

[1025] The terminal transmits the user's answers to the server, where the answers are instantly transmitted and recorded.

[1026] Step 10:

[1027] The server stores the received response data in a database, and analyzes the stored data to gain multifaceted insights related to the user request.

[1028] Step 11:

[1029] The server generates a detailed report based on the insights gained, including specific recommendations for product development and useful insights based on market needs.

[1030] Step 12:

[1031] The server generates a report based on the analysis results and provides it to the user, who then uses it as a reference for product development and marketing activities.

[1032] Example 1

[1033] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1034] A lack of methods for quickly and efficiently obtaining insights from diverse perspectives is a challenge in market research and product development. Traditional methods require time-consuming and laborious processes for collecting and analyzing user feedback, making it difficult to obtain accurate market insights. Furthermore, research methods using virtual characters are inadequate, making it difficult to obtain survey results that reflect the diverse needs of users.

[1035] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1036] In this invention, the server includes means for generating virtual characters with various attributes using a generative model, means for adjusting the content of a questionnaire based on the virtual character, means for presenting the adjusted questionnaire to users and collecting responses from them, means for analyzing the collected responses and obtaining multifaceted insights, means for generating a report of the analysis results and providing it to the user, means for loading the necessary database and generative model at system startup and configuring the system for normal operation, means for analyzing the content of user requests before sending instructions to the generative model, and means for saving the responses in a database for collecting them and performing data analysis. This makes it possible to efficiently and accurately obtain market insights from various perspectives.

[1037] A "generative model" is an algorithm that uses machine learning and artificial intelligence techniques to generate data or information based on specific attributes or conditions.

[1038] A "virtual character" refers to a fictional person or entity with specific attributes and conditions created using a generative model.

[1039] "Means for adjusting the content of the survey" refers to a process for changing or optimizing the content of the survey questions based on the attributes of the generated virtual character.

[1040] "Means for collecting responses from users" refers to the process and tools for storing the information users provide in response to the questionnaire in a database or the like.

[1041] "Methods of analyzing responses and gaining multifaceted insights" refers to the process of analyzing collected response data using statistical analysis and machine learning algorithms to extract useful insights from various perspectives.

[1042] "Means for generating a report and providing it to the user" refers to the process of organizing the analysis results, creating a report in the form of a document or graph, etc., and providing it to the user.

[1043] A "database" refers to a system that can efficiently manage, store, and search large amounts of data.

[1044] "Means for configuring the system to operate normally" refers to the process of initializing various data and parameters required when starting the system, and putting the system into a state where it can operate without any problems.

[1045] "Means for analyzing the content of a user's request" refers to a process for analyzing the content of a request entered by a user and determining the necessary processing based on that content.

[1046] This invention is a system in which a server, a terminal, and a user work together. Specifically, it is configured to efficiently obtain insights from various perspectives in market research and product development. The hardware of this system consists of a server and a terminal used by the user. Below, we will explain the details of each component and the program processing method.

[1047] System Components

[1048] 1. Server: This is the central part of the entire system, generating virtual characters using generative models, adjusting survey content, collecting user responses, and analyzing data to gain insights. It uses machine learning frameworks such as TensorFlow and PyTorch, as well as databases such as MongoDB and MySQL.

[1049] 2. Terminal: The device used by the user to access the system and respond to the survey. This includes a variety of devices, such as PCs and smartphones.

[1050] 3. User: Responsible for submitting requests for market research and product development through the system, answering questionnaires and providing data.

[1051] Program processing

[1052] System startup and initial setup

[1053] The server starts the system and loads the necessary databases and generative models, including TensorFlow, PyTorch, MongoDB, and MySQL, to prepare the system for normal operation.

[1054] Receiving user requests

[1055] A user logs into the system using a terminal and submits a request related to product development, for example, "creation of a virtual character for a robot toy for children aged 5 to 10."

[1056] The terminal sends this request to the server, which sends it as an HTTP request.

[1057] Character Generation

[1058] The server analyzes the user's request and sends instructions to a generative model, which is a large-scale language model such as GPT-3 or BERT.

[1059] The generative model generates virtual characters based on the given attributes and returns the character information to the server. For example, it generates an "8-year-old boy who loves sports" and a "7-year-old girl who loves reading."

[1060] Survey generation and coordination

[1061] The server receives the generated character information and adjusts the questionnaire content based on each character's attributes. For example, if a character likes sports, it adds a question such as "Which sport do you like?"

[1062] Conducting a survey

[1063] The user uses a terminal to check the questionnaire provided by the server and enter answers from the character's perspective, such as "What kind of robot features are most appealing?"

[1064] Data collection and analysis

[1065] The server stores the received response data in a database and analyzes it using Python libraries (e.g., Pandas, Scikit-learn).

[1066] Report generation and delivery

[1067] The server generates a detailed report based on the analysis results and provides it to the user. This report is typically generated in PDF format and sent via email.

[1068] Specific examples

[1069] If the product development department of a toy manufacturer were to develop a "robot toy for children aged 5 to 10," they would use this system as follows:

[1070] 1. A user (a toy manufacturer representative) logs into the system and requests the creation of a virtual character for a robot toy for children aged 5 to 10.

[1071] 2. The server analyzes the request and sends instructions to the generative model.

[1072] 3. The server adjusts the questionnaire based on the generated character information and distributes it to the user.

[1073] 4. The user answers the questionnaire and sends the answers to the server.

[1074] 5. The server collects and analyzes the responses to gain multifaceted insights.

[1075] 6. The server generates a report based on the analysis results and provides it to the user.

[1076] Prompt Sentence Examples

[1077] "Generate a virtual character for a robotic toy for children aged 5 to 10. Create a character based on the following attributes: age, gender, interests / preferences (sports, reading, music, science, etc.)."

[1078] By inputting such a specific prompt sentence, it becomes possible to generate a detailed virtual character and conduct a survey based on that character.

[1079] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1080] Step 1: System startup and initial setup

[1081] The server starts the system and loads the necessary database (e.g., MongoDB or MySQL) and generative model (e.g., GPT-3 or BERT using TensorFlow or PyTorch). Specifically, it loads the database connection information and loads the generative model parameters into memory. This prepares the system for normal operation. The input is the server configuration file and database connection information, and the output is an initialized database connection and the completion of loading the generative model.

[1082] Step 2: Receiving a user request

[1083] A user logs into the system using a terminal and enters a specific request (e.g., "generate a virtual character for a robotic toy for children aged 5 to 10").

[1084] The terminal sends this request to the server as an HTTP request. The input is the request data entered by the user into the terminal (e.g., parameters such as age, interests, etc.), and the output is the request data sent to the server.

[1085] Step 3: Character Generation

[1086] The server analyzes the received user request and sends instructions to the generative model (e.g., GPT-3). API calls are made using Python's requests or flask library. The specific input is the content of the user request, and the output is the generated character information returned by the generative model. For example, data such as an 8-year-old boy who loves sports or a 7-year-old girl who loves reading is generated.

[1087] Step 4: Generate and adjust the survey

[1088] The server receives the character information returned from the generative model and generates a questionnaire based on each character's attributes. It uses a template engine (e.g., Jinja2) to dynamically generate the questionnaire questions. The input is the generated character information, and the output is a tailored questionnaire based on each character's attributes.

[1089] Step 5: Present the survey

[1090] The server sends the adjusted survey to the terminal to distribute it to the user. Specifically, it generates a survey page in HTML format for the terminal's browser and sends it to the terminal. The input is the adjusted survey data, and the output is the survey form displayed on the terminal.

[1091] Step 6: Conduct a survey

[1092] The user answers a questionnaire using the terminal. For example, they answer questions such as "What kind of robot features are attractive?" The input is the response data that the user enters into the terminal, and the output is the response data that the terminal sends to the server.

[1093] Step 7: Data collection and storage

[1094] The server saves the user's answer data in a database. For example, it saves the data in JSON format in MongoDB. The input is the user's answer data, and the output is the answer data stored in the database.

[1095] Step 8: Data analysis

[1096] The server analyzes the response data stored in the database. It uses Python's Pandas and Scikit-learn to reprocess the data and perform statistical and clustering analysis. The input is the response data stored in the database, and the output is the analyzed insight data. It also includes visualizing the results using visualization tools (e.g., Matplotlib and Seaborn).

[1097] Step 9: Generate and serve reports

[1098] The server generates a detailed report based on the analysis results. The report is generated in PDF format and documented using Python's reportlab library. Finally, to provide this report to the user via email, an email module such as smtplib is used. The input is the analyzed insight data, and the output is the generated PDF report and the report sent to the user.

[1099] (Application example 1)

[1100] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1101] In conventional market research and product development, it has been difficult to quickly and efficiently obtain insights from a variety of perspectives. Furthermore, creating advertising strategies tailored to consumer tastes and preferences can be time-consuming and costly. A system that is both efficient and effective is needed to solve these problems.

[1102] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1103] In this invention, the server includes means for generating virtual characters with various attributes using a generative model, means for adjusting a questionnaire or advertising plan based on the virtual character, and means for presenting the adjusted questionnaire or advertising plan to a user and collecting responses and feedback from the user, thereby enabling consumer insights from various perspectives to be obtained quickly and efficiently.

[1104] - "Generative Model" means an artificial intelligence program used to generate the attributes of a virtual character.

[1105] A "virtual character" refers to a virtual person or entity with various attributes, which is generated based on a user's request.

[1106] A "survey" is a survey tool that includes questions for the user, the content of which is tailored based on the attributes of the virtual character.

[1107] "Advertising Plan" means the design of an advertising strategy targeted to a specific target audience and tailored based on the hobbies and preferences of a virtual character.

[1108] "User" refers to an individual or company that uses the system to enter requests and provide responses and feedback.

[1109] "Feedback" refers to answers, reactions, and opinions collected from users, and is information that is useful for improving products and services.

[1110] A "database" is a storage device for storing collected response data and feedback data.

[1111] A "report" is a document summarizing the analysis results and is provided to the user.

[1112] "Insight" refers to new knowledge and understanding gained by analyzing collected data.

[1113] A "means" refers to a method or device used to achieve a particular purpose.

[1114] MODE FOR CARRYING OUT THE INVENTION

[1115] This invention is a system for quickly and efficiently obtaining diverse consumer insights for advertising strategies and market research. This system works in cooperation with three parties: a server, a terminal (such as a smartphone), and a user.

[1116] System Overview

[1117] The center of the system is the server, which has the following main functions:

[1118] 1. Generate a virtual character using a generative model:

[1119] The server uses a generative model based on the user's input request to generate a virtual character with various attributes. The generative model generates the virtual character based on the target demographic information (e.g., age, gender, hobbies, etc.) provided by the user.

[1120] 2. Tailor your advertising plan based on the character:

[1121] The server tailors advertising plans based on the attributes of the generated virtual character, for example, advertising targeted at young people may include advertising messages and visual elements that reflect the character's hobbies and preferences.

[1122] 3. Present the adjusted plan to users and gather feedback:

[1123] The adjusted advertising plan is sent to the user's device (such as a smartphone), and after the user confirms it, they enter their feedback. The server receives and saves this feedback and stores it in a database.

[1124] 4. Analyze the collected data to gain insights:

[1125] The server analyzes the collected feedback data to gain multifaceted insights, which can then be used to improve advertising strategies and make new proposals.

[1126] 5. Generate the report and provide it to the user:

[1127] Finally, a report summarizing the analysis results is generated and provided to the user, detailing the effectiveness of the ad, the target audience's reaction, and suggestions for improvement next time.

[1128] Hardware and software used

[1129] Server: A powerful computer used to host generative models and databases.

[1130] Device: A smartphone, tablet, or computer that allows users to access the system and review advertising plans and provide feedback.

[1131] Generative model: An artificial intelligence-based program used to generate virtual characters (e.g., GPT-3).

[1132] Database: Used to store collected response and feedback data (e.g. MySQL).

[1133] Specific examples

[1134] For example, if a user wants to create a "sneaker ad for young people," the process is as follows:

[1135] 1. Users: Enter details about your target demographic into the app, such as "Young people aged 18-25 who enjoy sports."

[1136] 2. Server: Using the generative model, generate a virtual character (e.g., a 20-year-old college student) based on specified attributes.

[1137] 3. Server: Tailor the messaging and visual elements of sneaker ads based on the attributes of the virtual character.

[1138] 4. Device: Present the adjusted advertising plan to the user's smartphone and collect feedback from the user.

[1139] 5. Server: Analyzes the collected feedback data, gains multifaceted insights, and generates reports.

[1140] 6. Server: Provides the final report to the user.

[1141] Example prompt: "Generate a fictional character for a sneaker advertisement aimed at young people aged 18-25."

[1142] In this way, the system allows users to quickly design and optimize advertising strategies tailored to their target audience.

[1143] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1144] Step 1:

[1145] System startup and initial setup

[1146] The server starts the system and loads the necessary generative model (e.g., GPT-3) and database (e.g., MySQL) on a high-performance computer.

[1147] This process prepares the system for proper operation.

[1148] Input: The generated model and database load commands.

[1149] Output: The model and database are loaded into memory and the system is initialized.

[1150] Step 2:

[1151] Receiving user requests

[1152] A user logs in to the system using a terminal (such as a smartphone).

[1153] Enter target demographic details for your advertising plan (e.g., "Young people aged 18-25 who enjoy sports").

[1154] The terminal sends this request to the server.

[1155] Input: User's request for advertising plan.

[1156] Output: The user request is sent to the server.

[1157] Step 3:

[1158] Character Generation

[1159] The server analyzes the received request and sends instructions to the generative model (e.g., GPT-3).

[1160] The AI ​​model generates a virtual character based on specified attributes.

[1161] For example, a character such as "a 20-year-old college student whose hobby is sports" can be generated.

[1162] Input: Attribute information of the user request.

[1163] Output: Data of the generated virtual character.

[1164] Step 4:

[1165] Creating and adjusting advertising plans

[1166] The server uses the data of the generated virtual character to adjust the advertising plan.

[1167] Advertising messages and visual elements are customized based on each character's hobbies and preferences.

[1168] For example, advertisements aimed at young people who love sports may include visuals of sports equipment and related activities.

[1169] Input: Data of the generated virtual character.

[1170] Output: A tailored advertising plan.

[1171] Step 5:

[1172] Presenting advertising plans and collecting feedback

[1173] The server transmits the adjusted advertising plan to the terminal and presents it to the user.

[1174] The user reviews the advertising plan and enters feedback.

[1175] The terminal sends this feedback to the server.

[1176] Input: Your adjusted advertising plan.

[1177] Output: User feedback data.

[1178] Step 6:

[1179] Data collection and analysis

[1180] The server stores the feedback data in a database and analyzes it.

[1181] In the analysis process, feedback data is statistically analyzed to gain diverse perspectives.

[1182] For example, by aggregating multiple feedback data, the effectiveness of advertising and factors of interest can be identified.

[1183] Input: User feedback data.

[1184] Output: Analysis result data.

[1185] Step 7:

[1186] Report generation and delivery

[1187] The server generates a detailed report based on the analysis results.

[1188] This report includes information such as the effectiveness of the ad, the reaction of the target audience, and areas for improvement next time.

[1189] The generated report is sent to the user's terminal and provided to the user.

[1190] Input: Analysis result data.

[1191] Output: A detailed report provided to the user.

[1192] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1193] This invention is a system that combines a virtual character generation function with an emotion engine that recognizes user emotions to quickly and efficiently obtain multifaceted, emotion-based insights in market research and product development. This system operates in cooperation with four parties: a server, a terminal, an emotion engine, and a user.

[1194] System Overview

[1195] The core of the system is the server. The server has a unit that uses a generative model to generate virtual characters with diverse attributes and adjusts the content of the questionnaire based on the generated characters. The server also collects questionnaire responses submitted by users and analyzes the data. Based on the analysis results, it generates a report and provides it to the user. The system also includes an emotion engine that recognizes the user's emotions in real time and dynamically adjusts the content of the questionnaire.

[1196] The terminal is a device used by users to access the system and answer questionnaires. Based on a user's request, the user answers the questionnaire provided by the server and sends the results to the server. The emotion engine recognizes emotions from the user's facial expressions, tone of voice, etc., and sends that information to the server.

[1197] Program processing

[1198] 1. System startup and initial settings

[1199] The server starts the system and loads the necessary databases, generative models, and emotion engines, so the system is ready to operate normally.

[1200] 2. Receiving User Requests

[1201] A user logs in to the system using a terminal and inputs a request for the generation of a virtual character related to product development, for example, a request for "generation of a virtual character related to a robot toy for children aged 5 to 10."

[1202] The terminal sends this request to the server.

[1203] 3. Character Generation

[1204] The server analyzes the user's request and sends instructions to the generative model, which then generates a virtual character based on the specified attributes.

[1205] The generative model generates multiple virtual characters based on the request and returns that information to the server, such as an 8-year-old boy who loves sports or a 7-year-old girl who loves reading.

[1206] 4. Survey generation and adjustment

[1207] The server receives the generated character information and adjusts the questionnaire content based on the character's attributes, constructing specific questions that match each character's interests and preferences.

[1208] 5. Emotion recognition

[1209] The emotion engine recognizes the user's emotions in real time, analyzing facial expressions and tone of voice while the user is answering the questionnaire, and generates emotion data.

[1210] The emotion engine sends the recognized emotion data to the server.

[1211] 6. Dynamically adjusting surveys

[1212] The server dynamically adjusts the content of the questionnaire based on the emotion data sent from the emotion engine, for example, by determining whether the user is interested in the questions and changing the questions accordingly.

[1213] 7. Conducting a survey

[1214] The user uses a terminal to check the questionnaire provided by the server and enters answers from the character's perspective, such as "What kind of robot features are most appealing?"

[1215] The terminal transmits the user's answer to the server.

[1216] 8. Data Collection and Analysis

[1217] The server stores the received response data in a database, and analyzes the stored data to gain multifaceted insights related to the user request.

[1218] The server generates a detailed report based on the insights gained.

[1219] 9. Report generation and provision

[1220] The server generates a report based on the analysis results and provides it to the user, which includes specific recommendations for product development and useful insights based on market needs.

[1221] Specific examples

[1222] For example, if the product development department of a toy manufacturer is planning to develop a "robot toy for children aged 5 to 10," they can use this system as follows:

[1223] 1. A user (a toy manufacturer representative) logs into the system and inputs a request to generate a virtual character.

[1224] 2. The server generates a virtual character with the specified attributes (child aged 5 to 10) based on the generative model.

[1225] 3. The server tailors the survey based on the character and distributes it to the user.

[1226] 4. While the user answers the questionnaire and sends the answers to the server, the emotion engine recognizes the user's emotions and sends the data to the server in real time.

[1227] 5. The server dynamically adjusts the questionnaire content based on the emotional data and collects the user's responses.

[1228] 6. The server collects and analyzes the responses to gain multifaceted, emotional insights.

[1229] 7. The server generates a report based on the analysis results and provides it to the user.

[1230] This process allows toy manufacturers to efficiently develop products that take into account market needs, consumer preferences, and even emotional responses.

[1231] The processing flow will be explained below.

[1232] Step 1:

[1233] The server starts the system and loads the necessary databases, generative models, and emotion engines, so the system is ready to operate normally.

[1234] Step 2:

[1235] A user logs in to the system using a terminal and inputs a request for the generation of a virtual character related to product development, for example, a request for "generation of a virtual character related to a robot toy for children aged 5 to 10."

[1236] Step 3:

[1237] The device sends this request to the server, which includes the desired character attributes (e.g., age, interests, etc.).

[1238] Step 4:

[1239] The server analyzes the user's request and sends instructions to the generative model, which then generates a virtual character based on the specified attributes.

[1240] Step 5:

[1241] The generative model generates multiple virtual characters based on the request and returns that information to the server, such as an 8-year-old boy who loves sports or a 7-year-old girl who loves reading.

[1242] Step 6:

[1243] The server receives the generated character information and adjusts the questionnaire content based on the character's attributes, constructing specific questions that match each character's interests and preferences.

[1244] Step 7:

[1245] The server sends the tailored questionnaire to the terminal for distribution to the user, the questionnaire including specific questions appropriate for the character.

[1246] Step 8:

[1247] The emotion engine recognizes the user's emotions in real time while they are answering the questionnaire, for example, by using facial expression analysis and voice tone analysis to generate emotion data.

[1248] Step 9:

[1249] The emotion engine transmits the recognized emotion data to the server, where the emotion data includes the user's current emotional state.

[1250] Step 10:

[1251] The server dynamically adjusts the survey content based on the emotion data sent by the emotion engine, for example adding relevant follow-up questions if the user expresses interest in a question.

[1252] Step 11:

[1253] The user continues to answer questionnaires provided by the server using the terminal, and the answers entered by the user are transmitted from the terminal to the server in real time.

[1254] Step 12:

[1255] The server stores the received response data in a database, and analyzes the stored data to gain multifaceted insights related to the user request.

[1256] Step 13:

[1257] The server generates a detailed report based on the insights gained, including specific recommendations for product development and useful insights based on market needs.

[1258] Step 14:

[1259] The server generates a report based on the analysis results and provides it to the user, who then uses it as a reference for product development and marketing activities.

[1260] Specific examples

[1261] For example, if the product development department of a toy manufacturer is planning to develop a "robot toy for children aged 5 to 10," the specific process would be as follows:

[1262] Step 1:

[1263] A user (a toy manufacturer's representative) logs into the system and inputs a request for virtual character generation.

[1264] Step 2:

[1265] The server uses generative models to generate virtual characters for children between the ages of 5 and 10, such as an 8-year-old boy who loves sports or a 7-year-old girl who loves reading.

[1266] Step 3:

[1267] The server then tailors a questionnaire based on the generated character and distributes it to the user. The questionnaire includes questions such as, "What kind of robot features do you find most appealing?"

[1268] Step 4:

[1269] The user answers a questionnaire, while the emotion engine analyzes the user's facial expressions and tone of voice and transmits the emotion data to the server in real time.

[1270] Step 5:

[1271] The server dynamically adjusts the questionnaire content based on the emotion data and collects user responses.

[1272] Step 6:

[1273] The server stores the collected survey responses in a database and analyzes them to gain multifaceted, emotion-based insights.

[1274] Step 7:

[1275] The server generates a report based on the analysis results and provides it to the user, which includes specific recommendations for product development.

[1276] This process allows toy manufacturers to quickly grasp market needs and consumer preferences, and efficiently develop products that also take user emotions into consideration.

[1277] Example 2

[1278] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1279] Traditional market research and product development methods collect data without considering user emotions, resulting in limited insights and a poorly personalized user experience. Furthermore, the survey content is static, making it impossible to dynamically adjust based on user interests. This reduces the accuracy and usefulness of the collected data.

[1280] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1281] In this invention, the server includes means for generating virtual characters with diverse attributes using a generative model, means for adjusting the content of a questionnaire based on the virtual character, means for presenting the adjusted questionnaire to a user and collecting responses from the user, means for recognizing the user's emotions in real time using an emotion recognition engine and dynamically adjusting the content of the questionnaire, means for analyzing the collected responses to gain multifaceted insights, and means for generating a report of the analysis results. This enables the implementation of a questionnaire that reflects the user's emotions, improves the accuracy and usefulness of the collected data, and provides a more personalized user experience.

[1282] A "generative model" is an algorithm for generating virtual characters with diverse attributes based on user requests.

[1283] A "virtual character" is a character with specific attributes created by a generative model, and is used to adjust the content of the questionnaire.

[1284] The "survey content adjustment means" is a process that dynamically changes and adapts the content of the survey questions based on the attributes of the generated virtual character.

[1285] A "tailored questionnaire" is a questionnaire that has been modified and optimized based on the attributes of the virtual character and the user's emotional recognition.

[1286] The "means for collecting responses from users" is a mechanism by which the server receives responses entered by users to the questionnaire and stores them in a database.

[1287] An "emotion recognition engine" is software or hardware that analyzes a user's facial expressions and tone of voice in real time to identify their emotional state.

[1288] "Dynamic adjustment method based on emotion recognition" is a process of adjusting and changing the content of a questionnaire in real time based on information obtained from an emotion recognition engine.

[1289] "Data analysis methods" refers to the process of analyzing collected survey response data using statistical and machine learning techniques to derive multifaceted insights.

[1290] The "report generation means" is a process of creating a report containing useful insights and recommendations for the user based on the analysis results obtained by the data analysis means.

[1291] This invention is a system that uses a generative AI model to generate virtual characters with diverse attributes and dynamically adjusts the content of a survey based on those characters. Furthermore, it combines an emotion recognition engine to recognize users' emotions in real time and dynamically adjust the survey content based on that. This allows for more accurate data collection and insights that reflect users' emotions.

[1292] Hardware and software used

[1293] The system includes the following main components:

[1294] Server: Runs the generative model (e.g., OpenAI's GPT-3) and emotion recognition engine (e.g., Microsoft Azure Emotion API).

[1295] Device: The device through which the user accesses the system and completes the survey, such as a PC, tablet, or smartphone.

[1296] Camera and microphone: Devices used to analyze your facial expressions and tone of voice in real time.

[1297] System operation and concrete examples

[1298] First, the server starts the system and loads the necessary database, generative model, and emotion recognition engine, so the system is ready to operate normally.

[1299] Next, the user logs in to the system using a terminal. A user ID and password are required for login, which are used to verify authorization. The user then inputs a request for the generation of a virtual character related to product development. For example, the user requests "generation of a virtual character related to a robot toy for children aged 5 to 10." The terminal then sends this request to the server.

[1300] The server analyzes the user's request and sends instructions to the generative model, which then generates a virtual character based on the specified attributes. For example, an 8-year-old boy who loves sports or a 7-year-old girl who loves reading might be generated.

[1301] The server then receives the generated character information and adjusts the questionnaire content based on the character's attributes. For example, if a boy likes sports, it might add a question like "What is your favorite sport?", and if a girl likes reading, it might add a question like "What is your favorite genre of book?".

[1302] While the user is answering the survey, an emotion recognition engine analyzes the user's facial expressions and tone of voice to recognize the user's emotions in real time. The recognized emotion data is sent to the server, which then dynamically adjusts the survey content based on that data. For example, if the server determines that the user is interested in a question, it will introduce additional detailed questions.

[1303] Users use their devices to answer the questionnaire, which then transmits the answers to the server, which stores the received data in a database and analyzes it. Based on the analysis results, a report containing useful insights for product development is generated and provided to the user.

[1304] Specific prompt examples

[1305] "Generate a virtual character for children aged 5 to 10, conduct a survey based on the character's attributes, and adjust the survey based on real-time user emotions."

[1306] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1307] Step 1:

[1308] The server starts the system and loads the necessary databases, generative models, and emotion recognition engines.

[1309] Input: System startup command

[1310] Output: Load complete status

[1311] What happens: The server establishes a database connection and loads the generative AI model and emotion recognition software into memory. For example, it connects to an SQL database and initializes the generative AI model (e.g., GPT-3).

[1312] Step 2:

[1313] A user logs in to the system using a terminal. A user ID and password are required to log in, and authorization is confirmed using these.

[1314] Input: User ID, Password

[1315] Output: Login successful message

[1316] Specific operation: The terminal sends the entered user ID and password to the server, which verifies them and, if successful, starts the session.

[1317] Step 3:

[1318] The user inputs a request for the generation of a virtual character related to product development. For example, the user requests "generation of a virtual character related to a robot toy for children aged 5 to 10." The terminal then sends this request to the server.

[1319] Input: Character creation request

[1320] Output: Request receipt confirmation message

[1321] Specific operation: The terminal sends the request content as a prompt to the server, and the server adds it to the queue.

[1322] Step 4:

[1323] The server analyzes the user's request and sends instructions to the generative model, which then generates a virtual character based on the specified attributes.

[1324] Input: Character creation request

[1325] Output: Generated character information

[1326] Specific operation: The server analyzes the request content and sends appropriate prompts to the generative AI model (e.g., GPT-3), which returns multiple character information.

[1327] Step 5:

[1328] The server receives the generated character information and adjusts the content of the questionnaire based on the character's attributes.

[1329] Input: Generated character information

[1330] Output: Adjusted survey

[1331] Specific operation: The server dynamically generates questions based on the character's interests and preferences. For example, for a character who likes sports, the server adds the question "What is your favorite sport?"

[1332] Step 6:

[1333] The emotion recognition engine analyzes the user's facial expressions and tone of voice while they are answering the questionnaire, and recognizes their emotions in real time.

[1334] Input: User's facial expression data, voice data

[1335] Output: Emotion recognition data

[1336] How it works: Data is collected through the camera and microphone connected to the device, and an emotion recognition engine (e.g., Microsoft Azure Emotion API) analyzes it in real time.

[1337] Step 7:

[1338] The server dynamically adjusts the content of the questionnaire based on the emotion recognition data.

[1339] Input: Emotion recognition data

[1340] Output: Dynamically adjusted survey

[1341] Specific operation: The server uses emotion recognition data to change the content of survey questions according to the user's interests and stress level. For example, it changes questions that the user may find difficult to understand into simpler phrases.

[1342] Step 8:

[1343] The user uses the terminal to answer the questionnaire provided by the server.

[1344] Input: Survey Question

[1345] Output: User's answer

[1346] Specific operation: The user fills out a questionnaire and sends the answers to the server. The device then sends the answer data to the server.

[1347] Step 9:

[1348] The server stores the received response data in a database and analyzes the data.

[1349] Input: Answer data

[1350] Output: Analysis results

[1351] Specific operation: The server stores the response data and emotion recognition data in a database and analyzes them using statistical methods and machine learning algorithms.

[1352] Step 10:

[1353] The server generates a detailed report based on the analysis results.

[1354] Input: Analysis results

[1355] Output: Generated report

[1356] Specific operation: The server creates a report containing useful insights based on the analysis results and provides it to the user. For example, a report may be generated that states, "The most popular feature among 8-year-old boys who like sports is the exercise tracker function."

[1357] (Application example 2)

[1358] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1359] Modern advertising delivery systems lack the technology to dynamically adjust advertisements based on user emotions in real time. This results in a lack of timely advertisements that match user interests and preferences, resulting in reduced advertising effectiveness. Furthermore, there is a need for an efficient method to accurately recognize user emotions and instantly adjust advertisement content based on those emotions.

[1360] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1361] In this invention, the server includes means for generating a virtual character with various attributes using a generative model, means for adjusting the content of a questionnaire based on the virtual character, means for presenting the adjusted questionnaire to a user and collecting responses from the user, means for analyzing the collected responses and obtaining multifaceted insights, means for generating a report of the analysis results and providing it to the user, means for recognizing the user's emotions and dynamically adjusting the content of the questionnaire based on the data, means for collecting user emotion data using a sensor attached to the smart device, and means for adjusting and delivering advertisement content based on the emotion data in real time, thereby enabling effective advertisement delivery that responds to the user's emotional state.

[1362] A "generative model" is an algorithm or artificial intelligence mechanism for generating virtual characters.

[1363] A "virtual character" is a character that is generated using digital technology and has a variety of attributes.

[1364] "Means for adjusting the content of the survey" refers to technology or mechanisms for optimizing survey questions based on the attributes of the virtual character.

[1365] "Means for collecting responses from users" refers to the technology and equipment used to collect data from users responding to the questionnaire.

[1366] "Means of gaining multifaceted insights" are methods for analyzing collected data and deriving insights from multiple perspectives.

[1367] "Means for generating a report and providing it to the user" refers to the process or technology for compiling the analysis results in a report format and providing it to the user.

[1368] "Means for recognizing user emotions" refers to technology that infers emotions from the user's facial expressions, tone of voice, etc.

[1369] "Dynamic adjustment means" refers to methods and technologies that change content in real time depending on the state of the data.

[1370] "Smart device" refers to a portable electronic device that can connect to the Internet, including, for example, a smartphone or smart glasses.

[1371] A "sensor" is a device used to collect a user's facial expressions, tone of voice, and other physiological data.

[1372] "Emotion data" is data that indicates the emotional state of the user, and includes, for example, facial expression data and tone of voice data.

[1373] "Means for adjusting and delivering advertising content" refers to a mechanism that changes the content of advertisements based on collected emotional data and displays them to users.

[1374] This invention provides a system that recognizes the user's emotions in real time as they view advertisements using a smart device, and dynamically adjusts and delivers advertisement content. A specific embodiment of this system will be described below.

[1375] System Overview

[1376] The system mainly consists of four components: a server, a terminal, an emotion recognition engine, and a user.

[1377] 1. Server:

[1378] The server is the center of the system, running the generative model and emotion recognition engine. It uses the generative model to generate a virtual character and adjusts the content of the survey based on that character. It also analyzes the response data and emotion data sent by users and adjusts the content of advertisements in real time.

[1379] 2. Terminal:

[1380] The device is the device that the user actually operates, such as smart glasses or a smartphone. The device is equipped with a camera and microphone, which are used to transmit the user's facial expressions and voice to the emotion recognition engine.

[1381] 3. Emotion Recognition Engine:

[1382] The emotion recognition engine analyzes emotions from the user's facial expressions and tone of voice in real time. This engine is built using machine learning frameworks such as TensorFlow. The analyzed emotion data is sent to a server.

[1383] 4. User:

[1384] The user operates the device and is responsible for viewing the advertisements. The user's emotions are recognized in real time, and the advertisements are dynamically adjusted based on that data.

[1385] Data Generation and Processing

[1386] The server uses a generative model to generate a virtual character. The model sets the character's attributes based on a prompt entered by the user. For example, based on a prompt such as "Generate an advertisement for the latest fashion items enjoyed by women in their 20s," the server generates a character that best suits the target user and adjusts the relevant survey.

[1387] Emotion Recognition and Ad Tailoring

[1388] The device (e.g., smart glasses) uses a camera and microphone to capture the user's facial expressions and tone of voice, and then analyzes the data with an emotion recognition engine. This engine predicts the user's emotions based on the collected data and sends the results to a server. The server then dynamically adjusts advertising content based on the received emotional data, enabling more effective ad delivery.

[1389] Specific examples

[1390] For example, imagine a user wearing smart glasses while walking through a shopping mall. When the user views an advertisement displayed on a billboard, the smart glasses' camera and microphone capture the user's facial expressions and tone of voice. This data is analyzed by an emotion recognition engine, and if the user expresses "interest" or "enjoyment," the server adjusts the content displayed on the billboard so that the next relevant product is displayed.

[1391] Hardware and software used

[1392] Hardware: smart glasses, smartphone, camera, microphone

[1393] Software: TensorFlow (machine learning framework), real-time ad server (e.g., AWS, Google Cloud)

[1394] Prompt Sentence Examples

[1395] 1. "Generate ads for the latest fashion items enjoyed by women in their 20s."

[1396] 2. "Show recommended ads based on user interests."

[1397] This allows for effective advertising delivery based on the user's real-time emotional state.

[1398] The above is a specific embodiment of the present invention.

[1399] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1400] Step 1:

[1401] System startup and initial setup

[1402] The server starts the system and loads the necessary database, generative model, and emotion recognition engine. This prepares the system for normal operation. Specifically, the server loads various models and data. The input to this step is an instruction to start the server, and the output is the completion of loading of the model and data.

[1403] Step 2:

[1404] Receiving user requests

[1405] A user logs in to the system using a terminal and inputs a request for generating a virtual character related to product development. For example, the user might input a prompt such as, "Please generate an advertisement for the latest fashion items enjoyed by women in their twenties." The terminal then sends this request to the server. The input is the user request, and the output is the request sent to the server.

[1406] Step 3:

[1407] Character Generation

[1408] The server analyzes the user's request and sends instructions to the generative model. The generative model generates a virtual character based on the specified attributes. The input is the user request, and the output is information about the generated virtual character. The specific operation is to input a prompt to the generative model and generate a character.

[1409] Step 4:

[1410] Survey generation and coordination

[1411] The server receives the generated character information and adjusts the survey content based on the character's attributes. It constructs specific questions that match each character's interests and preferences. The input is virtual character information, and the output is the adjusted survey content. The specific operation is the generation and optimization of survey items.

[1412] Step 5:

[1413] emotion recognition

[1414] The device uses a camera and microphone to capture the user's facial expressions and tone of voice, and sends the data to an emotion recognition engine. The emotion recognition engine recognizes the user's emotions in real time and sends the information to a server. The input is the user's facial and voice data, and the output is recognized emotion data. The specific operations are data capture and emotion recognition.

[1415] Step 6:

[1416] Dynamic survey adjustment

[1417] The server dynamically adjusts the content of the questionnaire based on the emotion data sent from the emotion recognition engine. For example, it determines whether the user is interested in the question and changes the question accordingly. The input is emotion data, and the output is a dynamically adjusted questionnaire. The specific operations are emotion data analysis and questionnaire content adjustment.

[1418] Step 7:

[1419] Conducting a survey

[1420] The user uses the terminal to check the questionnaire provided by the server and input answers from the character's perspective. For example, they answer questions such as "What features of the product are attractive?" The terminal then sends the user's answers to the server. The input is the questionnaire answers, and the output is the sending of the answers to the server. The specific operations are the input and sending of the questionnaire answers.

[1421] Step 8:

[1422] Data collection and analysis

[1423] The server stores the received response data in a database. It then analyzes the stored data to gain multifaceted insights related to the user request. The input is the survey response data, and the output is the analysis results. The specific operations are data storage and analysis.

[1424] Step 9:

[1425] Report generation and delivery

[1426] The server generates a report based on the analysis results and provides it to the user. The report contains specific recommendations that are useful for product development and useful insights based on market needs. The input is the analysis results and the output is the report. The specific operation is generating and providing the report.

[1427] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1428] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1429] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1430] [Fourth embodiment]

[1431] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1432] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1433] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1434] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1435] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1436] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1437] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1438] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1439] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1440] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1441] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1442] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1443] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1444] This invention is a system for quickly and efficiently obtaining insights from multiple perspectives during market research and product development. This system operates in cooperation with three parties: a server, a terminal, and a user.

[1445] System Overview

[1446] The core of the system is the server. The server has a unit that uses a generative model to generate virtual characters with various attributes, and adjusts the content of the questionnaire based on the generated characters. The server also collects questionnaire responses submitted by users and analyzes the data. Based on the analysis results, it generates a report and provides it to the user.

[1447] The terminal is a device used by a user to access the system and answer the questionnaire. The user answers the questionnaire provided by the server based on a request and sends the results to the server.

[1448] Program processing

[1449] 1. System startup and initial settings

[1450] The server starts the system and loads the necessary databases and generative models, so the system is ready to operate normally.

[1451] 2. Receiving User Requests

[1452] A user logs into the system using a terminal and inputs a request for character generation related to product development, for example, "generation of a virtual character related to a robot toy for children aged 5 to 10."

[1453] The terminal sends this request to the server.

[1454] 3. Character Generation

[1455] The server analyzes the user's request and sends instructions to the generative model, which then generates a virtual character based on the specified attributes.

[1456] The generative model generates multiple virtual characters based on the request (e.g., an 8-year-old boy who loves sports, a 7-year-old girl who loves reading, etc.) and returns that information to the server.

[1457] 4. Survey generation and adjustment

[1458] The server receives the generated character information and adjusts the questionnaire content based on the character's attributes, constructing specific questions that match each character's interests and preferences.

[1459] The server sends the tailored questionnaire to the terminal for distribution to the user.

[1460] 5. Conducting a survey

[1461] The user uses a terminal to check the questionnaire provided by the server and enters answers from the character's perspective, such as "What kind of robot features are most appealing?"

[1462] The terminal transmits the user's answer to the server.

[1463] 6. Data Collection and Analysis

[1464] The server stores the received response data in a database, and analyzes the stored data to gain multifaceted insights related to the user request.

[1465] The server generates a detailed report based on the insights gained.

[1466] 7. Report generation and provision

[1467] The server generates a report based on the analysis results and provides it to the user, which includes specific recommendations for product development and useful insights based on market needs.

[1468] Specific examples

[1469] For example, if the product development department of a toy manufacturer is planning to develop a "robot toy for children aged 5 to 10," they can use this system as follows:

[1470] 1. A user (a toy manufacturer representative) logs into the system and inputs a request to generate a virtual character.

[1471] 2. The server generates a virtual character with the specified attributes (child aged 5 to 10) based on the generative model.

[1472] 3. The server tailors the survey based on the character and distributes it to the user.

[1473] 4. The user answers the questionnaire and sends the answers to the server.

[1474] 5. The server collects and analyzes the responses to gain multifaceted insights.

[1475] 6. The server generates a report based on the analysis results and provides it to the user.

[1476] This process allows toy manufacturers to efficiently develop products based on market needs and consumer preferences.

[1477] The processing flow will be explained below.

[1478] Step 1:

[1479] The server starts the system and loads the necessary databases and generative models, so the system is ready to operate normally.

[1480] Step 2:

[1481] A user logs in to the system using a terminal. After logging in, the user inputs a request for the generation of a virtual character related to product development. For example, the user requests "generation of a virtual character related to a robot toy for children aged 5 to 10."

[1482] Step 3:

[1483] The device sends this request to the server, which includes the desired character attributes (e.g., age, interests, etc.).

[1484] Step 4:

[1485] The server analyzes the user's request and sends instructions to the generative model, which then generates a virtual character based on the specified attributes.

[1486] Step 5:

[1487] The generative model generates multiple virtual characters based on the request and returns that information to the server, such as an 8-year-old boy who loves sports or a 7-year-old girl who loves reading.

[1488] Step 6:

[1489] The server receives the generated character information and adjusts the questionnaire content based on the character's attributes, constructing specific questions that match each character's interests and preferences.

[1490] Step 7:

[1491] The server sends the tailored questionnaire to the terminal for distribution to the user, the questionnaire including specific questions appropriate for the character.

[1492] Step 8:

[1493] The user uses a terminal to check the questionnaire provided by the server and enters answers from the character's perspective, such as "What kind of robot features are most appealing?"

[1494] Step 9:

[1495] The terminal transmits the user's answers to the server, where the answers are instantly transmitted and recorded.

[1496] Step 10:

[1497] The server stores the received response data in a database, and analyzes the stored data to gain multifaceted insights related to the user request.

[1498] Step 11:

[1499] The server generates a detailed report based on the insights gained, including specific recommendations for product development and useful insights based on market needs.

[1500] Step 12:

[1501] The server generates a report based on the analysis results and provides it to the user, who then uses it as a reference for product development and marketing activities.

[1502] Example 1

[1503] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1504] A lack of methods for quickly and efficiently obtaining insights from diverse perspectives is a challenge in market research and product development. Traditional methods require time-consuming and laborious processes for collecting and analyzing user feedback, making it difficult to obtain accurate market insights. Furthermore, research methods using virtual characters are inadequate, making it difficult to obtain survey results that reflect the diverse needs of users.

[1505] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1506] In this invention, the server includes means for generating virtual characters with various attributes using a generative model, means for adjusting the content of a questionnaire based on the virtual character, means for presenting the adjusted questionnaire to users and collecting responses from them, means for analyzing the collected responses and obtaining multifaceted insights, means for generating a report of the analysis results and providing it to the user, means for loading the necessary database and generative model at system startup and configuring the system for normal operation, means for analyzing the content of user requests before sending instructions to the generative model, and means for saving the responses in a database for collecting them and performing data analysis. This makes it possible to efficiently and accurately obtain market insights from various perspectives.

[1507] A "generative model" is an algorithm that uses machine learning and artificial intelligence techniques to generate data or information based on specific attributes or conditions.

[1508] A "virtual character" refers to a fictional person or entity with specific attributes and conditions created using a generative model.

[1509] "Means for adjusting the content of the survey" refers to a process for changing or optimizing the content of the survey questions based on the attributes of the generated virtual character.

[1510] "Means for collecting responses from users" refers to the process and tools for storing the information users provide in response to the questionnaire in a database or the like.

[1511] "Methods of analyzing responses and gaining multifaceted insights" refers to the process of analyzing collected response data using statistical analysis and machine learning algorithms to extract useful insights from various perspectives.

[1512] "Means for generating a report and providing it to the user" refers to the process of organizing the analysis results, creating a report in the form of a document or graph, etc., and providing it to the user.

[1513] A "database" refers to a system that can efficiently manage, store, and search large amounts of data.

[1514] "Means for configuring the system to operate normally" refers to the process of initializing various data and parameters required when starting the system, and putting the system into a state where it can operate without any problems.

[1515] "Means for analyzing the content of a user's request" refers to a process for analyzing the content of a request entered by a user and determining the necessary processing based on that content.

[1516] This invention is a system in which a server, a terminal, and a user work together. Specifically, it is configured to efficiently obtain insights from various perspectives in market research and product development. The hardware of this system consists of a server and a terminal used by the user. Below, we will explain the details of each component and the program processing method.

[1517] System Components

[1518] 1. Server: This is the central part of the entire system, generating virtual characters using generative models, adjusting survey content, collecting user responses, and analyzing data to gain insights. It uses machine learning frameworks such as TensorFlow and PyTorch, as well as databases such as MongoDB and MySQL.

[1519] 2. Terminal: The device used by the user to access the system and respond to the survey. This includes a variety of devices, such as PCs and smartphones.

[1520] 3. User: Responsible for submitting requests for market research and product development through the system, answering questionnaires and providing data.

[1521] Program processing

[1522] System startup and initial setup

[1523] The server starts the system and loads the necessary databases and generative models, including TensorFlow, PyTorch, MongoDB, and MySQL, to prepare the system for normal operation.

[1524] Receiving user requests

[1525] A user logs into the system using a terminal and submits a request related to product development, for example, "creation of a virtual character for a robot toy for children aged 5 to 10."

[1526] The terminal sends this request to the server, which sends it as an HTTP request.

[1527] Character Generation

[1528] The server analyzes the user's request and sends instructions to a generative model, which is a large-scale language model such as GPT-3 or BERT.

[1529] The generative model generates virtual characters based on the given attributes and returns the character information to the server. For example, it generates an "8-year-old boy who loves sports" and a "7-year-old girl who loves reading."

[1530] Survey generation and coordination

[1531] The server receives the generated character information and adjusts the questionnaire content based on each character's attributes. For example, if a character likes sports, it adds a question such as "Which sport do you like?"

[1532] Conducting a survey

[1533] The user uses a terminal to check the questionnaire provided by the server and enter answers from the character's perspective, such as "What kind of robot features are most appealing?"

[1534] Data collection and analysis

[1535] The server stores the received response data in a database and analyzes it using Python libraries (e.g., Pandas, Scikit-learn).

[1536] Report generation and delivery

[1537] The server generates a detailed report based on the analysis results and provides it to the user. This report is typically generated in PDF format and sent via email.

[1538] Specific examples

[1539] If the product development department of a toy manufacturer were to develop a "robot toy for children aged 5 to 10," they would use this system as follows:

[1540] 1. A user (a toy manufacturer representative) logs into the system and requests the creation of a virtual character for a robot toy for children aged 5 to 10.

[1541] 2. The server analyzes the request and sends instructions to the generative model.

[1542] 3. The server adjusts the questionnaire based on the generated character information and distributes it to the user.

[1543] 4. The user answers the questionnaire and sends the answers to the server.

[1544] 5. The server collects and analyzes the responses to gain multifaceted insights.

[1545] 6. The server generates a report based on the analysis results and provides it to the user.

[1546] Prompt Sentence Examples

[1547] "Generate a virtual character for a robotic toy for children aged 5 to 10. Create a character based on the following attributes: age, gender, interests / preferences (sports, reading, music, science, etc.)."

[1548] By inputting such a specific prompt sentence, it becomes possible to generate a detailed virtual character and conduct a survey based on that character.

[1549] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1550] Step 1: System startup and initial setup

[1551] The server starts the system and loads the necessary database (e.g., MongoDB or MySQL) and generative model (e.g., GPT-3 or BERT using TensorFlow or PyTorch). Specifically, it loads the database connection information and loads the generative model parameters into memory. This prepares the system for normal operation. The input is the server configuration file and database connection information, and the output is an initialized database connection and the completion of loading the generative model.

[1552] Step 2: Receiving a user request

[1553] A user logs into the system using a terminal and enters a specific request (e.g., "generate a virtual character for a robotic toy for children aged 5 to 10").

[1554] The terminal sends this request to the server as an HTTP request. The input is the request data entered by the user into the terminal (e.g., parameters such as age, interests, etc.), and the output is the request data sent to the server.

[1555] Step 3: Character Generation

[1556] The server analyzes the received user request and sends instructions to the generative model (e.g., GPT-3). API calls are made using Python's requests or flask library. The specific input is the content of the user request, and the output is the generated character information returned by the generative model. For example, data such as an 8-year-old boy who loves sports or a 7-year-old girl who loves reading is generated.

[1557] Step 4: Generate and adjust the survey

[1558] The server receives the character information returned from the generative model and generates a questionnaire based on each character's attributes. It uses a template engine (e.g., Jinja2) to dynamically generate the questionnaire questions. The input is the generated character information, and the output is a tailored questionnaire based on each character's attributes.

[1559] Step 5: Present the survey

[1560] The server sends the adjusted survey to the terminal to distribute it to the user. Specifically, it generates a survey page in HTML format for the terminal's browser and sends it to the terminal. The input is the adjusted survey data, and the output is the survey form displayed on the terminal.

[1561] Step 6: Conduct a survey

[1562] The user answers a questionnaire using the terminal. For example, they answer questions such as "What kind of robot features are attractive?" The input is the response data that the user enters into the terminal, and the output is the response data that the terminal sends to the server.

[1563] Step 7: Data collection and storage

[1564] The server saves the user's answer data in a database. For example, it saves the data in JSON format in MongoDB. The input is the user's answer data, and the output is the answer data stored in the database.

[1565] Step 8: Data analysis

[1566] The server analyzes the response data stored in the database. It uses Python's Pandas and Scikit-learn to reprocess the data and perform statistical and clustering analysis. The input is the response data stored in the database, and the output is the analyzed insight data. It also includes visualizing the results using visualization tools (e.g., Matplotlib and Seaborn).

[1567] Step 9: Generate and serve reports

[1568] The server generates a detailed report based on the analysis results. The report is generated in PDF format and documented using Python's reportlab library. Finally, to provide this report to the user via email, an email module such as smtplib is used. The input is the analyzed insight data, and the output is the generated PDF report and the report sent to the user.

[1569] (Application example 1)

[1570] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1571] In conventional market research and product development, it has been difficult to quickly and efficiently obtain insights from a variety of perspectives. Furthermore, creating advertising strategies tailored to consumer tastes and preferences can be time-consuming and costly. A system that is both efficient and effective is needed to solve these problems.

[1572] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1573] In this invention, the server includes means for generating virtual characters with various attributes using a generative model, means for adjusting a questionnaire or advertising plan based on the virtual character, and means for presenting the adjusted questionnaire or advertising plan to a user and collecting responses and feedback from the user, thereby enabling consumer insights from various perspectives to be obtained quickly and efficiently.

[1574] - "Generative Model" means an artificial intelligence program used to generate the attributes of a virtual character.

[1575] A "virtual character" refers to a virtual person or entity with various attributes, which is generated based on a user's request.

[1576] A "survey" is a survey tool that includes questions for the user, the content of which is tailored based on the attributes of the virtual character.

[1577] "Advertising Plan" means the design of an advertising strategy targeted to a specific target audience and tailored based on the hobbies and preferences of a virtual character.

[1578] "User" refers to an individual or company that uses the system to enter requests and provide responses and feedback.

[1579] "Feedback" refers to answers, reactions, and opinions collected from users, and is information that is useful for improving products and services.

[1580] A "database" is a storage device for storing collected response data and feedback data.

[1581] A "report" is a document summarizing the analysis results and is provided to the user.

[1582] "Insight" refers to new knowledge and understanding gained by analyzing collected data.

[1583] A "means" refers to a method or device used to achieve a particular purpose.

[1584] MODE FOR CARRYING OUT THE INVENTION

[1585] This invention is a system for quickly and efficiently obtaining diverse consumer insights for advertising strategies and market research. This system works in cooperation with three parties: a server, a terminal (such as a smartphone), and a user.

[1586] System Overview

[1587] The center of the system is the server, which has the following main functions:

[1588] 1. Generate a virtual character using a generative model:

[1589] The server uses a generative model based on the user's input request to generate a virtual character with various attributes. The generative model generates the virtual character based on the target demographic information (e.g., age, gender, hobbies, etc.) provided by the user.

[1590] 2. Tailor your advertising plan based on the character:

[1591] The server tailors advertising plans based on the attributes of the generated virtual character, for example, advertising targeted at young people may include advertising messages and visual elements that reflect the character's hobbies and preferences.

[1592] 3. Present the adjusted plan to users and gather feedback:

[1593] The adjusted advertising plan is sent to the user's device (such as a smartphone), and after the user confirms it, they enter their feedback. The server receives and saves this feedback and stores it in a database.

[1594] 4. Analyze the collected data to gain insights:

[1595] The server analyzes the collected feedback data to gain multifaceted insights, which can then be used to improve advertising strategies and make new proposals.

[1596] 5. Generate the report and provide it to the user:

[1597] Finally, a report summarizing the analysis results is generated and provided to the user, detailing the effectiveness of the ad, the target audience's reaction, and suggestions for improvement next time.

[1598] Hardware and software used

[1599] Server: A powerful computer used to host generative models and databases.

[1600] Device: A smartphone, tablet, or computer that allows users to access the system and review advertising plans and provide feedback.

[1601] Generative model: An artificial intelligence-based program used to generate virtual characters (e.g., GPT-3).

[1602] Database: Used to store collected response and feedback data (e.g. MySQL).

[1603] Specific examples

[1604] For example, if a user wants to create a "sneaker ad for young people," the process is as follows:

[1605] 1. Users: Enter details about your target demographic into the app, such as "Young people aged 18-25 who enjoy sports."

[1606] 2. Server: Using the generative model, generate a virtual character (e.g., a 20-year-old college student) based on specified attributes.

[1607] 3. Server: Tailor the messaging and visual elements of sneaker ads based on the attributes of the virtual character.

[1608] 4. Device: Present the adjusted advertising plan to the user's smartphone and collect feedback from the user.

[1609] 5. Server: Analyzes the collected feedback data, gains multifaceted insights, and generates reports.

[1610] 6. Server: Provides the final report to the user.

[1611] Example prompt: "Generate a fictional character for a sneaker advertisement aimed at young people aged 18-25."

[1612] In this way, the system allows users to quickly design and optimize advertising strategies tailored to their target audience.

[1613] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1614] Step 1:

[1615] System startup and initial setup

[1616] The server starts the system and loads the necessary generative model (e.g., GPT-3) and database (e.g., MySQL) on a high-performance computer.

[1617] This process prepares the system for proper operation.

[1618] Input: The generated model and database load commands.

[1619] Output: The model and database are loaded into memory and the system is initialized.

[1620] Step 2:

[1621] Receiving user requests

[1622] A user logs in to the system using a terminal (such as a smartphone).

[1623] Enter target demographic details for your advertising plan (e.g., "Young people aged 18-25 who enjoy sports").

[1624] The terminal sends this request to the server.

[1625] Input: User's request for advertising plan.

[1626] Output: The user request is sent to the server.

[1627] Step 3:

[1628] Character Generation

[1629] The server analyzes the received request and sends instructions to the generative model (e.g., GPT-3).

[1630] The AI ​​model generates a virtual character based on specified attributes.

[1631] For example, a character such as "a 20-year-old college student whose hobby is sports" can be generated.

[1632] Input: Attribute information of the user request.

[1633] Output: Data of the generated virtual character.

[1634] Step 4:

[1635] Creating and adjusting advertising plans

[1636] The server uses the data of the generated virtual character to adjust the advertising plan.

[1637] Advertising messages and visual elements are customized based on each character's hobbies and preferences.

[1638] For example, advertisements aimed at young people who love sports may include visuals of sports equipment and related activities.

[1639] Input: Data of the generated virtual character.

[1640] Output: A tailored advertising plan.

[1641] Step 5:

[1642] Presenting advertising plans and collecting feedback

[1643] The server transmits the adjusted advertising plan to the terminal and presents it to the user.

[1644] The user reviews the advertising plan and enters feedback.

[1645] The terminal sends this feedback to the server.

[1646] Input: Your adjusted advertising plan.

[1647] Output: User feedback data.

[1648] Step 6:

[1649] Data collection and analysis

[1650] The server stores the feedback data in a database and analyzes it.

[1651] In the analysis process, feedback data is statistically analyzed to gain diverse perspectives.

[1652] For example, by aggregating multiple feedback data, the effectiveness of advertising and factors of interest can be identified.

[1653] Input: User feedback data.

[1654] Output: Analysis result data.

[1655] Step 7:

[1656] Report generation and delivery

[1657] The server generates a detailed report based on the analysis results.

[1658] This report includes information such as the effectiveness of the ad, the reaction of the target audience, and areas for improvement next time.

[1659] The generated report is sent to the user's terminal and provided to the user.

[1660] Input: Analysis result data.

[1661] Output: A detailed report provided to the user.

[1662] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1663] This invention is a system that combines a virtual character generation function with an emotion engine that recognizes user emotions to quickly and efficiently obtain multifaceted, emotion-based insights in market research and product development. This system operates in cooperation with four parties: a server, a terminal, an emotion engine, and a user.

[1664] System Overview

[1665] The core of the system is the server. The server has a unit that uses a generative model to generate virtual characters with diverse attributes and adjusts the content of the questionnaire based on the generated characters. The server also collects questionnaire responses submitted by users and analyzes the data. Based on the analysis results, it generates a report and provides it to the user. The system also includes an emotion engine that recognizes the user's emotions in real time and dynamically adjusts the content of the questionnaire.

[1666] The terminal is a device used by users to access the system and answer questionnaires. Based on a user's request, the user answers the questionnaire provided by the server and sends the results to the server. The emotion engine recognizes emotions from the user's facial expressions, tone of voice, etc., and sends that information to the server.

[1667] Program processing

[1668] 1. System startup and initial settings

[1669] The server starts the system and loads the necessary databases, generative models, and emotion engines, so the system is ready to operate normally.

[1670] 2. Receiving User Requests

[1671] A user logs in to the system using a terminal and inputs a request for the generation of a virtual character related to product development, for example, a request for "generation of a virtual character related to a robot toy for children aged 5 to 10."

[1672] The terminal sends this request to the server.

[1673] 3. Character Generation

[1674] The server analyzes the user's request and sends instructions to the generative model, which then generates a virtual character based on the specified attributes.

[1675] The generative model generates multiple virtual characters based on the request and returns that information to the server, such as an 8-year-old boy who loves sports or a 7-year-old girl who loves reading.

[1676] 4. Survey generation and adjustment

[1677] The server receives the generated character information and adjusts the questionnaire content based on the character's attributes, constructing specific questions that match each character's interests and preferences.

[1678] 5. Emotion recognition

[1679] The emotion engine recognizes the user's emotions in real time, analyzing facial expressions and tone of voice while the user is answering the questionnaire, and generates emotion data.

[1680] The emotion engine sends the recognized emotion data to the server.

[1681] 6. Dynamically adjusting surveys

[1682] The server dynamically adjusts the content of the questionnaire based on the emotion data sent from the emotion engine, for example, by determining whether the user is interested in the questions and changing the questions accordingly.

[1683] 7. Conducting a survey

[1684] The user uses a terminal to check the questionnaire provided by the server and enters answers from the character's perspective, such as "What kind of robot features are most appealing?"

[1685] The terminal transmits the user's answer to the server.

[1686] 8. Data Collection and Analysis

[1687] The server stores the received response data in a database, and analyzes the stored data to gain multifaceted insights related to the user request.

[1688] The server generates a detailed report based on the insights gained.

[1689] 9. Report generation and provision

[1690] The server generates a report based on the analysis results and provides it to the user, which includes specific recommendations for product development and useful insights based on market needs.

[1691] Specific examples

[1692] For example, if the product development department of a toy manufacturer is planning to develop a "robot toy for children aged 5 to 10," they can use this system as follows:

[1693] 1. A user (a toy manufacturer representative) logs into the system and inputs a request to generate a virtual character.

[1694] 2. The server generates a virtual character with the specified attributes (child aged 5 to 10) based on the generative model.

[1695] 3. The server tailors the survey based on the character and distributes it to the user.

[1696] 4. While the user answers the questionnaire and sends the answers to the server, the emotion engine recognizes the user's emotions and sends the data to the server in real time.

[1697] 5. The server dynamically adjusts the questionnaire content based on the emotional data and collects the user's responses.

[1698] 6. The server collects and analyzes the responses to gain multifaceted, emotional insights.

[1699] 7. The server generates a report based on the analysis results and provides it to the user.

[1700] This process allows toy manufacturers to efficiently develop products that take into account market needs, consumer preferences, and even emotional responses.

[1701] The processing flow will be explained below.

[1702] Step 1:

[1703] The server starts the system and loads the necessary databases, generative models, and emotion engines, so the system is ready to operate normally.

[1704] Step 2:

[1705] A user logs in to the system using a terminal and inputs a request for the generation of a virtual character related to product development, for example, a request for "generation of a virtual character related to a robot toy for children aged 5 to 10."

[1706] Step 3:

[1707] The device sends this request to the server, which includes the desired character attributes (e.g., age, interests, etc.).

[1708] Step 4:

[1709] The server analyzes the user's request and sends instructions to the generative model, which then generates a virtual character based on the specified attributes.

[1710] Step 5:

[1711] The generative model generates multiple virtual characters based on the request and returns that information to the server, such as an 8-year-old boy who loves sports or a 7-year-old girl who loves reading.

[1712] Step 6:

[1713] The server receives the generated character information and adjusts the questionnaire content based on the character's attributes, constructing specific questions that match each character's interests and preferences.

[1714] Step 7:

[1715] The server sends the tailored questionnaire to the terminal for distribution to the user, the questionnaire including specific questions appropriate for the character.

[1716] Step 8:

[1717] The emotion engine recognizes the user's emotions in real time while they are answering the questionnaire, for example, by using facial expression analysis and voice tone analysis to generate emotion data.

[1718] Step 9:

[1719] The emotion engine transmits the recognized emotion data to the server, where the emotion data includes the user's current emotional state.

[1720] Step 10:

[1721] The server dynamically adjusts the survey content based on the emotion data sent by the emotion engine, for example adding relevant follow-up questions if the user expresses interest in a question.

[1722] Step 11:

[1723] The user continues to answer questionnaires provided by the server using the terminal, and the answers entered by the user are transmitted from the terminal to the server in real time.

[1724] Step 12:

[1725] The server stores the received response data in a database, and analyzes the stored data to gain multifaceted insights related to the user request.

[1726] Step 13:

[1727] The server generates a detailed report based on the insights gained, including specific recommendations for product development and useful insights based on market needs.

[1728] Step 14:

[1729] The server generates a report based on the analysis results and provides it to the user, who then uses it as a reference for product development and marketing activities.

[1730] Specific examples

[1731] For example, if the product development department of a toy manufacturer is planning to develop a "robot toy for children aged 5 to 10," the specific process would be as follows:

[1732] Step 1:

[1733] A user (a toy manufacturer's representative) logs into the system and inputs a request for virtual character generation.

[1734] Step 2:

[1735] The server uses generative models to generate virtual characters for children between the ages of 5 and 10, such as an 8-year-old boy who loves sports or a 7-year-old girl who loves reading.

[1736] Step 3:

[1737] The server then tailors a questionnaire based on the generated character and distributes it to the user. The questionnaire includes questions such as, "What kind of robot features do you find most appealing?"

[1738] Step 4:

[1739] The user answers a questionnaire, while the emotion engine analyzes the user's facial expressions and tone of voice and transmits the emotion data to the server in real time.

[1740] Step 5:

[1741] The server dynamically adjusts the questionnaire content based on the emotion data and collects user responses.

[1742] Step 6:

[1743] The server stores the collected survey responses in a database and analyzes them to gain multifaceted, emotion-based insights.

[1744] Step 7:

[1745] The server generates a report based on the analysis results and provides it to the user, which includes specific recommendations for product development.

[1746] This process allows toy manufacturers to quickly grasp market needs and consumer preferences, and efficiently develop products that also take user emotions into consideration.

[1747] Example 2

[1748] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1749] Traditional market research and product development methods collect data without considering user emotions, resulting in limited insights and a poorly personalized user experience. Furthermore, the survey content is static, making it impossible to dynamically adjust based on user interests. This reduces the accuracy and usefulness of the collected data.

[1750] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1751] In this invention, the server includes means for generating virtual characters with diverse attributes using a generative model, means for adjusting the content of a questionnaire based on the virtual character, means for presenting the adjusted questionnaire to a user and collecting responses from the user, means for recognizing the user's emotions in real time using an emotion recognition engine and dynamically adjusting the content of the questionnaire, means for analyzing the collected responses to gain multifaceted insights, and means for generating a report of the analysis results. This enables the implementation of a questionnaire that reflects the user's emotions, improves the accuracy and usefulness of the collected data, and provides a more personalized user experience.

[1752] A "generative model" is an algorithm for generating virtual characters with diverse attributes based on user requests.

[1753] A "virtual character" is a character with specific attributes created by a generative model, and is used to adjust the content of the questionnaire.

[1754] The "survey content adjustment means" is a process that dynamically changes and adapts the content of the survey questions based on the attributes of the generated virtual character.

[1755] A "tailored questionnaire" is a questionnaire that has been modified and optimized based on the attributes of the virtual character and the user's emotional recognition.

[1756] The "means for collecting responses from users" is a mechanism by which the server receives responses entered by users to the questionnaire and stores them in a database.

[1757] An "emotion recognition engine" is software or hardware that analyzes a user's facial expressions and tone of voice in real time to identify their emotional state.

[1758] "Dynamic adjustment method based on emotion recognition" is a process of adjusting and changing the content of a questionnaire in real time based on information obtained from an emotion recognition engine.

[1759] "Data analysis methods" refers to the process of analyzing collected survey response data using statistical and machine learning techniques to derive multifaceted insights.

[1760] The "report generation means" is a process of creating a report containing useful insights and recommendations for the user based on the analysis results obtained by the data analysis means.

[1761] This invention is a system that uses a generative AI model to generate virtual characters with diverse attributes and dynamically adjusts the content of a survey based on those characters. Furthermore, it combines an emotion recognition engine to recognize users' emotions in real time and dynamically adjust the survey content based on that. This allows for more accurate data collection and insights that reflect users' emotions.

[1762] Hardware and software used

[1763] The system includes the following main components:

[1764] Server: Runs the generative model (e.g., OpenAI's GPT-3) and emotion recognition engine (e.g., Microsoft Azure Emotion API).

[1765] Device: The device through which the user accesses the system and completes the survey, such as a PC, tablet, or smartphone.

[1766] Camera and microphone: Devices used to analyze your facial expressions and tone of voice in real time.

[1767] System operation and concrete examples

[1768] First, the server starts the system and loads the necessary database, generative model, and emotion recognition engine, so the system is ready to operate normally.

[1769] Next, the user logs in to the system using a terminal. A user ID and password are required for login, which are used to verify authorization. The user then inputs a request for the generation of a virtual character related to product development. For example, the user requests "generation of a virtual character related to a robot toy for children aged 5 to 10." The terminal then sends this request to the server.

[1770] The server analyzes the user's request and sends instructions to the generative model, which then generates a virtual character based on the specified attributes. For example, an 8-year-old boy who loves sports or a 7-year-old girl who loves reading might be generated.

[1771] The server then receives the generated character information and adjusts the questionnaire content based on the character's attributes. For example, if a boy likes sports, it might add a question like "What is your favorite sport?", and if a girl likes reading, it might add a question like "What is your favorite genre of book?".

[1772] While the user is answering the survey, an emotion recognition engine analyzes the user's facial expressions and tone of voice to recognize the user's emotions in real time. The recognized emotion data is sent to the server, which then dynamically adjusts the survey content based on that data. For example, if the server determines that the user is interested in a question, it will introduce additional detailed questions.

[1773] Users use their devices to answer the questionnaire, which then transmits the answers to the server, which stores the received data in a database and analyzes it. Based on the analysis results, a report containing useful insights for product development is generated and provided to the user.

[1774] Specific prompt examples

[1775] "Generate a virtual character for children aged 5 to 10, conduct a survey based on the character's attributes, and adjust the survey based on real-time user emotions."

[1776] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1777] Step 1:

[1778] The server starts the system and loads the necessary databases, generative models, and emotion recognition engines.

[1779] Input: System startup command

[1780] Output: Load complete status

[1781] What happens: The server establishes a database connection and loads the generative AI model and emotion recognition software into memory. For example, it connects to an SQL database and initializes the generative AI model (e.g., GPT-3).

[1782] Step 2:

[1783] A user logs in to the system using a terminal. A user ID and password are required to log in, and authorization is confirmed using these.

[1784] Input: User ID, Password

[1785] Output: Login successful message

[1786] Specific operation: The terminal sends the entered user ID and password to the server, which verifies them and, if successful, starts the session.

[1787] Step 3:

[1788] The user inputs a request for the generation of a virtual character related to product development. For example, the user requests "generation of a virtual character related to a robot toy for children aged 5 to 10." The terminal then sends this request to the server.

[1789] Input: Character creation request

[1790] Output: Request receipt confirmation message

[1791] Specific operation: The terminal sends the request content as a prompt to the server, and the server adds it to the queue.

[1792] Step 4:

[1793] The server analyzes the user's request and sends instructions to the generative model, which then generates a virtual character based on the specified attributes.

[1794] Input: Character creation request

[1795] Output: Generated character information

[1796] Specific operation: The server analyzes the request content and sends appropriate prompts to the generative AI model (e.g., GPT-3), which returns multiple character information.

[1797] Step 5:

[1798] The server receives the generated character information and adjusts the content of the questionnaire based on the character's attributes.

[1799] Input: Generated character information

[1800] Output: Adjusted survey

[1801] Specific operation: The server dynamically generates questions based on the character's interests and preferences. For example, for a character who likes sports, the server adds the question "What is your favorite sport?"

[1802] Step 6:

[1803] The emotion recognition engine analyzes the user's facial expressions and tone of voice while they are answering the questionnaire, and recognizes their emotions in real time.

[1804] Input: User's facial expression data, voice data

[1805] Output: Emotion recognition data

[1806] How it works: Data is collected through the camera and microphone connected to the device, and an emotion recognition engine (e.g., Microsoft Azure Emotion API) analyzes it in real time.

[1807] Step 7:

[1808] The server dynamically adjusts the content of the questionnaire based on the emotion recognition data.

[1809] Input: Emotion recognition data

[1810] Output: Dynamically adjusted survey

[1811] Specific operation: The server uses emotion recognition data to change the content of survey questions according to the user's interests and stress level. For example, it changes questions that the user may find difficult to understand into simpler phrases.

[1812] Step 8:

[1813] The user uses the terminal to answer the questionnaire provided by the server.

[1814] Input: Survey Question

[1815] Output: User's answer

[1816] Specific operation: The user fills out a questionnaire and sends the answers to the server. The device then sends the answer data to the server.

[1817] Step 9:

[1818] The server stores the received response data in a database and analyzes the data.

[1819] Input: Answer data

[1820] Output: Analysis results

[1821] Specific operation: The server stores the response data and emotion recognition data in a database and analyzes them using statistical methods and machine learning algorithms.

[1822] Step 10:

[1823] The server generates a detailed report based on the analysis results.

[1824] Input: Analysis results

[1825] Output: Generated report

[1826] Specific operation: The server creates a report containing useful insights based on the analysis results and provides it to the user. For example, a report may be generated that states, "The most popular feature among 8-year-old boys who like sports is the exercise tracker function."

[1827] (Application example 2)

[1828] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1829] Modern advertising delivery systems lack the technology to dynamically adjust advertisements based on user emotions in real time. This results in a lack of timely advertisements that match user interests and preferences, resulting in reduced advertising effectiveness. Furthermore, there is a need for an efficient method to accurately recognize user emotions and instantly adjust advertisement content based on those emotions.

[1830] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1831] In this invention, the server includes means for generating a virtual character with various attributes using a generative model, means for adjusting the content of a questionnaire based on the virtual character, means for presenting the adjusted questionnaire to a user and collecting responses from the user, means for analyzing the collected responses and obtaining multifaceted insights, means for generating a report of the analysis results and providing it to the user, means for recognizing the user's emotions and dynamically adjusting the content of the questionnaire based on the data, means for collecting user emotion data using a sensor attached to the smart device, and means for adjusting and delivering advertisement content based on the emotion data in real time, thereby enabling effective advertisement delivery that responds to the user's emotional state.

[1832] A "generative model" is an algorithm or artificial intelligence mechanism for generating virtual characters.

[1833] A "virtual character" is a character that is generated using digital technology and has a variety of attributes.

[1834] "Means for adjusting the content of the survey" refers to technology or mechanisms for optimizing survey questions based on the attributes of the virtual character.

[1835] "Means for collecting responses from users" refers to the technology and equipment used to collect data from users responding to the questionnaire.

[1836] "Means of gaining multifaceted insights" are methods for analyzing collected data and deriving insights from multiple perspectives.

[1837] "Means for generating a report and providing it to the user" refers to the process or technology for compiling the analysis results in a report format and providing it to the user.

[1838] "Means for recognizing user emotions" refers to technology that infers emotions from the user's facial expressions, tone of voice, etc.

[1839] "Dynamic adjustment means" refers to methods and technologies that change content in real time depending on the state of the data.

[1840] "Smart device" refers to a portable electronic device that can connect to the Internet, including, for example, a smartphone or smart glasses.

[1841] A "sensor" is a device used to collect a user's facial expressions, tone of voice, and other physiological data.

[1842] "Emotion data" is data that indicates the emotional state of the user, and includes, for example, facial expression data and tone of voice data.

[1843] "Means for adjusting and delivering advertising content" refers to a mechanism that changes the content of advertisements based on collected emotional data and displays them to users.

[1844] This invention provides a system that recognizes the user's emotions in real time as they view advertisements using a smart device, and dynamically adjusts and delivers advertisement content. A specific embodiment of this system will be described below.

[1845] System Overview

[1846] The system mainly consists of four components: a server, a terminal, an emotion recognition engine, and a user.

[1847] 1. Server:

[1848] The server is the center of the system, running the generative model and emotion recognition engine. It uses the generative model to generate a virtual character and adjusts the content of the survey based on that character. It also analyzes the response data and emotion data sent by users and adjusts the content of advertisements in real time.

[1849] 2. Terminal:

[1850] The device is the device that the user actually operates, such as smart glasses or a smartphone. The device is equipped with a camera and microphone, which are used to transmit the user's facial expressions and voice to the emotion recognition engine.

[1851] 3. Emotion Recognition Engine:

[1852] The emotion recognition engine analyzes emotions from the user's facial expressions and tone of voice in real time. This engine is built using machine learning frameworks such as TensorFlow. The analyzed emotion data is sent to a server.

[1853] 4. User:

[1854] The user operates the device and is responsible for viewing the advertisements. The user's emotions are recognized in real time, and the advertisements are dynamically adjusted based on that data.

[1855] Data Generation and Processing

[1856] The server uses a generative model to generate a virtual character. The model sets the character's attributes based on a prompt entered by the user. For example, based on a prompt such as "Generate an advertisement for the latest fashion items enjoyed by women in their 20s," the server generates a character that best suits the target user and adjusts the relevant survey.

[1857] Emotion Recognition and Ad Tailoring

[1858] The device (e.g., smart glasses) uses a camera and microphone to capture the user's facial expressions and tone of voice, and then analyzes the data with an emotion recognition engine. This engine predicts the user's emotions based on the collected data and sends the results to a server. The server then dynamically adjusts advertising content based on the received emotional data, enabling more effective ad delivery.

[1859] Specific examples

[1860] For example, imagine a user wearing smart glasses while walking through a shopping mall. When the user views an advertisement displayed on a billboard, the smart glasses' camera and microphone capture the user's facial expressions and tone of voice. This data is analyzed by an emotion recognition engine, and if the user expresses "interest" or "enjoyment," the server adjusts the content displayed on the billboard so that the next relevant product is displayed.

[1861] Hardware and software used

[1862] Hardware: smart glasses, smartphone, camera, microphone

[1863] Software: TensorFlow (machine learning framework), real-time ad server (e.g., AWS, Google Cloud)

[1864] Prompt Sentence Examples

[1865] 1. "Generate ads for the latest fashion items enjoyed by women in their 20s."

[1866] 2. "Show recommended ads based on user interests."

[1867] This allows for effective advertising delivery based on the user's real-time emotional state.

[1868] The above is a specific embodiment of the present invention.

[1869] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1870] Step 1:

[1871] System startup and initial setup

[1872] The server starts the system and loads the necessary database, generative model, and emotion recognition engine. This prepares the system for normal operation. Specifically, the server loads various models and data. The input to this step is an instruction to start the server, and the output is the completion of loading of the model and data.

[1873] Step 2:

[1874] Receiving user requests

[1875] A user logs in to the system using a terminal and inputs a request for generating a virtual character related to product development. For example, the user might input a prompt such as, "Please generate an advertisement for the latest fashion items enjoyed by women in their twenties." The terminal then sends this request to the server. The input is the user request, and the output is the request sent to the server.

[1876] Step 3:

[1877] Character Generation

[1878] The server analyzes the user's request and sends instructions to the generative model. The generative model generates a virtual character based on the specified attributes. The input is the user request, and the output is information about the generated virtual character. The specific operation is to input a prompt to the generative model and generate a character.

[1879] Step 4:

[1880] Survey generation and coordination

[1881] The server receives the generated character information and adjusts the survey content based on the character's attributes. It constructs specific questions that match each character's interests and preferences. The input is virtual character information, and the output is the adjusted survey content. The specific operation is the generation and optimization of survey items.

[1882] Step 5:

[1883] emotion recognition

[1884] The device uses a camera and microphone to capture the user's facial expressions and tone of voice, and sends the data to an emotion recognition engine. The emotion recognition engine recognizes the user's emotions in real time and sends the information to a server. The input is the user's facial and voice data, and the output is recognized emotion data. The specific operations are data capture and emotion recognition.

[1885] Step 6:

[1886] Dynamic survey adjustment

[1887] The server dynamically adjusts the content of the questionnaire based on the emotion data sent from the emotion recognition engine. For example, it determines whether the user is interested in the question and changes the question accordingly. The input is emotion data, and the output is a dynamically adjusted questionnaire. The specific operations are emotion data analysis and questionnaire content adjustment.

[1888] Step 7:

[1889] Conducting a survey

[1890] The user uses the terminal to check the questionnaire provided by the server and input answers from the character's perspective. For example, they answer questions such as "What features of the product are attractive?" The terminal then sends the user's answers to the server. The input is the questionnaire answers, and the output is the sending of the answers to the server. The specific operations are the input and sending of the questionnaire answers.

[1891] Step 8:

[1892] Data collection and analysis

[1893] The server stores the received response data in a database. It then analyzes the stored data to gain multifaceted insights related to the user request. The input is the survey response data, and the output is the analysis results. The specific operations are data storage and analysis.

[1894] Step 9:

[1895] Report generation and delivery

[1896] The server generates a report based on the analysis results and provides it to the user. The report contains specific recommendations that are useful for product development and useful insights based on market needs. The input is the analysis results and the output is the report. The specific operation is generating and providing the report.

[1897] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1898] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1899] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1900] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1901] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1902] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1903] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1904] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1905] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1906] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1907] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1908] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1909] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1910] 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.

[1911] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1912] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1913] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1914] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1915] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1916] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1917] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1918] The following is further disclosed regarding the above embodiment.

[1919] (Claim 1)

[1920] A means for generating a virtual character having various attributes using a generative model;

[1921] a means for tailoring survey content based on the virtual character;

[1922] means for presenting the tailored survey to users and collecting responses from the users;

[1923] A means of analyzing the collected responses and gaining multifaceted insights;

[1924] A means for generating a report of the analysis results and providing it to a user;

[1925] A system including:

[1926] (Claim 2)

[1927] 10. The system of claim 1, further comprising means for specifying attributes of the virtual character based on a user request and sending instructions to the generative model based on the request.

[1928] (Claim 3)

[1929] 10. The system according to claim 1, further comprising means for storing the collected response data in a database and generating a report based on the analysis results from the database.

[1930] "Example 1"

[1931] (Claim 1)

[1932] A means for generating a virtual character having various attributes using a generative model;

[1933] a means for tailoring survey content based on the virtual character;

[1934] means for presenting the tailored survey to users and collecting responses from the users;

[1935] A means of analyzing the collected responses and gaining multifaceted insights;

[1936] A means for generating a report of the analysis results and providing it to a user;

[1937] A means for loading the necessary database and generative model at system startup and configuring the system for normal operation;

[1938] a means for analyzing the user's request before sending instructions to the generative model;

[1939] A database for collecting responses and a means for data analysis;

[1940] A system including:

[1941] (Claim 2)

[1942] 10. The system of claim 1, further comprising means for specifying attributes of the virtual character based on a user request and sending instructions to the generative model based on the request.

[1943] (Claim 3)

[1944] 10. The system according to claim 1, further comprising means for storing the collected response data in a database and generating a report based on the analysis results.

[1945] "Application Example 1"

[1946] (Claim 1)

[1947] A means for generating a virtual character having various attributes using a generative model;

[1948] A means for adjusting survey content and advertising plans based on the virtual character;

[1949] a means for presenting tailored surveys and advertising offers to users and collecting responses and feedback from users;

[1950] A means to analyze collected responses and feedback to gain multifaceted insights,

[1951] A means for generating a report of the analysis results and providing it to a user;

[1952] A system including:

[1953] (Claim 2)

[1954] 10. The system of claim 1, further comprising means for specifying attributes of the virtual character based on a user request and sending instructions to the generative model based on the request.

[1955] (Claim 3)

[1956] 10. The system according to claim 1, further comprising means for storing the collected response data and feedback data in a database and generating a report based on the analysis results from the database.

[1957] "Example 2: Combining Emotion Engines"

[1958] (Claim 1)

[1959] A means for generating a virtual character having various attributes using a generative model;

[1960] a means for tailoring survey content based on the virtual character;

[1961] means for presenting the tailored survey to users and collecting responses from the users;

[1962] A means of analyzing the collected responses and gaining multifaceted insights;

[1963] A means for generating a report of the analysis results and providing it to a user;

[1964] a means for using an emotion recognition engine to recognize a user's emotions and dynamically adjust the questionnaire content;

[1965] A system including:

[1966] (Claim 2)

[1967] 10. The system of claim 1, further comprising means for specifying attributes of the virtual character based on a user request and sending instructions to the generative model based on the request.

[1968] (Claim 3)

[1969] 10. The system according to claim 1, further comprising means for storing the collected response data in a database and generating a report based on the analysis results from the database.

[1970] "Application example 2 when combining emotion engines"

[1971] (Claim 1)

[1972] A means for generating a virtual character having various attributes using a generative model;

[1973] a means for tailoring survey content based on the virtual character;

[1974] means for presenting the tailored survey to users and collecting responses from the users;

[1975] A means of analyzing the collected responses and gaining multifaceted insights;

[1976] A means for generating a report of the analysis results and providing it to a user;

[1977] A means for recognizing user emotions and dynamically adjusting survey content based on that data;

[1978] A means for collecting emotion data of a user using a sensor attached to the smart device;

[1979] A means to adjust and deliver advertising content based on real-time emotional data,

[1980] A system including:

[1981] (Claim 2)

[1982] 10. The system of claim 1, further comprising means for specifying attributes of the virtual character based on a user request and sending instructions to the generative model based on the request.

[1983] (Claim 3)

[1984] 10. The system according to claim 1, further comprising means for storing the collected response data in a database and generating a report based on the analysis results from the database.

[1985] (Claim 4)

[1986] 10. The system of claim 1, further comprising means for analyzing emotion data collected by a user using a smart device and dynamically modifying advertisements in real time based on the analysis results.

[1987] (Claim 5)

[1988] 5. The system of claim 4, further comprising means for using a camera and microphone for collecting emotion data. [Explanation of symbols]

[1989] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for generating a virtual character having various attributes using a generative model; a means for tailoring survey content based on the virtual character; means for presenting the tailored survey to users and collecting responses from the users; A means of analyzing the collected responses and gaining multifaceted insights; A means for generating a report of the analysis results and providing it to a user; A system including:

2. The system according to claim 1 , further comprising means for specifying attributes of the virtual character based on a user request and sending instructions to the generative model based on the request.

3. 2. The system according to claim 1, further comprising means for storing the collected response data in a database and generating a report based on the analysis results from the database.

Images