System

Abstract

A system is provided.SOLUTION: A system, comprising: means for a user to input information about a service; means for analyzing the input service information and extracting relevant data points; means for generating a plurality of proposed personas using an artificial intelligence model based on the extracted data points; means for presenting the generated proposed personas to the user; and means for storing proposed personas selected by the user and processing feedback.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] When service planners consider personas, they are influenced by personal biases and preconceptions, making it difficult to create a realistic and effective persona. This can lead to a decline in service quality and the inability to provide services that are appropriate for the target demographic. [Means for solving the problem]

[0005] The system includes a means for a user to input information about a service, a means for analyzing the input service information and extracting relevant data points, a means for generating multiple persona proposals using an artificial intelligence model based on the extracted data points, a means for presenting the generated persona proposals to the user, and a means for saving the persona proposal selected by the user and processing feedback. This eliminates the bias of service planners and enables the formation of efficient and realistic persona images, leading to the creation of better services.

[0006] The "means for the user to input information about the service" is an interface that allows the user to input detailed information about the service that the user wishes to provide to the system.

[0007] "Means for analyzing input service information and extracting relevant data points" refers to a function that analyzes information about a service input by a user and identifies data points necessary for generating an effective persona.

[0008] The "means for generating multiple persona proposals using an artificial intelligence model based on the extracted data points" refers to an algorithm for using an artificial intelligence model with the data points obtained through the analysis as input to generate a variety of persona proposals.

[0009] The "means for presenting the generated persona proposals to the user" refers to a display means for visually presenting the multiple persona proposals generated by the artificial intelligence model to the user.

[0010] "Means for saving user-selected persona ideas and processing feedback" refers to the function of saving user-selected persona ideas in a database and collecting and processing feedback information. [Brief explanation of the drawings]

[0011] [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

[0012] 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.

[0013] First, the terms used in the following description will be explained.

[0014] 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).

[0015] 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.

[0016] 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.

[0017] 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.

[0018] 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."

[0019] [First embodiment]

[0020] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0021] 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.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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."

[0032] System Overview

[0033] The present invention is a system that allows service planners to create effective personas while eliminating bias. This system involves a series of processes: inputting information about a service, generating multiple personas using artificial intelligence to overcome human biases and limitations, and presenting, selecting, and saving them to the user.

[0034] Explaining the program's processing

[0035] 1. The user enters the service details into the system

[0036] The user inputs detailed information about the service they wish to provide through the terminal. For example, if a user wants to provide a "luxury urban bicycle rental service," they would input details such as "target market: urban areas, age group: 20-35 years old, frequency of use: mostly on weekends." This information will be the basis for subsequent processing.

[0037] 2. The server processes the input data

[0038] The server receives the service information and parses it into structured data. Specifically, it converts the data into a format such as JSON and extracts relevant data points (e.g., age group, region, interests, etc.). The data obtained from this analysis process becomes the input for generating personas.

[0039] 3. The server starts the generated AI

[0040] The server runs a pre-trained generative AI model, which inputs the analyzed data points and generates multiple persona proposals. The personas generated are a combination of demographics (age, gender, occupation, etc.) and psychographics (interests, values, behavioral patterns, etc.).

[0041] 4. The server presents the persona proposal to the user

[0042] The server presents the user with multiple persona ideas generated by the generative AI, including detailed information such as "30-year-old male, engineer living in the city, bicycle commuter" and "33-year-old female, marketing, gym-goer on weekday evenings."

[0043] 5. Users choose the persona that best suits them

[0044] Users can select the persona they think is most suitable from the presented persona list. For example, they can choose the persona "33-year-old female, marketing staff, uses bicycle to go to the gym on weekday evenings."

[0045] 6. The server stores the persona information

[0046] The server stores the persona information selected by the user in a database and receives feedback provided by the user, which is used as training data for the AI ​​to improve the accuracy of future persona generation.

[0047] Specific examples

[0048] As a specific example, the case of a user who wishes to provide an "urban luxury bicycle rental service" will be described.

[0049] 1. The user enters details about the service: "Target market: urban areas," "Age range: 20-35 years old," "Frequency of use: mostly on weekends," etc.

[0050] 2. The server analyzes the input data: extracting data points such as "age group," "region," and "interests."

[0051] 3. The server launches the generation AI: The AI ​​generates persona proposals based on the extracted data.

[0052] 4. The server presents persona options: Multiple persona options (e.g., a 30-year-old male engineer living in an urban area who commutes by bicycle).

[0053] 5. User selects persona: A persona that fits (e.g., 33-year-old female, marketing).

[0054] 6. Server saves persona information: The selected persona is saved in the database and feedback is collected.

[0055] In this way, the present invention allows users to input the details of the service, and the server uses generation AI to generate and present a detailed persona, eliminating bias and efficiently forming personas, which enables the provision of better services.

[0056] The processing flow will be explained below.

[0057] Step 1:

[0058] The user inputs service information. Specifically, the user uses the interface on the device to input details about the service they plan to provide (e.g., "urban luxury bicycle rental service," "target market: urban areas," "age range: 20-35 years old," "usage frequency: mostly on weekends").

[0059] Step 2:

[0060] The server receives the input service information. Specifically, the server converts the information sent by the user into an analyzable data format and stores it in a database.

[0061] Step 3:

[0062] The server analyzes the input data. Specifically, the server analyzes the received service information and extracts relevant data points (e.g., age group, region, interests, etc.). This process uses natural language processing technology.

[0063] Step 4:

[0064] The server launches a generative AI model, which inputs the extracted data points into the model to generate persona suggestions. This AI model is pre-trained to generate multiple detailed personas based on the input data.

[0065] Step 5:

[0066] The server presents the generated persona proposals to the user. Specifically, the server visually displays multiple generated personas (e.g., "30-year-old male, engineer living in the city, bicycle commuter" and "33-year-old female, marketing, gym-goer on weekday evenings") on the user's device.

[0067] Step 6:

[0068] The user selects the most suitable persona. Specifically, the user selects the most suitable persona from the presented persona list and sends the selection result to the server.

[0069] Step 7:

[0070] The server saves the selected persona information. Specifically, the server stores the user-selected persona data in a database and uses it for future service planning. It also receives feedback from users and uses it as further training data for the generative AI model.

[0071] This series of processing steps allows users to efficiently create realistic and useful personas while eliminating bias, which will enable them to develop strategies that are more suited to the target market when planning and providing services.

[0072] Example 1

[0073] 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."

[0074] Traditional service design tends to rely on the biases and experiences of individuals in charge, making it difficult to generate objective and effective personas. Furthermore, there is often a lack of mechanisms for properly storing the personas and incorporating feedback. This creates challenges that make it difficult to maximize the effectiveness of services.

[0075] 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.

[0076] In this invention, the server includes means for a user to input information about a service, means for converting the input service information into structured data and analyzing it, means for using a generative AI model to generate multiple persona proposals based on the analyzed data points, means for presenting the generated persona proposals to the user, and means for saving the persona proposal selected by the user and processing feedback, thereby eliminating bias and enabling objective and effective persona generation, and further enabling continuous improvement of the service by incorporating feedback.

[0077] "Information about the service" refers to data such as details of the service provided by the user, target market, age group, frequency of use, etc.

[0078] "Structured data" is data that is organized in a certain format that is easy to analyze and process. Examples include JSON and CSV formats.

[0079] "Analysis" is the process of converting input data into an understandable format and extracting the necessary information.

[0080] A "data point" is an individual unit of information extracted from analyzed data, and includes information such as age group, region, and interests.

[0081] A "generative AI model" is a model that has been trained using artificial intelligence (AI) technology and is an algorithm that generates new information based on input data.

[0082] A "persona proposal" is a virtual user profile created by a generative AI model, combining demographic and psychographic information.

[0083] "Presentation" is the process of showing the generated persona proposals to the user, allowing the user to evaluate and select a persona.

[0084] "Saving" means recording the selected persona and related data in a storage device such as a database.

[0085] "Feedback" refers to evaluations and opinions provided by users, and is data used to improve generative AI models and optimize services.

[0086] A "system" is an integrated technology collection that combines the above means to carry out a series of processes.

[0087] System configuration

[0088] This invention is a system that allows service planners to create effective personas while eliminating bias. This system uses a generative AI model to generate multiple persona proposals based on service information entered by the user, and includes a series of processes for presenting, selecting, and saving the personas to the user.

[0089] Hardware and Software

[0090] The system consists of the following hardware and software:

[0091] Server: Receives data, analyzes it, launches the generated AI model, generates personas, and stores data. In this invention, a general web server (e.g., Apache) can be used.

[0092] Terminal: A device on which users input service information and view and select generated personas. A general PC or smartphone can be used.

[0093] Generative AI model: An artificial intelligence model that generates personas based on data entered by users. A specific example would be a natural language processing model such as GPT-4.

[0094] Operational Overview

[0095] Entering Service Information

[0096] Users use their own devices to input service details. The information input includes the name of the service, the target market, the expected age group, and frequency of use. For example, if a user wants to provide a "luxury urban bicycle rental service," they would input information such as "target market: urban areas, age group: 20-35 years old, frequency of use: mostly on weekends."

[0097] Data transmission and analysis

[0098] The device sends the entered data to a server, which converts it into structured data, such as JSON format, and extracts relevant data points, such as age group, location, and interests, facilitating subsequent data analysis.

[0099] Launching the generative AI model and generating personas

[0100] The server then runs a trained generative AI model and inputs the extracted data points to generate multiple personas, each of which includes demographic and psychographic information, providing an unbiased, objective portrayal of the user.

[0101] Persona Presentation and Selection

[0102] The server sends the generated persona proposals to the user's device, allowing the user to view and select the most suitable one from the presented persona list.

[0103] Data storage and feedback processing

[0104] The persona ideas selected by the user are stored in a database by the server, and user feedback is also collected to help improve the accuracy of future persona generation.

[0105] Specific examples

[0106] As a specific example, the procedure when a user wants to provide an "urban luxury bicycle rental service" will be shown.

[0107] Example of a prompt for user input:

[0108] "The target market is urban areas. The age range is 20-35, and usage is mostly on weekends."

[0109] Example of a server-generated persona:

[0110] 30-year-old male, engineer living in a city, commutes to work by bicycle on weekends

[0111] 33-year-old woman, marketing manager, weekday evening gym goer

[0112] In this way, users can efficiently generate and select personas targeted at specific markets and improve the quality of their services by obtaining appropriate feedback, thereby eliminating user bias and enabling objective and effective service design.

[0113] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0114] Step 1:

[0115] User enters service details

[0116] Users use their own devices to input detailed information about the service they wish to provide. Specifically, they input information such as the name of the service, target market, age group, and frequency of use into a form. Examples of information that can be input include "target market: urban areas," "age group: 20-35 years old," and "frequency of use: mostly on weekends."

[0117] Input and Output

[0118] Input: Service details

[0119] Output: Structured JSON format data

[0120] Specific actions

[0121] The user enters service information into an input form on the device.

[0122] After completing the input, press the submit button and the form data will be converted to JSON format.

[0123] Step 2:

[0124] The device sends the input data to the server

[0125] The user's device sends the input data to the server as structured data (JSON format), using HTTPS as the communication protocol.

[0126] Input and Output

[0127] Input: Structured JSON format data

[0128] Output: HTTP request to the server

[0129] Specific actions

[0130] The terminal converts the input data into JSON format.

[0131] When the submit button is pressed, an HTTP POST request is sent to the server.

[0132] Step 3:

[0133] The server receives and analyzes the input data

[0134] The server parses the received data, specifically the JSON format data, and extracts the necessary data points (e.g., age group, region, interests).

[0135] Input and Output

[0136] Input: Received JSON format data

[0137] Output: Extracted data points

[0138] Specific actions

[0139] Parse the JSON data received by the server.

[0140] Data points such as "age group," "region," and "interests" are extracted and stored in internal memory.

[0141] Step 4:

[0142] The server starts the generation AI and generates a persona.

[0143] The server then launches the trained generative AI model, inputting the extracted data points to generate multiple persona suggestions.

[0144] Input and Output

[0145] Input: Data points

[0146] Output: Multiple persona ideas generated

[0147] Specific actions

[0148] The server launches a generative AI model (e.g., GPT-4).

[0149] The extracted data points are input into a generative AI model.

[0150] The generative AI model generates multiple persona ideas and stores them in memory.

[0151] Step 5:

[0152] The server presents the generated persona ideas to the user

[0153] The server sends the generated persona proposals to the user's device, allowing the user to view and select from them.

[0154] Input and Output

[0155] Input: Multiple persona ideas generated

[0156] Output: Data presented to the user's device

[0157] Specific actions

[0158] The server sends the generated persona proposal to the user's device.

[0159] Display a list of personas on the user's device.

[0160] Step 6:

[0161] User selects persona

[0162] The user selects the most suitable persona from the presented persona list and sends the selection to the server.

[0163] Input and Output

[0164] Input: Personalist

[0165] Output: Data for selected personas

[0166] Specific actions

[0167] Users can view the persona list on their device and select the most suitable persona.

[0168] The data of the selected persona is sent to the server.

[0169] Step 7:

[0170] The server stores the selected persona information and processes the feedback

[0171] The server stores the user-selected persona information in a database and also collects user feedback to use as training data for the generative AI model.

[0172] Input and Output

[0173] Input: Selected persona information, feedback

[0174] Output: Saved persona information, updated generative AI model

[0175] Specific actions

[0176] The server stores the selected persona information in a database.

[0177] Collect user feedback and use it to improve generative AI models.

[0178] (Application example 1)

[0179] 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."

[0180] In conventional advertising campaigns, the creation of targeting personas often relies on the subjectivity and bias of marketers, which can lead to a high risk of missing the right target demographic. Another issue is that the persona creation process is time-consuming and inefficient. Therefore, there is a demand for a system that can eliminate bias and quickly and effectively generate multiple persona proposals.

[0181] 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.

[0182] In this invention, the server includes means for a user to input information about a service, means for analyzing the input service information and extracting relevant data points, means for using an artificial intelligence model to generate multiple persona proposals based on the extracted data points, means for presenting the generated persona proposals to the user, means for saving the persona proposals selected by the user and processing feedback, means for presenting the persona proposals generated by the analysis data to a smartphone application, and means for saving the persona proposals selected by the user in a cloud database. This makes it possible to quickly generate effective persona proposals that are free from bias and improve the targeting of advertising campaigns.

[0183] "Service" refers to the products or actions provided, and is an activity that provides value to users.

[0184] "Information" is a collection of data or knowledge that can be used for a specific purpose.

[0185] "User" refers to any individual or entity that uses the System or Services.

[0186] "Means" refers to a method or device for achieving a particular purpose.

[0187] "Input" refers to the act of taking data into the system from outside.

[0188] "Analysis" is the process of breaking down input data into an understandable form.

[0189] "Relevant data points" refer to elements of data that are important for analysis.

[0190] "Extraction" is the act of extracting the necessary information from a data set.

[0191] An "artificial intelligence model" refers to a combination of algorithms designed to perform a specific task using machine learning or deep learning.

[0192] A "persona" is a concrete representation of a specific typical customer, a virtual person who is the target of a service or advertisement.

[0193] "Generation" is the act of creating new data or information according to predetermined rules or algorithms.

[0194] "Presenting" is the act of displaying or providing information to a user.

[0195] "Selection" is the act of choosing a specific option from multiple options.

[0196] "Storage" is the act of keeping data in a usable state for a long period of time.

[0197] "Feedback" refers to the reaction or information obtained as a result of an action or operation.

[0198] "Processing" is the act of manipulating or transforming input information to make it suitable for a purpose.

[0199] "Smartphone application" refers to a software program that runs on a smartphone.

[0200] "Cloud database" refers to a collection of digital information stored on remote servers accessible via the internet.

[0201] The present invention provides a system for quickly generating target personas for advertising campaigns with high accuracy, which involves a process in which a user inputs information about a service through a smartphone application, and the information is analyzed to generate a persona.

[0202] System configuration

[0203] 1. User input:

[0204] Using a smartphone application, users enter details of the services they wish to offer, such as the objectives of their advertising campaign, their target market, age group, and interests.

[0205] 2. Data Analysis Methods:

[0206] The server receives the input information and converts it into structured data such as JSON format using the Python json library.

[0207] Extract relevant data points (e.g., age, gender, location, interests) from structured data.

[0208] 3. Using generative AI models:

[0209] The server runs a pre-trained generative AI model that generates multiple persona suggestions from the extracted data points based on a specific algorithm.

[0210] 4. How to present persona ideas:

[0211] The server presents the generated persona proposal to the user's smartphone application. For example, the proposed persona displays detailed information such as "25-year-old male, freelance designer, online shopping on weekday evenings."

[0212] 5. User Choice:

[0213] The user selects the persona that they think is most suitable from the persona proposals presented.

[0214] 6. How persona information is stored:

[0215] The selected personas are saved in a cloud database, which ensures data persistence.

[0216] Specific examples

[0217] Consider a case where a user wants to run an advertising campaign. For example, the user uses the system in the following steps:

[0218] Example of input prompt:

[0219] Product Category: High-end fashion

[0220] Target market: Big cities

[0221] Campaign Objective: Increase brand awareness

[0222] Age range: 20-35

[0223] Examples of generated persona ideas:

[0224] 1. 25-year-old male, freelance designer, online shopping on weekday evenings

[0225] 2. A 28-year-old woman, a marketing manager, visits the mall on weekends.

[0226] Users can select a persona and store it in a cloud database for efficient targeting of advertising campaigns. This system is a powerful tool for eliminating bias and providing scientifically based targeting strategies.

[0227] The specific hardware and software used include smartphones, cloud servers, and computing resources for running AI models (e.g., servers with GPUs). The software is based on Python, and the AI ​​model uses deep learning libraries such as TensorFlow and PyTorch.

[0228] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0229] Step 1:

[0230] Users enter service details for their advertising campaigns through a smartphone application, including product category, target market, campaign objectives, age group, etc. This information is the initial input data for the system.

[0231] Step 2:

[0232] The device (smartphone) receives the input information and sends it to the server, which converts it into structured data such as JSON. For example, the Python json library can be used to parse the input data and extract relevant data points (such as age, gender, region, and interests).

[0233] Step 3:

[0234] The server then launches a pre-trained generative AI model based on the analyzed data points. The generative AI model is built using deep learning libraries such as TensorFlow and PyTorch. The AI ​​model takes the analyzed data as input and generates persona suggestions. The output is a set of detailed personas.

[0235] Step 4:

[0236] The server sends the generated persona proposals to a smartphone application and presents them to the user. The user can check multiple persona proposals on the smartphone screen. For example, persona information such as "25-year-old male, freelance designer, online shopping on weekday evenings" is displayed.

[0237] Step 5:

[0238] The user selects the persona they think is most suitable from the proposed personas. The selected persona is sent from the device to the server. The user's selection is transmitted to the server as feedback and used to improve the proposed persona.

[0239] Step 6:

[0240] The server stores the selected persona information in a cloud database, which is used for future advertising campaigns and system improvements. User feedback data is also used as training data for generative AI models.

[0241] This will enable more effective targeting in advertising campaigns, improve the accuracy of persona generation, and further strengthen marketing strategies by providing unbiased, scientific persona proposals quickly.

[0242] 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.

[0243] System Overview

[0244] The present invention is a system that recognizes a user's emotions and generates a persona that takes those emotions into consideration. This system involves a series of processes: inputting information about a service, analyzing the user's emotional state using an emotion engine, generating and presenting multiple personas, and evaluating the user's preferences in real time and providing feedback.

[0245] Explaining the program's processing

[0246] 1. The user enters the service details into the system

[0247] The user inputs detailed information about the service they wish to provide through the terminal. For example, if a user wants to provide a "luxury urban bicycle rental service," they would input details such as "target market: urban areas, age group: 20-35 years old, frequency of use: mostly on weekends." This information will be the basis for subsequent processing.

[0248] 2. The server processes the input data

[0249] The server receives the service information and parses it into structured data. Specifically, it converts the data into a format such as JSON and extracts relevant data points (e.g., age group, region, interests, etc.). The data obtained from this analysis process becomes the input for generating personas.

[0250] 3. Recognize user emotions using an emotion engine

[0251] When a user enters service information, the emotional state of the user is analyzed through the emotion engine. The emotional data obtained through this analysis will be an important factor in later persona generation.

[0252] 4. The server launches the generative AI model

[0253] The server launches a pre-trained generative AI model, which inputs the analyzed data points and emotional data into the AI ​​model, and the artificial intelligence generates multiple persona proposals. The AI ​​model aims to generate a more appropriate persona by taking the emotional data into account.

[0254] 5. The server presents the generated persona to the user.

[0255] The server presents the user with multiple persona ideas generated by the generative AI, including detailed information such as "30-year-old male, engineer living in the city, bicycle commuter" and "33-year-old female, marketing, gym-goer on weekday evenings."

[0256] 6. Users choose the persona that best suits them

[0257] The user selects the persona they think is most suitable from the presented persona list, and the emotion engine evaluates the user's preferences in real time and collects emotional data based on the selection results as feedback.

[0258] 7. The server stores the persona information

[0259] The server stores the persona information selected by the user in a database, and also receives feedback provided by the user, which is used as training data for the AI ​​generator to improve the accuracy of future persona generation.

[0260] Specific examples

[0261] As a specific example, the case of a user who wishes to provide an "urban luxury bicycle rental service" will be described.

[0262] 1. The user enters details about the service: "Target market: urban areas," "Age range: 20-35 years old," "Frequency of use: mostly on weekends," etc.

[0263] 2. The server analyzes the input data: extracting data points such as "age group," "region," and "interests."

[0264] 3. The emotion engine recognizes the user's emotions and analyzes the data.

[0265] 4. The server launches the generation AI: The AI ​​generates a persona proposal based on the extracted data and emotional data.

[0266] 5. The server presents the generated persona ideas: multiple persona ideas (e.g., a 30-year-old male engineer living in an urban area who commutes by bicycle).

[0267] 6. User selects persona: A persona that fits (e.g., 33-year-old female, marketing).

[0268] 7. Server saves persona information: The selected persona is saved in the database and feedback is collected.

[0269] In this way, the present invention allows users to input the details of a service, and the server uses AI to generate and present a detailed persona. Real-time evaluation incorporating the user's emotions is then performed, eliminating bias and efficiently creating realistic and useful personas. This allows for the formulation of strategies that are more suited to the target market when planning and providing services.

[0270] The processing flow will be explained below.

[0271] Step 1:

[0272] The user inputs service information. Specifically, the user uses the interface on the device to input details about the service they plan to provide (e.g., "urban luxury bicycle rental service," "target market: urban areas," "age range: 20-35 years old," "usage frequency: mostly on weekends").

[0273] Step 2:

[0274] The server receives the input service information. Specifically, the server converts the information sent by the user into an analyzable data format and stores it in a database.

[0275] Step 3:

[0276] The server analyzes the input data. Specifically, the server analyzes the received service information and extracts relevant data points (e.g., age group, region, interests, etc.). This process uses natural language processing technology.

[0277] Step 4:

[0278] The emotion engine recognizes the user's emotions. Specifically, when the user enters service information, emotional data is collected and analyzed from facial expressions and tone of voice using sensors such as the camera and microphone installed on the device.

[0279] Step 5:

[0280] The server launches the generative AI model, which inputs the analyzed data points and emotional data into the AI ​​model to generate multiple persona candidates. The generated persona takes the emotional data into account and matches the user's emotional state.

[0281] Step 6:

[0282] The server presents the generated persona proposals to the user. Specifically, the server visually displays multiple generated personas (e.g., "30-year-old male, engineer living in the city, commutes by bicycle" and "33-year-old female, marketing, goes to the gym on weekday evenings") on the user's device.

[0283] Step 7:

[0284] The user selects the most suitable persona from the presented persona list and sends the selection result to the server. At this time, the emotion engine evaluates the user's preferences in real time and collects emotional data during the selection process as feedback.

[0285] Step 8:

[0286] The server saves the selected persona information. Specifically, the server stores the user-selected persona data in a database and uses it for future service planning. It also receives feedback from users and uses it as further training data for the generative AI model.

[0287] This series of processing steps allows users to efficiently create realistic and useful personas while eliminating bias. Using the emotion engine, more accurate personas are generated that take into account the user's emotional state, improving the quality and suitability of services.

[0288] Example 2

[0289] 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."

[0290] Conventional persona generation systems have typically generated personas simply based on service information entered by users. This does not take into account the user's emotional state, and the generated personas often do not reflect the user's true needs or emotions. This has led to problems such as services provided and marketing strategies not being optimized for the target market.

[0291] 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.

[0292] In this invention, the server includes means for a user to input information about a service, means for analyzing the input service information and extracting relevant data points, means for analyzing the emotional state of the user at the time of input, means for using an artificial intelligence model based on the extracted data points and emotional data to generate multiple persona proposals, means for presenting the generated persona proposals to the user, and means for saving the persona proposal selected by the user and processing feedback, thereby enabling the generation of more realistic and useful personas that take the user's emotions into consideration.

[0293] "Service-related information" is data about the details of the service that the user wishes to provide.

[0294] The "means for inputting" is an interface that allows a user to input information about a service into the system.

[0295] "Means for analysis" refers to the process or technology for analyzing input service information and converting it into structured data.

[0296] "Relevant data points" are data items extracted from the entered service information that are necessary for analysis, such as age group, region, and interests.

[0297] The "emotional state" refers to the emotional or psychological state of the user when inputting service information.

[0298] "Means of analysis (emotional state)" refers to the techniques and processes for analyzing the user's emotional state from their input data and behavior.

[0299] "Artificial Intelligence Model" refers to an AI algorithm and trained model for generating personas based on user input data and emotional data.

[0300] A "persona proposal" is a human figure created to virtually represent the target market or user group of a service.

[0301] "Presentation means" refers to the interface or technology used to visually display the generated persona proposal to the user.

[0302] The "means of selection" is an interface that allows the user to choose the most suitable persona from the presented persona proposals.

[0303] "Storage methods" are techniques and processes for long-term storage of user-selected persona proposals.

[0304] "Feedback processing means" are techniques and processes that collect emotional data based on user choices and use it to improve the system.

[0305] This invention is a system that recognizes user emotions and generates personas that take these emotions into consideration. The purpose of this system is to execute a series of processes: generate multiple personas based on emotion data from detailed service information input, present them to the user, and finally collect user preferences as feedback.

[0306] Overview of program processing

[0307] 1. User enters service details

[0308] The user uses a terminal to input detailed information about the service they wish to provide. For example, if a user wants to provide a "luxury urban bicycle rental service," they would input specific information such as "target market: urban areas, age group: 20-35 years old, frequency of use: mostly on weekends." This becomes the basic data entered into the system.

[0309] 2. The server receives the input data

[0310] The server receives the service information entered by the user and parses it into structured data using a database management system or data analysis tool. In a specific step, the entered data is converted into JSON format and data points (e.g., age group, region, interests, etc.) are extracted.

[0311] 3. Recognize user emotions using an emotion engine

[0312] The emotion engine analyzes the user's emotional state when they input text. This analysis uses natural language processing (NLP) technology and emotion analysis tools. For example, the emotion engine (for example, Microsoft Azure text analysis API) can be used to recognize the user's emotional state based on the text they input and their behavioral patterns.

[0313] 4. The server launches the generative AI model

[0314] The server launches a pre-trained generative AI model, which inputs the analyzed data points and emotional data to generate several persona candidates. This process uses deep learning frameworks such as TensorFlow and PyTorch.

[0315] 5. The server presents the generated persona to the user.

[0316] The server presents multiple persona proposals generated by the generative AI to the user. For presentation, a web application front-end framework (e.g., React or Vue.js) is used to display the persona proposals to the user through a UI. Specific examples include the following persona proposals:

[0317] "30-year-old male, engineer living in a city, bicycle commuter"

[0318] "33-year-old woman, marketing manager, goes to the gym on weekday evenings"

[0319] 6. Users choose the persona that best suits them

[0320] Users select the most suitable persona from a list of multiple personas. As the user makes their selection, the emotion engine evaluates them in real time and collects emotional data, allowing for a more detailed understanding of the user's true needs and emotions.

[0321] 7. The server stores the persona information

[0322] The server stores the persona information selected by the user in a database. It also receives user feedback and uses it as training data for the generative AI model. The database can be an SQL-based database (e.g., MySQL or PostgreSQL) or a NoSQL database (e.g., MongoDB or Firebase).

[0323] Specific examples

[0324] As a concrete example, we will describe in detail the case of a user who wants to provide an "urban luxury bicycle rental service."

[0325] 1. The user uses the terminal to enter the service details: "Target market: urban areas", "Age range: 20-35 years old", "Frequency of use: mostly on weekends".

[0326] 2. The server receives and analyzes the input data, extracting data points such as demographics, geography, and interests.

[0327] 3. The emotion engine recognizes the user's emotions and analyzes the data, such as excitement, interest, and doubt.

[0328] 4. The server launches the generation AI to generate persona proposals, such as "a 30-year-old male engineer who lives in the city and commutes by bicycle" or "a 33-year-old female in marketing who goes to the gym on weekday evenings."

[0329] 5. The server presents the generated persona proposal to the user. The persona proposal is displayed through the UI.

[0330] 6. User selects a persona. Emotional data is collected based on user preferences.

[0331] 7. The server stores the persona information and collects feedback. The selected persona is stored in a database and used as training data for the generative AI.

[0332] In this way, the system can generate more accurate personas that take user emotions into account, making it easier to formulate strategies suited to target markets when planning and providing services.

[0333] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0334] Step 1:

[0335] The user inputs detailed information about the service they wish to provide through their terminal. Specifically, they input information such as "target market: urban areas," "age group: 20-35 years old," and "frequency of use: mostly on weekends." This information is sent to the server as basic data for subsequent processing. Input data: detailed service information. Output data: service information as basic data.

[0336] Step 2:

[0337] The server receives the service information entered by the user and analyzes it as structured data. Specifically, it uses a database management system (DBMS) and data analysis tools to convert the received data into JSON format and extract data points (e.g., age group, region, interests, etc.). Input data: Service details information. Output data: Structured data and extracted data points.

[0338] Step 3:

[0339] The emotion engine analyzes the user's emotional state at the time of input. Analysis is performed using natural language processing (NLP) technology and emotion analysis tools based on the user's input text and reaction data. For example, the Microsoft Azure text analysis API is used to recognize the user's emotional state (excitement, interest, suspicion, etc.). Input data: User's input text and reaction data. Output data: Analyzed emotion data.

[0340] Step 4:

[0341] The server launches a pre-trained generative AI model. The server inputs the analyzed data points and emotion data into the generative AI model to generate several persona candidates. This process uses a deep learning framework (such as TensorFlow or PyTorch). Input data: structured data and emotion data. Output data: generated persona candidates.

[0342] Step 5:

[0343] The server presents the generated multiple persona proposals to the user. Specifically, the persona proposals are visually displayed to the user through a UI using a web application front-end framework (such as React or Vue.js). For example, persona proposals such as "30-year-old male, engineer living in the city, commutes by bicycle" and "33-year-old female, marketing staff, goes to the gym on weekday evenings" are presented. Input data: Generated persona proposals. Output data: Persona proposals presented to the user.

[0344] Step 6:

[0345] The user selects the persona they consider most suitable from the presented options. As the user makes their selection, the emotion engine evaluates it in real time and collects emotional data. This allows for a detailed understanding of the user's true needs and emotions. Input data: User's selection of persona options. Output data: Optimal persona selection results and emotional feedback data.

[0346] Step 7:

[0347] The server saves the persona information selected by the user in a database and collects feedback from the user. The saved data is used as training data for the generative AI model in subsequent persona generation attempts, improving the accuracy of the model. The database used is an SQL-based database (e.g., MySQL or PostgreSQL) or a NoSQL database (e.g., MongoDB or Firebase). Input data: User-selected persona information and feedback data. Output data: Saved persona information and updated AI model.

[0348] (Application example 2)

[0349] 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."

[0350] Conventional persona generation systems generate personas based on static data without considering user emotions. As a result, the generated personas may not reflect the user's actual emotions and preferences, limiting the effectiveness of targeting and marketing strategies. Furthermore, to maximize the effectiveness of advertising campaigns, it is necessary to consider user emotions and preferences in the persona generation process, but no such means have been provided.

[0351] 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.

[0352] In this invention, the server includes means for a user to input information about a service, means for analyzing the input service information and extracting related data points, means for generating a plurality of persona proposals using an artificial intelligence model based on the extracted data points, means for presenting the generated persona proposals to the user, means for analyzing user emotion data in real time and reflecting the analysis result in the persona generation process, means for saving the persona proposal selected by the user and processing feedback, and means for performing ad targeting and delivering ad campaigns based on the generated persona proposals, thereby enabling real-time persona generation and targeting that reflects user emotions.

[0353] "Service Information" means details of the services you intend to provide, including your overall goals, target market, and product or service features.

[0354] "Means for analyzing the entered service information and extracting relevant data points" refers to the process of processing and analyzing the service information entered by the user to extract useful data points (e.g., age group, region, interests, etc.).

[0355] "Means for generating multiple persona proposals using an artificial intelligence model" refers to a technical means for generating multiple personas using AI technology based on extracted data points.

[0356] The "means for presenting the generated persona proposals to the user" is a technical process for presenting the generated multiple personas to the user visually or through an interface.

[0357] "Means for analyzing user emotional data in real time and reflecting it in the persona generation process" refers to a technical process for analyzing the emotional state of the user when entering service information and reflecting it in persona generation in real time.

[0358] "Means for storing user-selected persona proposals and processing feedback" refers to the technical means for storing user-selected persona proposals in a database and collecting and processing feedback from users.

[0359] "Means for targeting advertisements and delivering advertising campaigns based on the generated persona proposals" means the technical means for targeting advertisement campaigns and delivering the advertisements based on the generated personas.

[0360] The present invention is a system that recognizes user emotions and generates personas that take those emotions into account, thereby improving the targeting accuracy of advertising campaigns and enabling more effective marketing strategies.

[0361] System Overview

[0362] The system consists of the following major hardware and software components:

[0363] User devices: smartphones, tablets, etc.

[0364] Server: Data processing and persona generation

[0365] Emotion Engine: Software that analyzes user emotion data in real time

[0366] Generative AI model: Artificial intelligence that generates personas based on analytical data

[0367] Program processing

[0368] 1. Input on the user's terminal

[0369] Users use their smartphones or tablets to enter detailed information about the services they wish to offer, including, for example, the target market, product features, age group, and advertising objectives.

[0370] 2. Analysis by emotion engine

[0371] When a user inputs information, the device uses an emotion engine to collect real-time emotional data from the user, which is derived from facial expression analysis, voice analysis, touch speed, and other factors.

[0372] 3. Data processing and analysis on the server

[0373] The server receives the service information and emotion data entered by the user, converts it into structured data, and analyzes it. The extracted data points (e.g., age group, region, interests, etc.) become the basis for generating personas.

[0374] 4. Persona generation using generative AI models

[0375] The server then runs a generative AI model to generate multiple personas by inputting the analyzed data points and emotional data. The model generates personas taking the emotional data into account, providing a more realistic and useful portrayal of the target.

[0376] 5. Persona Presentation and Selection

[0377] The generated personas are presented to the user via their device, and the user can select the persona they think is most suitable. During this process, emotional data is analyzed and used as feedback.

[0378] 6. Persona-Based Ad Targeting

[0379] Based on the selected personas, advertising campaigns are designed and targeted. The ads are then linked to the appropriate distribution platforms and distributed. This targeting process allows for sophisticated strategies that reflect user sentiment.

[0380] 7. Gather feedback and refine the model

[0381] After the ad is delivered, user response data is collected and used as training data for the generative AI model, which will improve the accuracy of future persona generation.

[0382] Specific examples

[0383] Example: Advertising campaign for luxury urban bicycles

[0384] Step 1: The user enters information such as "Target market: urban areas," "Age group: 20-35 years old," and "Advertising purpose: brand awareness" into their smartphone.

[0385] Step 2: The device's emotion engine analyzes the emotion data entered by the user in real time.

[0386] Step 3: The server receives the information, converts it into structured data, and parses it.

[0387] Step 4: The generative AI model generates multiple personas based on the data.

[0388] Step 5: The generated personas are presented to the user, who then selects the most appropriate one.

[0389] Step 6: Ad targeting is performed based on the selected persona, and the actual ad campaign is delivered.

[0390] Prompt Sentence Examples

[0391] "Enter your advertising campaign information. Enter the data advertisers need for customer targeting. We also collect sentiment data in real time and generate multiple personas based on this. For example, the target audience for the "Premium Bicycle" advertising campaign is urban users aged 20-35. Based on this information, we generate appropriate personas and collect feedback."

[0392] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0393] Step 1:

[0394] Users input information about the services they wish to provide from their terminals. This information includes the target market, age group, advertising objectives, product features, etc. This information becomes the basic data for the entire system.

[0395] Input: Service information such as target market, age group, advertising purpose, product features, etc.

[0396] Output: Raw data entered by the user

[0397] Step 2:

[0398] The device sends the entered service information to the server. At the same time, the device's emotion engine analyzes the user's emotional data (facial expressions, voice, touch operation speed, etc.) in real time and sends this emotional data to the server.

[0399] Input: User service information, real-time emotion data

[0400] Output: Data points and sentiment data sent to the server

[0401] Step 3:

[0402] The server converts the received service information and emotional data into structured data and analyzes it. At this stage, data points such as target market, age group, and product features are extracted. Emotional data is also analyzed and integrated as information necessary for persona generation.

[0403] Input: Service information, raw emotion data

[0404] Output: Structured data points and parsed sentiment data

[0405] Step 4:

[0406] The server launches a generative AI model, inputting the analyzed data points and emotional data. The generative AI model generates multiple personas based on this data. This persona generation takes into account the user's emotional data to create a more specific target image.

[0407] Input: Structured data points, parsed sentiment data

[0408] Output: Multiple persona ideas generated

[0409] Step 5:

[0410] The generated persona proposals are sent from the server to the device, which then presents them to the user. The user can then select the most suitable persona, and this selection process is also analyzed by the emotion engine, with the results being fed back to the server.

[0411] Input: Generated persona ideas

[0412] Output: Persona proposals selected by the user and emotional data at the time of preference

[0413] Step 6:

[0414] The server stores the persona choices selected by the user and uses this information to target ads. An ad campaign is then set up and delivered to the target market. After the ad is delivered, user response data is also collected.

[0415] Input: Persona proposal selected by the user, emotional data at the time of preference

[0416] Output: Stored persona data, ad targeting information, and post-delivery response data

[0417] Step 7:

[0418] The server generates feedback based on the collected reaction data and uses this feedback information as training data for the generative AI model, thereby improving the accuracy of future persona generation.

[0419] Input: Post-distribution reaction data

[0420] Output: Updated training data, improved AI model

[0421] 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.

[0422] 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.

[0423] 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.

[0424] [Second embodiment]

[0425] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0426] 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.

[0427] 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).

[0428] 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.

[0429] 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.

[0430] 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).

[0431] 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.

[0432] 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.

[0433] 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.

[0434] 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.

[0435] 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.

[0436] 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."

[0437] System Overview

[0438] The present invention is a system that allows service planners to create effective personas while eliminating bias. This system involves a series of processes: inputting information about a service, generating multiple personas using artificial intelligence to overcome human biases and limitations, and presenting, selecting, and saving them to the user.

[0439] Explaining the program's processing

[0440] 1. The user enters the service details into the system

[0441] The user inputs detailed information about the service they wish to provide through the terminal. For example, if a user wants to provide a "luxury urban bicycle rental service," they would input details such as "target market: urban areas, age group: 20-35 years old, frequency of use: mostly on weekends." This information will be the basis for subsequent processing.

[0442] 2. The server processes the input data

[0443] The server receives the service information and parses it into structured data. Specifically, it converts the data into a format such as JSON and extracts relevant data points (e.g., age group, region, interests, etc.). The data obtained from this analysis process becomes the input for generating personas.

[0444] 3. The server starts the generated AI

[0445] The server runs a pre-trained generative AI model, which inputs the analyzed data points and generates multiple persona proposals. The personas generated are a combination of demographics (age, gender, occupation, etc.) and psychographics (interests, values, behavioral patterns, etc.).

[0446] 4. The server presents the persona proposal to the user

[0447] The server presents the user with multiple persona ideas generated by the generative AI, including detailed information such as "30-year-old male, engineer living in the city, bicycle commuter" and "33-year-old female, marketing, gym-goer on weekday evenings."

[0448] 5. Users choose the persona that best suits them

[0449] Users can select the persona they think is most suitable from the presented persona list. For example, they can choose the persona "33-year-old female, marketing staff, uses bicycle to go to the gym on weekday evenings."

[0450] 6. The server stores the persona information

[0451] The server stores the persona information selected by the user in a database and receives feedback provided by the user, which is used as training data for the AI ​​to improve the accuracy of future persona generation.

[0452] Specific examples

[0453] As a specific example, the case of a user who wishes to provide an "urban luxury bicycle rental service" will be described.

[0454] 1. The user enters details about the service: "Target market: urban areas," "Age range: 20-35 years old," "Frequency of use: mostly on weekends," etc.

[0455] 2. The server analyzes the input data: extracting data points such as "age group," "region," and "interests."

[0456] 3. The server launches the generation AI: The AI ​​generates persona proposals based on the extracted data.

[0457] 4. The server presents persona options: Multiple persona options (e.g., a 30-year-old male engineer living in an urban area who commutes by bicycle).

[0458] 5. User selects persona: A persona that fits (e.g., 33-year-old female, marketing).

[0459] 6. Server saves persona information: The selected persona is saved in the database and feedback is collected.

[0460] In this way, the present invention allows users to input the details of the service, and the server uses generation AI to generate and present a detailed persona, eliminating bias and efficiently forming personas, which enables the provision of better services.

[0461] The processing flow will be explained below.

[0462] Step 1:

[0463] The user inputs service information. Specifically, the user uses the interface on the device to input details about the service they plan to provide (e.g., "urban luxury bicycle rental service," "target market: urban areas," "age range: 20-35 years old," "usage frequency: mostly on weekends").

[0464] Step 2:

[0465] The server receives the input service information. Specifically, the server converts the information sent by the user into an analyzable data format and stores it in a database.

[0466] Step 3:

[0467] The server analyzes the input data. Specifically, the server analyzes the received service information and extracts relevant data points (e.g., age group, region, interests, etc.). This process uses natural language processing technology.

[0468] Step 4:

[0469] The server launches a generative AI model, which inputs the extracted data points into the model to generate persona suggestions. This AI model is pre-trained to generate multiple detailed personas based on the input data.

[0470] Step 5:

[0471] The server presents the generated persona proposals to the user. Specifically, the server visually displays multiple generated personas (e.g., "30-year-old male, engineer living in the city, bicycle commuter" and "33-year-old female, marketing, gym-goer on weekday evenings") on the user's device.

[0472] Step 6:

[0473] The user selects the most suitable persona. Specifically, the user selects the most suitable persona from the presented persona list and sends the selection result to the server.

[0474] Step 7:

[0475] The server saves the selected persona information. Specifically, the server stores the user-selected persona data in a database and uses it for future service planning. It also receives feedback from users and uses it as further training data for the generative AI model.

[0476] This series of processing steps allows users to efficiently create realistic and useful personas while eliminating bias, which will enable them to develop strategies that are more suited to the target market when planning and providing services.

[0477] Example 1

[0478] 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."

[0479] Traditional service design tends to rely on the biases and experiences of individuals in charge, making it difficult to generate objective and effective personas. Furthermore, there is often a lack of mechanisms for properly storing the personas and incorporating feedback. This creates challenges that make it difficult to maximize the effectiveness of services.

[0480] 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.

[0481] In this invention, the server includes means for a user to input information about a service, means for converting the input service information into structured data and analyzing it, means for using a generative AI model to generate multiple persona proposals based on the analyzed data points, means for presenting the generated persona proposals to the user, and means for saving the persona proposal selected by the user and processing feedback, thereby eliminating bias and enabling objective and effective persona generation, and further enabling continuous improvement of the service by incorporating feedback.

[0482] "Information about the service" refers to data such as details of the service provided by the user, target market, age group, frequency of use, etc.

[0483] "Structured data" is data that is organized in a certain format that is easy to analyze and process. Examples include JSON and CSV formats.

[0484] "Analysis" is the process of converting input data into an understandable format and extracting the necessary information.

[0485] A "data point" is an individual unit of information extracted from analyzed data, and includes information such as age group, region, and interests.

[0486] A "generative AI model" is a model that has been trained using artificial intelligence (AI) technology and is an algorithm that generates new information based on input data.

[0487] A "persona proposal" is a virtual user profile created by a generative AI model, combining demographic and psychographic information.

[0488] "Presentation" is the process of showing the generated persona proposals to the user, allowing the user to evaluate and select a persona.

[0489] "Saving" means recording the selected persona and related data in a storage device such as a database.

[0490] "Feedback" refers to evaluations and opinions provided by users, and is data used to improve generative AI models and optimize services.

[0491] A "system" is an integrated technology collection that combines the above means to carry out a series of processes.

[0492] System configuration

[0493] This invention is a system that allows service planners to create effective personas while eliminating bias. This system uses a generative AI model to generate multiple persona proposals based on service information entered by the user, and includes a series of processes for presenting, selecting, and saving the personas to the user.

[0494] Hardware and Software

[0495] The system consists of the following hardware and software:

[0496] Server: Receives data, analyzes it, launches the generated AI model, generates personas, and stores data. In this invention, a general web server (e.g., Apache) can be used.

[0497] Terminal: A device on which users input service information and view and select generated personas. A general PC or smartphone can be used.

[0498] Generative AI model: An artificial intelligence model that generates personas based on data entered by users. A specific example would be a natural language processing model such as GPT-4.

[0499] Operational Overview

[0500] Entering Service Information

[0501] Users use their own devices to input service details. The information input includes the name of the service, the target market, the expected age group, and frequency of use. For example, if a user wants to provide a "luxury urban bicycle rental service," they would input information such as "target market: urban areas, age group: 20-35 years old, frequency of use: mostly on weekends."

[0502] Data transmission and analysis

[0503] The device sends the entered data to a server, which converts it into structured data, such as JSON format, and extracts relevant data points, such as age group, location, and interests, facilitating subsequent data analysis.

[0504] Launching the generative AI model and generating personas

[0505] The server then runs a trained generative AI model and inputs the extracted data points to generate multiple personas, each of which includes demographic and psychographic information, providing an unbiased, objective portrayal of the user.

[0506] Persona Presentation and Selection

[0507] The server sends the generated persona proposals to the user's device, allowing the user to view and select the most suitable one from the presented persona list.

[0508] Data storage and feedback processing

[0509] The persona ideas selected by the user are stored in a database by the server, and user feedback is also collected to help improve the accuracy of future persona generation.

[0510] Specific examples

[0511] As a specific example, the procedure when a user wants to provide an "urban luxury bicycle rental service" will be shown.

[0512] Example of a prompt for user input:

[0513] "The target market is urban areas. The age range is 20-35, and usage is mostly on weekends."

[0514] Example of a server-generated persona:

[0515] 30-year-old male, engineer living in a city, commutes to work by bicycle on weekends

[0516] 33-year-old woman, marketing manager, weekday evening gym goer

[0517] In this way, users can efficiently generate and select personas targeted at specific markets and improve the quality of their services by obtaining appropriate feedback, thereby eliminating user bias and enabling objective and effective service design.

[0518] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0519] Step 1:

[0520] User enters service details

[0521] Users use their own devices to input detailed information about the service they wish to provide. Specifically, they input information such as the name of the service, target market, age group, and frequency of use into a form. Examples of information that can be input include "target market: urban areas," "age group: 20-35 years old," and "frequency of use: mostly on weekends."

[0522] Input and Output

[0523] Input: Service details

[0524] Output: Structured JSON format data

[0525] Specific actions

[0526] The user enters service information into an input form on the device.

[0527] After completing the input, press the submit button and the form data will be converted to JSON format.

[0528] Step 2:

[0529] The device sends the input data to the server

[0530] The user's device sends the input data to the server as structured data (JSON format), using HTTPS as the communication protocol.

[0531] Input and Output

[0532] Input: Structured JSON format data

[0533] Output: HTTP request to the server

[0534] Specific actions

[0535] The terminal converts the input data into JSON format.

[0536] When the submit button is pressed, an HTTP POST request is sent to the server.

[0537] Step 3:

[0538] The server receives and analyzes the input data

[0539] The server parses the received data, specifically the JSON format data, and extracts the necessary data points (e.g., age group, region, interests).

[0540] Input and Output

[0541] Input: Received JSON format data

[0542] Output: Extracted data points

[0543] Specific actions

[0544] Parse the JSON data received by the server.

[0545] Data points such as "age group," "region," and "interests" are extracted and stored in internal memory.

[0546] Step 4:

[0547] The server starts the generation AI and generates a persona.

[0548] The server then launches the trained generative AI model, inputting the extracted data points to generate multiple persona suggestions.

[0549] Input and Output

[0550] Input: Data points

[0551] Output: Multiple persona ideas generated

[0552] Specific actions

[0553] The server launches a generative AI model (e.g., GPT-4).

[0554] The extracted data points are input into a generative AI model.

[0555] The generative AI model generates multiple persona ideas and stores them in memory.

[0556] Step 5:

[0557] The server presents the generated persona ideas to the user

[0558] The server sends the generated persona proposals to the user's device, allowing the user to view and select from them.

[0559] Input and Output

[0560] Input: Multiple persona ideas generated

[0561] Output: Data presented to the user's device

[0562] Specific actions

[0563] The server sends the generated persona proposal to the user's device.

[0564] Display a list of personas on the user's device.

[0565] Step 6:

[0566] User selects persona

[0567] The user selects the most suitable persona from the presented persona list and sends the selection to the server.

[0568] Input and Output

[0569] Input: Personalist

[0570] Output: Data for selected personas

[0571] Specific actions

[0572] Users can view the persona list on their device and select the most suitable persona.

[0573] The data of the selected persona is sent to the server.

[0574] Step 7:

[0575] The server stores the selected persona information and processes the feedback

[0576] The server stores the user-selected persona information in a database and also collects user feedback to use as training data for the generative AI model.

[0577] Input and Output

[0578] Input: Selected persona information, feedback

[0579] Output: Saved persona information, updated generative AI model

[0580] Specific actions

[0581] The server stores the selected persona information in a database.

[0582] Collect user feedback and use it to improve generative AI models.

[0583] (Application example 1)

[0584] 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."

[0585] In conventional advertising campaigns, the creation of targeting personas often relies on the subjectivity and bias of marketers, which can lead to a high risk of missing the right target demographic. Another issue is that the persona creation process is time-consuming and inefficient. Therefore, there is a demand for a system that can eliminate bias and quickly and effectively generate multiple persona proposals.

[0586] 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.

[0587] In this invention, the server includes means for a user to input information about a service, means for analyzing the input service information and extracting relevant data points, means for using an artificial intelligence model to generate multiple persona proposals based on the extracted data points, means for presenting the generated persona proposals to the user, means for saving the persona proposals selected by the user and processing feedback, means for presenting the persona proposals generated by the analysis data to a smartphone application, and means for saving the persona proposals selected by the user in a cloud database. This makes it possible to quickly generate effective persona proposals that are free from bias and improve the targeting of advertising campaigns.

[0588] "Service" refers to the products or actions provided, and is an activity that provides value to users.

[0589] "Information" is a collection of data or knowledge that can be used for a specific purpose.

[0590] "User" refers to any individual or entity that uses the System or Services.

[0591] "Means" refers to a method or device for achieving a particular purpose.

[0592] "Input" refers to the act of taking data into the system from outside.

[0593] "Analysis" is the process of breaking down input data into an understandable form.

[0594] "Relevant data points" refer to elements of data that are important for analysis.

[0595] "Extraction" is the act of extracting the necessary information from a data set.

[0596] An "artificial intelligence model" refers to a combination of algorithms designed to perform a specific task using machine learning or deep learning.

[0597] A "persona" is a concrete representation of a specific typical customer, a virtual person who is the target of a service or advertisement.

[0598] "Generation" is the act of creating new data or information according to predetermined rules or algorithms.

[0599] "Presenting" is the act of displaying or providing information to a user.

[0600] "Selection" is the act of choosing a specific option from multiple options.

[0601] "Storage" is the act of keeping data in a usable state for a long period of time.

[0602] "Feedback" refers to the reaction or information obtained as a result of an action or operation.

[0603] "Processing" is the act of manipulating or transforming input information to make it suitable for a purpose.

[0604] "Smartphone application" refers to a software program that runs on a smartphone.

[0605] "Cloud database" refers to a collection of digital information stored on remote servers accessible via the internet.

[0606] The present invention provides a system for quickly generating target personas for advertising campaigns with high accuracy, which involves a process in which a user inputs information about a service through a smartphone application, and the information is analyzed to generate a persona.

[0607] System configuration

[0608] 1. User input:

[0609] Using a smartphone application, users enter details of the services they wish to offer, such as the objectives of their advertising campaign, their target market, age group, and interests.

[0610] 2. Data Analysis Methods:

[0611] The server receives the input information and converts it into structured data such as JSON format using the Python json library.

[0612] Extract relevant data points (e.g., age, gender, location, interests) from structured data.

[0613] 3. Using generative AI models:

[0614] The server runs a pre-trained generative AI model that generates multiple persona suggestions from the extracted data points based on a specific algorithm.

[0615] 4. How to present persona ideas:

[0616] The server presents the generated persona proposal to the user's smartphone application. For example, the proposed persona displays detailed information such as "25-year-old male, freelance designer, online shopping on weekday evenings."

[0617] 5. User Choice:

[0618] The user selects the persona that they think is most suitable from the persona proposals presented.

[0619] 6. How persona information is stored:

[0620] The selected personas are saved in a cloud database, which ensures data persistence.

[0621] Specific examples

[0622] Consider a case where a user wants to run an advertising campaign. For example, the user uses the system in the following steps:

[0623] Example of input prompt:

[0624] Product Category: High-end fashion

[0625] Target market: Big cities

[0626] Campaign Objective: Increase brand awareness

[0627] Age range: 20-35

[0628] Examples of generated persona ideas:

[0629] 1. 25-year-old male, freelance designer, online shopping on weekday evenings

[0630] 2. A 28-year-old woman, a marketing manager, visits the mall on weekends.

[0631] Users can select a persona and store it in a cloud database for efficient targeting of advertising campaigns. This system is a powerful tool for eliminating bias and providing scientifically based targeting strategies.

[0632] The specific hardware and software used include smartphones, cloud servers, and computing resources for running AI models (e.g., servers with GPUs). The software is based on Python, and the AI ​​model uses deep learning libraries such as TensorFlow and PyTorch.

[0633] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0634] Step 1:

[0635] Users enter service details for their advertising campaigns through a smartphone application, including product category, target market, campaign objectives, age group, etc. This information is the initial input data for the system.

[0636] Step 2:

[0637] The device (smartphone) receives the input information and sends it to the server, which converts it into structured data such as JSON. For example, the Python json library can be used to parse the input data and extract relevant data points (such as age, gender, region, and interests).

[0638] Step 3:

[0639] The server then launches a pre-trained generative AI model based on the analyzed data points. The generative AI model is built using deep learning libraries such as TensorFlow and PyTorch. The AI ​​model takes the analyzed data as input and generates persona suggestions. The output is a set of detailed personas.

[0640] Step 4:

[0641] The server sends the generated persona proposals to a smartphone application and presents them to the user. The user can check multiple persona proposals on the smartphone screen. For example, persona information such as "25-year-old male, freelance designer, online shopping on weekday evenings" is displayed.

[0642] Step 5:

[0643] The user selects the persona they think is most suitable from the proposed personas. The selected persona is sent from the device to the server. The user's selection is transmitted to the server as feedback and used to improve the proposed persona.

[0644] Step 6:

[0645] The server stores the selected persona information in a cloud database, which is used for future advertising campaigns and system improvements. User feedback data is also used as training data for generative AI models.

[0646] This will enable more effective targeting in advertising campaigns, improve the accuracy of persona generation, and further strengthen marketing strategies by providing unbiased, scientific persona proposals quickly.

[0647] 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.

[0648] System Overview

[0649] The present invention is a system that recognizes a user's emotions and generates a persona that takes those emotions into consideration. This system involves a series of processes: inputting information about a service, analyzing the user's emotional state using an emotion engine, generating and presenting multiple personas, and evaluating the user's preferences in real time and providing feedback.

[0650] Explaining the program's processing

[0651] 1. The user enters the service details into the system

[0652] The user inputs detailed information about the service they wish to provide through the terminal. For example, if a user wants to provide a "luxury urban bicycle rental service," they would input details such as "target market: urban areas, age group: 20-35 years old, frequency of use: mostly on weekends." This information will be the basis for subsequent processing.

[0653] 2. The server processes the input data

[0654] The server receives the service information and parses it into structured data. Specifically, it converts the data into a format such as JSON and extracts relevant data points (e.g., age group, region, interests, etc.). The data obtained from this analysis process becomes the input for generating personas.

[0655] 3. Recognize user emotions using an emotion engine

[0656] When a user enters service information, the emotional state of the user is analyzed through the emotion engine. The emotional data obtained through this analysis will be an important factor in later persona generation.

[0657] 4. The server launches the generative AI model

[0658] The server launches a pre-trained generative AI model, which inputs the analyzed data points and emotional data into the AI ​​model, and the artificial intelligence generates multiple persona proposals. The AI ​​model aims to generate a more appropriate persona by taking the emotional data into account.

[0659] 5. The server presents the generated persona to the user.

[0660] The server presents the user with multiple persona ideas generated by the generative AI, including detailed information such as "30-year-old male, engineer living in the city, bicycle commuter" and "33-year-old female, marketing, gym-goer on weekday evenings."

[0661] 6. Users choose the persona that best suits them

[0662] The user selects the persona they think is most suitable from the presented persona list, and the emotion engine evaluates the user's preferences in real time and collects emotional data based on the selection results as feedback.

[0663] 7. The server stores the persona information

[0664] The server stores the persona information selected by the user in a database, and also receives feedback provided by the user, which is used as training data for the AI ​​generator to improve the accuracy of future persona generation.

[0665] Specific examples

[0666] As a specific example, the case of a user who wishes to provide an "urban luxury bicycle rental service" will be described.

[0667] 1. The user enters details about the service: "Target market: urban areas," "Age range: 20-35 years old," "Frequency of use: mostly on weekends," etc.

[0668] 2. The server analyzes the input data: extracting data points such as "age group," "region," and "interests."

[0669] 3. The emotion engine recognizes the user's emotions and analyzes the data.

[0670] 4. The server launches the generation AI: The AI ​​generates a persona proposal based on the extracted data and emotional data.

[0671] 5. The server presents the generated persona ideas: multiple persona ideas (e.g., a 30-year-old male engineer living in an urban area who commutes by bicycle).

[0672] 6. User selects persona: A persona that fits (e.g., 33-year-old female, marketing).

[0673] 7. Server saves persona information: The selected persona is saved in the database and feedback is collected.

[0674] In this way, the present invention allows users to input the details of a service, and the server uses AI to generate and present a detailed persona. Real-time evaluation incorporating the user's emotions is then performed, eliminating bias and efficiently creating realistic and useful personas. This allows for the formulation of strategies that are more suited to the target market when planning and providing services.

[0675] The processing flow will be explained below.

[0676] Step 1:

[0677] The user inputs service information. Specifically, the user uses the interface on the device to input details about the service they plan to provide (e.g., "urban luxury bicycle rental service," "target market: urban areas," "age range: 20-35 years old," "usage frequency: mostly on weekends").

[0678] Step 2:

[0679] The server receives the input service information. Specifically, the server converts the information sent by the user into an analyzable data format and stores it in a database.

[0680] Step 3:

[0681] The server analyzes the input data. Specifically, the server analyzes the received service information and extracts relevant data points (e.g., age group, region, interests, etc.). This process uses natural language processing technology.

[0682] Step 4:

[0683] The emotion engine recognizes the user's emotions. Specifically, when the user enters service information, emotional data is collected and analyzed from facial expressions and tone of voice using sensors such as the camera and microphone installed on the device.

[0684] Step 5:

[0685] The server launches the generative AI model, which inputs the analyzed data points and emotional data into the AI ​​model to generate multiple persona candidates. The generated persona takes the emotional data into account and matches the user's emotional state.

[0686] Step 6:

[0687] The server presents the generated persona proposals to the user. Specifically, the server visually displays multiple generated personas (e.g., "30-year-old male, engineer living in the city, commutes by bicycle" and "33-year-old female, marketing, goes to the gym on weekday evenings") on the user's device.

[0688] Step 7:

[0689] The user selects the most suitable persona from the presented persona list and sends the selection result to the server. At this time, the emotion engine evaluates the user's preferences in real time and collects emotional data during the selection process as feedback.

[0690] Step 8:

[0691] The server saves the selected persona information. Specifically, the server stores the user-selected persona data in a database and uses it for future service planning. It also receives feedback from users and uses it as further training data for the generative AI model.

[0692] This series of processing steps allows users to efficiently create realistic and useful personas while eliminating bias. Using the emotion engine, more accurate personas are generated that take into account the user's emotional state, improving the quality and suitability of services.

[0693] Example 2

[0694] 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."

[0695] Conventional persona generation systems have typically generated personas simply based on service information entered by users. This does not take into account the user's emotional state, and the generated personas often do not reflect the user's true needs or emotions. This has led to problems such as services provided and marketing strategies not being optimized for the target market.

[0696] 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.

[0697] In this invention, the server includes means for a user to input information about a service, means for analyzing the input service information and extracting relevant data points, means for analyzing the emotional state of the user at the time of input, means for using an artificial intelligence model based on the extracted data points and emotional data to generate multiple persona proposals, means for presenting the generated persona proposals to the user, and means for saving the persona proposal selected by the user and processing feedback, thereby enabling the generation of more realistic and useful personas that take the user's emotions into consideration.

[0698] "Service-related information" is data about the details of the service that the user wishes to provide.

[0699] The "means for inputting" is an interface that allows a user to input information about a service into the system.

[0700] "Means for analysis" refers to the process or technology for analyzing input service information and converting it into structured data.

[0701] "Relevant data points" are data items extracted from the entered service information that are necessary for analysis, such as age group, region, and interests.

[0702] The "emotional state" refers to the emotional or psychological state of the user when inputting service information.

[0703] "Means of analysis (emotional state)" refers to the techniques and processes for analyzing the user's emotional state from their input data and behavior.

[0704] "Artificial Intelligence Model" refers to an AI algorithm and trained model for generating personas based on user input data and emotional data.

[0705] A "persona proposal" is a human figure created to virtually represent the target market or user group of a service.

[0706] "Presentation means" refers to the interface or technology used to visually display the generated persona proposal to the user.

[0707] The "means of selection" is an interface that allows the user to choose the most suitable persona from the presented persona proposals.

[0708] "Storage methods" are techniques and processes for long-term storage of user-selected persona proposals.

[0709] "Feedback processing means" are techniques and processes that collect emotional data based on user choices and use it to improve the system.

[0710] This invention is a system that recognizes user emotions and generates personas that take these emotions into consideration. The purpose of this system is to execute a series of processes: generate multiple personas based on emotion data from detailed service information input, present them to the user, and finally collect user preferences as feedback.

[0711] Overview of program processing

[0712] 1. User enters service details

[0713] The user uses a terminal to input detailed information about the service they wish to provide. For example, if a user wants to provide a "luxury urban bicycle rental service," they would input specific information such as "target market: urban areas, age group: 20-35 years old, frequency of use: mostly on weekends." This becomes the basic data entered into the system.

[0714] 2. The server receives the input data

[0715] The server receives the service information entered by the user and parses it into structured data using a database management system or data analysis tool. In a specific step, the entered data is converted into JSON format and data points (e.g., age group, region, interests, etc.) are extracted.

[0716] 3. Recognize user emotions using an emotion engine

[0717] The emotion engine analyzes the user's emotional state when they input text. This analysis uses natural language processing (NLP) technology and emotion analysis tools. For example, the emotion engine (for example, Microsoft Azure text analysis API) can be used to recognize the user's emotional state based on the text they input and their behavioral patterns.

[0718] 4. The server launches the generative AI model

[0719] The server launches a pre-trained generative AI model, which inputs the analyzed data points and emotional data to generate several persona candidates. This process uses deep learning frameworks such as TensorFlow and PyTorch.

[0720] 5. The server presents the generated persona to the user.

[0721] The server presents multiple persona proposals generated by the generative AI to the user. For presentation, a web application front-end framework (e.g., React or Vue.js) is used to display the persona proposals to the user through a UI. Specific examples include the following persona proposals:

[0722] "30-year-old male, engineer living in a city, bicycle commuter"

[0723] "33-year-old woman, marketing manager, goes to the gym on weekday evenings"

[0724] 6. Users choose the persona that best suits them

[0725] Users select the most suitable persona from a list of multiple personas. As the user makes their selection, the emotion engine evaluates them in real time and collects emotional data, allowing for a more detailed understanding of the user's true needs and emotions.

[0726] 7. The server stores the persona information

[0727] The server stores the persona information selected by the user in a database. It also receives user feedback and uses it as training data for the generative AI model. The database can be an SQL-based database (e.g., MySQL or PostgreSQL) or a NoSQL database (e.g., MongoDB or Firebase).

[0728] Specific examples

[0729] As a concrete example, we will describe in detail the case of a user who wants to provide an "urban luxury bicycle rental service."

[0730] 1. The user uses the terminal to enter the service details: "Target market: urban areas", "Age range: 20-35 years old", "Frequency of use: mostly on weekends".

[0731] 2. The server receives and analyzes the input data, extracting data points such as demographics, geography, and interests.

[0732] 3. The emotion engine recognizes the user's emotions and analyzes the data, such as excitement, interest, and doubt.

[0733] 4. The server launches the generation AI to generate persona proposals, such as "a 30-year-old male engineer who lives in the city and commutes by bicycle" or "a 33-year-old female in marketing who goes to the gym on weekday evenings."

[0734] 5. The server presents the generated persona proposal to the user. The persona proposal is displayed through the UI.

[0735] 6. User selects a persona. Emotional data is collected based on user preferences.

[0736] 7. The server stores the persona information and collects feedback. The selected persona is stored in a database and used as training data for the generative AI.

[0737] In this way, the system can generate more accurate personas that take user emotions into account, making it easier to formulate strategies suited to target markets when planning and providing services.

[0738] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0739] Step 1:

[0740] The user inputs detailed information about the service they wish to provide through their terminal. Specifically, they input information such as "target market: urban areas," "age group: 20-35 years old," and "frequency of use: mostly on weekends." This information is sent to the server as basic data for subsequent processing. Input data: detailed service information. Output data: service information as basic data.

[0741] Step 2:

[0742] The server receives the service information entered by the user and analyzes it as structured data. Specifically, it uses a database management system (DBMS) and data analysis tools to convert the received data into JSON format and extract data points (e.g., age group, region, interests, etc.). Input data: Service details information. Output data: Structured data and extracted data points.

[0743] Step 3:

[0744] The emotion engine analyzes the user's emotional state at the time of input. Analysis is performed using natural language processing (NLP) technology and emotion analysis tools based on the user's input text and reaction data. For example, the Microsoft Azure text analysis API is used to recognize the user's emotional state (excitement, interest, suspicion, etc.). Input data: User's input text and reaction data. Output data: Analyzed emotion data.

[0745] Step 4:

[0746] The server launches a pre-trained generative AI model. The server inputs the analyzed data points and emotion data into the generative AI model to generate several persona candidates. This process uses a deep learning framework (such as TensorFlow or PyTorch). Input data: structured data and emotion data. Output data: generated persona candidates.

[0747] Step 5:

[0748] The server presents the generated multiple persona proposals to the user. Specifically, the persona proposals are visually displayed to the user through a UI using a web application front-end framework (such as React or Vue.js). For example, persona proposals such as "30-year-old male, engineer living in the city, commutes by bicycle" and "33-year-old female, marketing staff, goes to the gym on weekday evenings" are presented. Input data: Generated persona proposals. Output data: Persona proposals presented to the user.

[0749] Step 6:

[0750] The user selects the persona they consider most suitable from the presented options. As the user makes their selection, the emotion engine evaluates it in real time and collects emotional data. This allows for a detailed understanding of the user's true needs and emotions. Input data: User's selection of persona options. Output data: Optimal persona selection results and emotional feedback data.

[0751] Step 7:

[0752] The server saves the persona information selected by the user in a database and collects feedback from the user. The saved data is used as training data for the generative AI model in subsequent persona generation attempts, improving the accuracy of the model. The database used is an SQL-based database (e.g., MySQL or PostgreSQL) or a NoSQL database (e.g., MongoDB or Firebase). Input data: User-selected persona information and feedback data. Output data: Saved persona information and updated AI model.

[0753] (Application example 2)

[0754] 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."

[0755] Conventional persona generation systems generate personas based on static data without considering user emotions. As a result, the generated personas may not reflect the user's actual emotions and preferences, limiting the effectiveness of targeting and marketing strategies. Furthermore, to maximize the effectiveness of advertising campaigns, it is necessary to consider user emotions and preferences in the persona generation process, but no such means have been provided.

[0756] 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.

[0757] In this invention, the server includes means for a user to input information about a service, means for analyzing the input service information and extracting related data points, means for generating a plurality of persona proposals using an artificial intelligence model based on the extracted data points, means for presenting the generated persona proposals to the user, means for analyzing user emotion data in real time and reflecting the analysis result in the persona generation process, means for saving the persona proposal selected by the user and processing feedback, and means for performing ad targeting and delivering ad campaigns based on the generated persona proposals, thereby enabling real-time persona generation and targeting that reflects user emotions.

[0758] "Service Information" means details of the services you intend to provide, including your overall goals, target market, and product or service features.

[0759] "Means for analyzing the entered service information and extracting relevant data points" refers to the process of processing and analyzing the service information entered by the user to extract useful data points (e.g., age group, region, interests, etc.).

[0760] "Means for generating multiple persona proposals using an artificial intelligence model" refers to a technical means for generating multiple personas using AI technology based on extracted data points.

[0761] The "means for presenting the generated persona proposals to the user" is a technical process for presenting the generated multiple personas to the user visually or through an interface.

[0762] "Means for analyzing user emotional data in real time and reflecting it in the persona generation process" refers to a technical process for analyzing the emotional state of the user when entering service information and reflecting it in persona generation in real time.

[0763] "Means for storing user-selected persona proposals and processing feedback" refers to the technical means for storing user-selected persona proposals in a database and collecting and processing feedback from users.

[0764] "Means for targeting advertisements and delivering advertising campaigns based on the generated persona proposals" means the technical means for targeting advertisement campaigns and delivering the advertisements based on the generated personas.

[0765] The present invention is a system that recognizes user emotions and generates personas that take those emotions into account, thereby improving the targeting accuracy of advertising campaigns and enabling more effective marketing strategies.

[0766] System Overview

[0767] The system consists of the following major hardware and software components:

[0768] User devices: smartphones, tablets, etc.

[0769] Server: Data processing and persona generation

[0770] Emotion Engine: Software that analyzes user emotion data in real time

[0771] Generative AI model: Artificial intelligence that generates personas based on analytical data

[0772] Program processing

[0773] 1. Input on the user's terminal

[0774] Users use their smartphones or tablets to enter detailed information about the services they wish to offer, including, for example, the target market, product features, age group, and advertising objectives.

[0775] 2. Analysis by emotion engine

[0776] When a user inputs information, the device uses an emotion engine to collect real-time emotional data from the user, which is derived from facial expression analysis, voice analysis, touch speed, and other factors.

[0777] 3. Data processing and analysis on the server

[0778] The server receives the service information and emotion data entered by the user, converts it into structured data, and analyzes it. The extracted data points (e.g., age group, region, interests, etc.) become the basis for generating personas.

[0779] 4. Persona generation using generative AI models

[0780] The server then runs a generative AI model to generate multiple personas by inputting the analyzed data points and emotional data. The model generates personas taking the emotional data into account, providing a more realistic and useful portrayal of the target.

[0781] 5. Persona Presentation and Selection

[0782] The generated personas are presented to the user via their device, and the user can select the persona they think is most suitable. During this process, emotional data is analyzed and used as feedback.

[0783] 6. Persona-Based Ad Targeting

[0784] Based on the selected personas, advertising campaigns are designed and targeted. The ads are then linked to the appropriate distribution platforms and distributed. This targeting process allows for sophisticated strategies that reflect user sentiment.

[0785] 7. Gather feedback and refine the model

[0786] After the ad is delivered, user response data is collected and used as training data for the generative AI model, which will improve the accuracy of future persona generation.

[0787] Specific examples

[0788] Example: Advertising campaign for luxury urban bicycles

[0789] Step 1: The user enters information such as "Target market: urban areas," "Age group: 20-35 years old," and "Advertising purpose: brand awareness" into their smartphone.

[0790] Step 2: The device's emotion engine analyzes the emotion data entered by the user in real time.

[0791] Step 3: The server receives the information, converts it into structured data, and parses it.

[0792] Step 4: The generative AI model generates multiple personas based on the data.

[0793] Step 5: The generated personas are presented to the user, who then selects the most appropriate one.

[0794] Step 6: Ad targeting is performed based on the selected persona, and the actual ad campaign is delivered.

[0795] Prompt Sentence Examples

[0796] "Enter your advertising campaign information. Enter the data advertisers need for customer targeting. We also collect sentiment data in real time and generate multiple personas based on this. For example, the target audience for the "Premium Bicycle" advertising campaign is urban users aged 20-35. Based on this information, we generate appropriate personas and collect feedback."

[0797] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0798] Step 1:

[0799] Users input information about the services they wish to provide from their terminals. This information includes the target market, age group, advertising objectives, product features, etc. This information becomes the basic data for the entire system.

[0800] Input: Service information such as target market, age group, advertising purpose, product features, etc.

[0801] Output: Raw data entered by the user

[0802] Step 2:

[0803] The device sends the entered service information to the server. At the same time, the device's emotion engine analyzes the user's emotional data (facial expressions, voice, touch operation speed, etc.) in real time and sends this emotional data to the server.

[0804] Input: User service information, real-time emotion data

[0805] Output: Data points and sentiment data sent to the server

[0806] Step 3:

[0807] The server converts the received service information and emotional data into structured data and analyzes it. At this stage, data points such as target market, age group, and product features are extracted. Emotional data is also analyzed and integrated as information necessary for persona generation.

[0808] Input: Service information, raw emotion data

[0809] Output: Structured data points and parsed sentiment data

[0810] Step 4:

[0811] The server launches a generative AI model, inputting the analyzed data points and emotional data. The generative AI model generates multiple personas based on this data. This persona generation takes into account the user's emotional data to create a more specific target image.

[0812] Input: Structured data points, parsed sentiment data

[0813] Output: Multiple persona ideas generated

[0814] Step 5:

[0815] The generated persona proposals are sent from the server to the device, which then presents them to the user. The user can then select the most suitable persona, and this selection process is also analyzed by the emotion engine, with the results being fed back to the server.

[0816] Input: Generated persona ideas

[0817] Output: Persona proposals selected by the user and emotional data at the time of preference

[0818] Step 6:

[0819] The server stores the persona choices selected by the user and uses this information to target ads. An ad campaign is then set up and delivered to the target market. After the ad is delivered, user response data is also collected.

[0820] Input: Persona proposal selected by the user, emotional data at the time of preference

[0821] Output: Stored persona data, ad targeting information, and post-delivery response data

[0822] Step 7:

[0823] The server generates feedback based on the collected reaction data and uses this feedback information as training data for the generative AI model, thereby improving the accuracy of future persona generation.

[0824] Input: Post-distribution reaction data

[0825] Output: Updated training data, improved AI model

[0826] 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.

[0827] 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.

[0828] 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.

[0829] [Third embodiment]

[0830] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0831] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0832] 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).

[0833] 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.

[0834] 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.

[0835] 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).

[0836] 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.

[0837] 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.

[0838] 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.

[0839] 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.

[0840] 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.

[0841] 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."

[0842] System Overview

[0843] The present invention is a system that allows service planners to create effective personas while eliminating bias. This system involves a series of processes: inputting information about a service, generating multiple personas using artificial intelligence to overcome human biases and limitations, and presenting, selecting, and saving them to the user.

[0844] Explaining the program's processing

[0845] 1. The user enters the service details into the system

[0846] The user inputs detailed information about the service they wish to provide through the terminal. For example, if a user wants to provide a "luxury urban bicycle rental service," they would input details such as "target market: urban areas, age group: 20-35 years old, frequency of use: mostly on weekends." This information will be the basis for subsequent processing.

[0847] 2. The server processes the input data

[0848] The server receives the service information and parses it into structured data. Specifically, it converts the data into a format such as JSON and extracts relevant data points (e.g., age group, region, interests, etc.). The data obtained from this analysis process becomes the input for generating personas.

[0849] 3. The server starts the generated AI

[0850] The server runs a pre-trained generative AI model, which inputs the analyzed data points and generates multiple persona proposals. The personas generated are a combination of demographics (age, gender, occupation, etc.) and psychographics (interests, values, behavioral patterns, etc.).

[0851] 4. The server presents the persona proposal to the user

[0852] The server presents the user with multiple persona ideas generated by the generative AI, including detailed information such as "30-year-old male, engineer living in the city, bicycle commuter" and "33-year-old female, marketing, gym-goer on weekday evenings."

[0853] 5. Users choose the persona that best suits them

[0854] Users can select the persona they think is most suitable from the presented persona list. For example, they can choose the persona "33-year-old female, marketing staff, uses bicycle to go to the gym on weekday evenings."

[0855] 6. The server stores the persona information

[0856] The server stores the persona information selected by the user in a database and receives feedback provided by the user, which is used as training data for the AI ​​to improve the accuracy of future persona generation.

[0857] Specific examples

[0858] As a specific example, the case of a user who wishes to provide an "urban luxury bicycle rental service" will be described.

[0859] 1. The user enters details about the service: "Target market: urban areas," "Age range: 20-35 years old," "Frequency of use: mostly on weekends," etc.

[0860] 2. The server analyzes the input data: extracting data points such as "age group," "region," and "interests."

[0861] 3. The server launches the generation AI: The AI ​​generates persona proposals based on the extracted data.

[0862] 4. The server presents persona options: Multiple persona options (e.g., a 30-year-old male engineer living in an urban area who commutes by bicycle).

[0863] 5. User selects persona: A persona that fits (e.g., 33-year-old female, marketing).

[0864] 6. Server saves persona information: The selected persona is saved in the database and feedback is collected.

[0865] In this way, the present invention allows users to input the details of the service, and the server uses generation AI to generate and present a detailed persona, eliminating bias and efficiently forming personas, which enables the provision of better services.

[0866] The processing flow will be explained below.

[0867] Step 1:

[0868] The user inputs service information. Specifically, the user uses the interface on the device to input details about the service they plan to provide (e.g., "urban luxury bicycle rental service," "target market: urban areas," "age range: 20-35 years old," "usage frequency: mostly on weekends").

[0869] Step 2:

[0870] The server receives the input service information. Specifically, the server converts the information sent by the user into an analyzable data format and stores it in a database.

[0871] Step 3:

[0872] The server analyzes the input data. Specifically, the server analyzes the received service information and extracts relevant data points (e.g., age group, region, interests, etc.). This process uses natural language processing technology.

[0873] Step 4:

[0874] The server launches a generative AI model, which inputs the extracted data points into the model to generate persona suggestions. This AI model is pre-trained to generate multiple detailed personas based on the input data.

[0875] Step 5:

[0876] The server presents the generated persona proposals to the user. Specifically, the server visually displays multiple generated personas (e.g., "30-year-old male, engineer living in the city, bicycle commuter" and "33-year-old female, marketing, gym-goer on weekday evenings") on the user's device.

[0877] Step 6:

[0878] The user selects the most suitable persona. Specifically, the user selects the most suitable persona from the presented persona list and sends the selection result to the server.

[0879] Step 7:

[0880] The server saves the selected persona information. Specifically, the server stores the user-selected persona data in a database and uses it for future service planning. It also receives feedback from users and uses it as further training data for the generative AI model.

[0881] This series of processing steps allows users to efficiently create realistic and useful personas while eliminating bias, which will enable them to develop strategies that are more suited to the target market when planning and providing services.

[0882] Example 1

[0883] 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."

[0884] Traditional service design tends to rely on the biases and experiences of individuals in charge, making it difficult to generate objective and effective personas. Furthermore, there is often a lack of mechanisms for properly storing the personas and incorporating feedback. This creates challenges that make it difficult to maximize the effectiveness of services.

[0885] 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.

[0886] In this invention, the server includes means for a user to input information about a service, means for converting the input service information into structured data and analyzing it, means for using a generative AI model to generate multiple persona proposals based on the analyzed data points, means for presenting the generated persona proposals to the user, and means for saving the persona proposal selected by the user and processing feedback, thereby eliminating bias and enabling objective and effective persona generation, and further enabling continuous improvement of the service by incorporating feedback.

[0887] "Information about the service" refers to data such as details of the service provided by the user, target market, age group, frequency of use, etc.

[0888] "Structured data" is data that is organized in a certain format that is easy to analyze and process. Examples include JSON and CSV formats.

[0889] "Analysis" is the process of converting input data into an understandable format and extracting the necessary information.

[0890] A "data point" is an individual unit of information extracted from analyzed data, and includes information such as age group, region, and interests.

[0891] A "generative AI model" is a model that has been trained using artificial intelligence (AI) technology and is an algorithm that generates new information based on input data.

[0892] A "persona proposal" is a virtual user profile created by a generative AI model, combining demographic and psychographic information.

[0893] "Presentation" is the process of showing the generated persona proposals to the user, allowing the user to evaluate and select a persona.

[0894] "Saving" means recording the selected persona and related data in a storage device such as a database.

[0895] "Feedback" refers to evaluations and opinions provided by users, and is data used to improve generative AI models and optimize services.

[0896] A "system" is an integrated technology collection that combines the above means to carry out a series of processes.

[0897] System configuration

[0898] This invention is a system that allows service planners to create effective personas while eliminating bias. This system uses a generative AI model to generate multiple persona proposals based on service information entered by the user, and includes a series of processes for presenting, selecting, and saving the personas to the user.

[0899] Hardware and Software

[0900] The system consists of the following hardware and software:

[0901] Server: Receives data, analyzes it, launches the generated AI model, generates personas, and stores data. In this invention, a general web server (e.g., Apache) can be used.

[0902] Terminal: A device on which users input service information and view and select generated personas. A general PC or smartphone can be used.

[0903] Generative AI model: An artificial intelligence model that generates personas based on data entered by users. A specific example would be a natural language processing model such as GPT-4.

[0904] Operational Overview

[0905] Entering Service Information

[0906] Users use their own devices to input service details. The information input includes the name of the service, the target market, the expected age group, and frequency of use. For example, if a user wants to provide a "luxury urban bicycle rental service," they would input information such as "target market: urban areas, age group: 20-35 years old, frequency of use: mostly on weekends."

[0907] Data transmission and analysis

[0908] The device sends the entered data to a server, which converts it into structured data, such as JSON format, and extracts relevant data points, such as age group, location, and interests, facilitating subsequent data analysis.

[0909] Launching the generative AI model and generating personas

[0910] The server then runs a trained generative AI model and inputs the extracted data points to generate multiple personas, each of which includes demographic and psychographic information, providing an unbiased, objective portrayal of the user.

[0911] Persona Presentation and Selection

[0912] The server sends the generated persona proposals to the user's device, allowing the user to view and select the most suitable one from the presented persona list.

[0913] Data storage and feedback processing

[0914] The persona ideas selected by the user are stored in a database by the server, and user feedback is also collected to help improve the accuracy of future persona generation.

[0915] Specific examples

[0916] As a specific example, the procedure when a user wants to provide an "urban luxury bicycle rental service" will be shown.

[0917] Example of a prompt for user input:

[0918] "The target market is urban areas. The age range is 20-35, and usage is mostly on weekends."

[0919] Example of a server-generated persona:

[0920] 30-year-old male, engineer living in a city, commutes to work by bicycle on weekends

[0921] 33-year-old woman, marketing manager, weekday evening gym goer

[0922] In this way, users can efficiently generate and select personas targeted at specific markets and improve the quality of their services by obtaining appropriate feedback, thereby eliminating user bias and enabling objective and effective service design.

[0923] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0924] Step 1:

[0925] User enters service details

[0926] Users use their own devices to input detailed information about the service they wish to provide. Specifically, they input information such as the name of the service, target market, age group, and frequency of use into a form. Examples of information that can be input include "target market: urban areas," "age group: 20-35 years old," and "frequency of use: mostly on weekends."

[0927] Input and Output

[0928] Input: Service details

[0929] Output: Structured JSON format data

[0930] Specific actions

[0931] The user enters service information into an input form on the device.

[0932] After completing the input, press the submit button and the form data will be converted to JSON format.

[0933] Step 2:

[0934] The device sends the input data to the server

[0935] The user's device sends the input data to the server as structured data (JSON format), using HTTPS as the communication protocol.

[0936] Input and Output

[0937] Input: Structured JSON format data

[0938] Output: HTTP request to the server

[0939] Specific actions

[0940] The terminal converts the input data into JSON format.

[0941] When the submit button is pressed, an HTTP POST request is sent to the server.

[0942] Step 3:

[0943] The server receives and analyzes the input data

[0944] The server parses the received data, specifically the JSON format data, and extracts the necessary data points (e.g., age group, region, interests).

[0945] Input and Output

[0946] Input: Received JSON format data

[0947] Output: Extracted data points

[0948] Specific actions

[0949] Parse the JSON data received by the server.

[0950] Data points such as "age group," "region," and "interests" are extracted and stored in internal memory.

[0951] Step 4:

[0952] The server starts the generation AI and generates a persona.

[0953] The server then launches the trained generative AI model, inputting the extracted data points to generate multiple persona suggestions.

[0954] Input and Output

[0955] Input: Data points

[0956] Output: Multiple persona ideas generated

[0957] Specific actions

[0958] The server launches a generative AI model (e.g., GPT-4).

[0959] The extracted data points are input into a generative AI model.

[0960] The generative AI model generates multiple persona ideas and stores them in memory.

[0961] Step 5:

[0962] The server presents the generated persona ideas to the user

[0963] The server sends the generated persona proposals to the user's device, allowing the user to view and select from them.

[0964] Input and Output

[0965] Input: Multiple persona ideas generated

[0966] Output: Data presented to the user's device

[0967] Specific actions

[0968] The server sends the generated persona proposal to the user's device.

[0969] Display a list of personas on the user's device.

[0970] Step 6:

[0971] User selects persona

[0972] The user selects the most suitable persona from the presented persona list and sends the selection to the server.

[0973] Input and Output

[0974] Input: Personalist

[0975] Output: Data for selected personas

[0976] Specific actions

[0977] Users can view the persona list on their device and select the most suitable persona.

[0978] The data of the selected persona is sent to the server.

[0979] Step 7:

[0980] The server stores the selected persona information and processes the feedback

[0981] The server stores the user-selected persona information in a database and also collects user feedback to use as training data for the generative AI model.

[0982] Input and Output

[0983] Input: Selected persona information, feedback

[0984] Output: Saved persona information, updated generative AI model

[0985] Specific actions

[0986] The server stores the selected persona information in a database.

[0987] Collect user feedback and use it to improve generative AI models.

[0988] (Application example 1)

[0989] 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."

[0990] In conventional advertising campaigns, the creation of targeting personas often relies on the subjectivity and bias of marketers, which can lead to a high risk of missing the right target demographic. Another issue is that the persona creation process is time-consuming and inefficient. Therefore, there is a demand for a system that can eliminate bias and quickly and effectively generate multiple persona proposals.

[0991] 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.

[0992] In this invention, the server includes means for a user to input information about a service, means for analyzing the input service information and extracting relevant data points, means for using an artificial intelligence model to generate multiple persona proposals based on the extracted data points, means for presenting the generated persona proposals to the user, means for saving the persona proposals selected by the user and processing feedback, means for presenting the persona proposals generated by the analysis data to a smartphone application, and means for saving the persona proposals selected by the user in a cloud database. This makes it possible to quickly generate effective persona proposals that are free from bias and improve the targeting of advertising campaigns.

[0993] "Service" refers to the products or actions provided, and is an activity that provides value to users.

[0994] "Information" is a collection of data or knowledge that can be used for a specific purpose.

[0995] "User" refers to any individual or entity that uses the System or Services.

[0996] "Means" refers to a method or device for achieving a particular purpose.

[0997] "Input" refers to the act of taking data into the system from outside.

[0998] "Analysis" is the process of breaking down input data into an understandable form.

[0999] "Relevant data points" refer to elements of data that are important for analysis.

[1000] "Extraction" is the act of extracting the necessary information from a data set.

[1001] An "artificial intelligence model" refers to a combination of algorithms designed to perform a specific task using machine learning or deep learning.

[1002] A "persona" is a concrete representation of a specific typical customer, a virtual person who is the target of a service or advertisement.

[1003] "Generation" is the act of creating new data or information according to predetermined rules or algorithms.

[1004] "Presenting" is the act of displaying or providing information to a user.

[1005] "Selection" is the act of choosing a specific option from multiple options.

[1006] "Storage" is the act of keeping data in a usable state for a long period of time.

[1007] "Feedback" refers to the reaction or information obtained as a result of an action or operation.

[1008] "Processing" is the act of manipulating or transforming input information to make it suitable for a purpose.

[1009] "Smartphone application" refers to a software program that runs on a smartphone.

[1010] "Cloud database" refers to a collection of digital information stored on remote servers accessible via the internet.

[1011] The present invention provides a system for quickly generating target personas for advertising campaigns with high accuracy, which involves a process in which a user inputs information about a service through a smartphone application, and the information is analyzed to generate a persona.

[1012] System configuration

[1013] 1. User input:

[1014] Using a smartphone application, users enter details of the services they wish to offer, such as the objectives of their advertising campaign, their target market, age group, and interests.

[1015] 2. Data Analysis Methods:

[1016] The server receives the input information and converts it into structured data such as JSON format using the Python json library.

[1017] Extract relevant data points (e.g., age, gender, location, interests) from structured data.

[1018] 3. Using generative AI models:

[1019] The server runs a pre-trained generative AI model that generates multiple persona suggestions from the extracted data points based on a specific algorithm.

[1020] 4. How to present persona ideas:

[1021] The server presents the generated persona proposal to the user's smartphone application. For example, the proposed persona displays detailed information such as "25-year-old male, freelance designer, online shopping on weekday evenings."

[1022] 5. User Choice:

[1023] The user selects the persona that they think is most suitable from the persona proposals presented.

[1024] 6. How persona information is stored:

[1025] The selected personas are saved in a cloud database, which ensures data persistence.

[1026] Specific examples

[1027] Consider a case where a user wants to run an advertising campaign. For example, the user uses the system in the following steps:

[1028] Example of input prompt:

[1029] Product Category: High-end fashion

[1030] Target market: Big cities

[1031] Campaign Objective: Increase brand awareness

[1032] Age range: 20-35

[1033] Examples of generated persona ideas:

[1034] 1. 25-year-old male, freelance designer, online shopping on weekday evenings

[1035] 2. A 28-year-old woman, a marketing manager, visits the mall on weekends.

[1036] Users can select a persona and store it in a cloud database for efficient targeting of advertising campaigns. This system is a powerful tool for eliminating bias and providing scientifically based targeting strategies.

[1037] The specific hardware and software used include smartphones, cloud servers, and computing resources for running AI models (e.g., servers with GPUs). The software is based on Python, and the AI ​​model uses deep learning libraries such as TensorFlow and PyTorch.

[1038] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1039] Step 1:

[1040] Users enter service details for their advertising campaigns through a smartphone application, including product category, target market, campaign objectives, age group, etc. This information is the initial input data for the system.

[1041] Step 2:

[1042] The device (smartphone) receives the input information and sends it to the server, which converts it into structured data such as JSON. For example, the Python json library can be used to parse the input data and extract relevant data points (such as age, gender, region, and interests).

[1043] Step 3:

[1044] The server then launches a pre-trained generative AI model based on the analyzed data points. The generative AI model is built using deep learning libraries such as TensorFlow and PyTorch. The AI ​​model takes the analyzed data as input and generates persona suggestions. The output is a set of detailed personas.

[1045] Step 4:

[1046] The server sends the generated persona proposals to a smartphone application and presents them to the user. The user can check multiple persona proposals on the smartphone screen. For example, persona information such as "25-year-old male, freelance designer, online shopping on weekday evenings" is displayed.

[1047] Step 5:

[1048] The user selects the persona they think is most suitable from the proposed personas. The selected persona is sent from the device to the server. The user's selection is transmitted to the server as feedback and used to improve the proposed persona.

[1049] Step 6:

[1050] The server stores the selected persona information in a cloud database, which is used for future advertising campaigns and system improvements. User feedback data is also used as training data for generative AI models.

[1051] This will enable more effective targeting in advertising campaigns, improve the accuracy of persona generation, and further strengthen marketing strategies by providing unbiased, scientific persona proposals quickly.

[1052] 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.

[1053] System Overview

[1054] The present invention is a system that recognizes a user's emotions and generates a persona that takes those emotions into consideration. This system involves a series of processes: inputting information about a service, analyzing the user's emotional state using an emotion engine, generating and presenting multiple personas, and evaluating the user's preferences in real time and providing feedback.

[1055] Explaining the program's processing

[1056] 1. The user enters the service details into the system

[1057] The user inputs detailed information about the service they wish to provide through the terminal. For example, if a user wants to provide a "luxury urban bicycle rental service," they would input details such as "target market: urban areas, age group: 20-35 years old, frequency of use: mostly on weekends." This information will be the basis for subsequent processing.

[1058] 2. The server processes the input data

[1059] The server receives the service information and parses it into structured data. Specifically, it converts the data into a format such as JSON and extracts relevant data points (e.g., age group, region, interests, etc.). The data obtained from this analysis process becomes the input for generating personas.

[1060] 3. Recognize user emotions using an emotion engine

[1061] When a user enters service information, the emotional state of the user is analyzed through the emotion engine. The emotional data obtained through this analysis will be an important factor in later persona generation.

[1062] 4. The server launches the generative AI model

[1063] The server launches a pre-trained generative AI model, which inputs the analyzed data points and emotional data into the AI ​​model, and the artificial intelligence generates multiple persona proposals. The AI ​​model aims to generate a more appropriate persona by taking the emotional data into account.

[1064] 5. The server presents the generated persona to the user.

[1065] The server presents the user with multiple persona ideas generated by the generative AI, including detailed information such as "30-year-old male, engineer living in the city, bicycle commuter" and "33-year-old female, marketing, gym-goer on weekday evenings."

[1066] 6. Users choose the persona that best suits them

[1067] The user selects the persona they think is most suitable from the presented persona list, and the emotion engine evaluates the user's preferences in real time and collects emotional data based on the selection results as feedback.

[1068] 7. The server stores the persona information

[1069] The server stores the persona information selected by the user in a database, and also receives feedback provided by the user, which is used as training data for the AI ​​generator to improve the accuracy of future persona generation.

[1070] Specific examples

[1071] As a specific example, the case of a user who wishes to provide an "urban luxury bicycle rental service" will be described.

[1072] 1. The user enters details about the service: "Target market: urban areas," "Age range: 20-35 years old," "Frequency of use: mostly on weekends," etc.

[1073] 2. The server analyzes the input data: extracting data points such as "age group," "region," and "interests."

[1074] 3. The emotion engine recognizes the user's emotions and analyzes the data.

[1075] 4. The server launches the generation AI: The AI ​​generates a persona proposal based on the extracted data and emotional data.

[1076] 5. The server presents the generated persona ideas: multiple persona ideas (e.g., a 30-year-old male engineer living in an urban area who commutes by bicycle).

[1077] 6. User selects persona: A persona that fits (e.g., 33-year-old female, marketing).

[1078] 7. Server saves persona information: The selected persona is saved in the database and feedback is collected.

[1079] In this way, the present invention allows users to input the details of a service, and the server uses AI to generate and present a detailed persona. Real-time evaluation incorporating the user's emotions is then performed, eliminating bias and efficiently creating realistic and useful personas. This allows for the formulation of strategies that are more suited to the target market when planning and providing services.

[1080] The processing flow will be explained below.

[1081] Step 1:

[1082] The user inputs service information. Specifically, the user uses the interface on the device to input details about the service they plan to provide (e.g., "urban luxury bicycle rental service," "target market: urban areas," "age range: 20-35 years old," "usage frequency: mostly on weekends").

[1083] Step 2:

[1084] The server receives the input service information. Specifically, the server converts the information sent by the user into an analyzable data format and stores it in a database.

[1085] Step 3:

[1086] The server analyzes the input data. Specifically, the server analyzes the received service information and extracts relevant data points (e.g., age group, region, interests, etc.). This process uses natural language processing technology.

[1087] Step 4:

[1088] The emotion engine recognizes the user's emotions. Specifically, when the user enters service information, emotional data is collected and analyzed from facial expressions and tone of voice using sensors such as the camera and microphone installed on the device.

[1089] Step 5:

[1090] The server launches the generative AI model, which inputs the analyzed data points and emotional data into the AI ​​model to generate multiple persona candidates. The generated persona takes the emotional data into account and matches the user's emotional state.

[1091] Step 6:

[1092] The server presents the generated persona proposals to the user. Specifically, the server visually displays multiple generated personas (e.g., "30-year-old male, engineer living in the city, commutes by bicycle" and "33-year-old female, marketing, goes to the gym on weekday evenings") on the user's device.

[1093] Step 7:

[1094] The user selects the most suitable persona from the presented persona list and sends the selection result to the server. At this time, the emotion engine evaluates the user's preferences in real time and collects emotional data during the selection process as feedback.

[1095] Step 8:

[1096] The server saves the selected persona information. Specifically, the server stores the user-selected persona data in a database and uses it for future service planning. It also receives feedback from users and uses it as further training data for the generative AI model.

[1097] This series of processing steps allows users to efficiently create realistic and useful personas while eliminating bias. Using the emotion engine, more accurate personas are generated that take into account the user's emotional state, improving the quality and suitability of services.

[1098] Example 2

[1099] 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."

[1100] Conventional persona generation systems have typically generated personas simply based on service information entered by users. This does not take into account the user's emotional state, and the generated personas often do not reflect the user's true needs or emotions. This has led to problems such as services provided and marketing strategies not being optimized for the target market.

[1101] 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.

[1102] In this invention, the server includes means for a user to input information about a service, means for analyzing the input service information and extracting relevant data points, means for analyzing the emotional state of the user at the time of input, means for using an artificial intelligence model based on the extracted data points and emotional data to generate multiple persona proposals, means for presenting the generated persona proposals to the user, and means for saving the persona proposal selected by the user and processing feedback, thereby enabling the generation of more realistic and useful personas that take the user's emotions into consideration.

[1103] "Service-related information" is data about the details of the service that the user wishes to provide.

[1104] The "means for inputting" is an interface that allows a user to input information about a service into the system.

[1105] "Means for analysis" refers to the process or technology for analyzing input service information and converting it into structured data.

[1106] "Relevant data points" are data items extracted from the entered service information that are necessary for analysis, such as age group, region, and interests.

[1107] The "emotional state" refers to the emotional or psychological state of the user when inputting service information.

[1108] "Means of analysis (emotional state)" refers to the techniques and processes for analyzing the user's emotional state from their input data and behavior.

[1109] "Artificial Intelligence Model" refers to an AI algorithm and trained model for generating personas based on user input data and emotional data.

[1110] A "persona proposal" is a human figure created to virtually represent the target market or user group of a service.

[1111] "Presentation means" refers to the interface or technology used to visually display the generated persona proposal to the user.

[1112] The "means of selection" is an interface that allows the user to choose the most suitable persona from the presented persona proposals.

[1113] "Storage methods" are techniques and processes for long-term storage of user-selected persona proposals.

[1114] "Feedback processing means" are techniques and processes that collect emotional data based on user choices and use it to improve the system.

[1115] This invention is a system that recognizes user emotions and generates personas that take these emotions into consideration. The purpose of this system is to execute a series of processes: generate multiple personas based on emotion data from detailed service information input, present them to the user, and finally collect user preferences as feedback.

[1116] Overview of program processing

[1117] 1. User enters service details

[1118] The user uses a terminal to input detailed information about the service they wish to provide. For example, if a user wants to provide a "luxury urban bicycle rental service," they would input specific information such as "target market: urban areas, age group: 20-35 years old, frequency of use: mostly on weekends." This becomes the basic data entered into the system.

[1119] 2. The server receives the input data

[1120] The server receives the service information entered by the user and parses it into structured data using a database management system or data analysis tool. In a specific step, the entered data is converted into JSON format and data points (e.g., age group, region, interests, etc.) are extracted.

[1121] 3. Recognize user emotions using an emotion engine

[1122] The emotion engine analyzes the user's emotional state when they input text. This analysis uses natural language processing (NLP) technology and emotion analysis tools. For example, the emotion engine (for example, Microsoft Azure text analysis API) can be used to recognize the user's emotional state based on the text they input and their behavioral patterns.

[1123] 4. The server launches the generative AI model

[1124] The server launches a pre-trained generative AI model, which inputs the analyzed data points and emotional data to generate several persona candidates. This process uses deep learning frameworks such as TensorFlow and PyTorch.

[1125] 5. The server presents the generated persona to the user.

[1126] The server presents multiple persona proposals generated by the generative AI to the user. For presentation, a web application front-end framework (e.g., React or Vue.js) is used to display the persona proposals to the user through a UI. Specific examples include the following persona proposals:

[1127] "30-year-old male, engineer living in a city, bicycle commuter"

[1128] "33-year-old woman, marketing manager, goes to the gym on weekday evenings"

[1129] 6. Users choose the persona that best suits them

[1130] Users select the most suitable persona from a list of multiple personas. As the user makes their selection, the emotion engine evaluates them in real time and collects emotional data, allowing for a more detailed understanding of the user's true needs and emotions.

[1131] 7. The server stores the persona information

[1132] The server stores the persona information selected by the user in a database. It also receives user feedback and uses it as training data for the generative AI model. The database can be an SQL-based database (e.g., MySQL or PostgreSQL) or a NoSQL database (e.g., MongoDB or Firebase).

[1133] Specific examples

[1134] As a concrete example, we will describe in detail the case of a user who wants to provide an "urban luxury bicycle rental service."

[1135] 1. The user uses the terminal to enter the service details: "Target market: urban areas", "Age range: 20-35 years old", "Frequency of use: mostly on weekends".

[1136] 2. The server receives and analyzes the input data, extracting data points such as demographics, geography, and interests.

[1137] 3. The emotion engine recognizes the user's emotions and analyzes the data, such as excitement, interest, and doubt.

[1138] 4. The server launches the generation AI to generate persona proposals, such as "a 30-year-old male engineer who lives in the city and commutes by bicycle" or "a 33-year-old female in marketing who goes to the gym on weekday evenings."

[1139] 5. The server presents the generated persona proposal to the user. The persona proposal is displayed through the UI.

[1140] 6. User selects a persona. Emotional data is collected based on user preferences.

[1141] 7. The server stores the persona information and collects feedback. The selected persona is stored in a database and used as training data for the generative AI.

[1142] In this way, the system can generate more accurate personas that take user emotions into account, making it easier to formulate strategies suited to target markets when planning and providing services.

[1143] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1144] Step 1:

[1145] The user inputs detailed information about the service they wish to provide through their terminal. Specifically, they input information such as "target market: urban areas," "age group: 20-35 years old," and "frequency of use: mostly on weekends." This information is sent to the server as basic data for subsequent processing. Input data: detailed service information. Output data: service information as basic data.

[1146] Step 2:

[1147] The server receives the service information entered by the user and analyzes it as structured data. Specifically, it uses a database management system (DBMS) and data analysis tools to convert the received data into JSON format and extract data points (e.g., age group, region, interests, etc.). Input data: Service details information. Output data: Structured data and extracted data points.

[1148] Step 3:

[1149] The emotion engine analyzes the user's emotional state at the time of input. Analysis is performed using natural language processing (NLP) technology and emotion analysis tools based on the user's input text and reaction data. For example, the Microsoft Azure text analysis API is used to recognize the user's emotional state (excitement, interest, suspicion, etc.). Input data: User's input text and reaction data. Output data: Analyzed emotion data.

[1150] Step 4:

[1151] The server launches a pre-trained generative AI model. The server inputs the analyzed data points and emotion data into the generative AI model to generate several persona candidates. This process uses a deep learning framework (such as TensorFlow or PyTorch). Input data: structured data and emotion data. Output data: generated persona candidates.

[1152] Step 5:

[1153] The server presents the generated multiple persona proposals to the user. Specifically, the persona proposals are visually displayed to the user through a UI using a web application front-end framework (such as React or Vue.js). For example, persona proposals such as "30-year-old male, engineer living in the city, commutes by bicycle" and "33-year-old female, marketing staff, goes to the gym on weekday evenings" are presented. Input data: Generated persona proposals. Output data: Persona proposals presented to the user.

[1154] Step 6:

[1155] The user selects the persona they consider most suitable from the presented options. As the user makes their selection, the emotion engine evaluates it in real time and collects emotional data. This allows for a detailed understanding of the user's true needs and emotions. Input data: User's selection of persona options. Output data: Optimal persona selection results and emotional feedback data.

[1156] Step 7:

[1157] The server saves the persona information selected by the user in a database and collects feedback from the user. The saved data is used as training data for the generative AI model in subsequent persona generation attempts, improving the accuracy of the model. The database used is an SQL-based database (e.g., MySQL or PostgreSQL) or a NoSQL database (e.g., MongoDB or Firebase). Input data: User-selected persona information and feedback data. Output data: Saved persona information and updated AI model.

[1158] (Application example 2)

[1159] 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."

[1160] Conventional persona generation systems generate personas based on static data without considering user emotions. As a result, the generated personas may not reflect the user's actual emotions and preferences, limiting the effectiveness of targeting and marketing strategies. Furthermore, to maximize the effectiveness of advertising campaigns, it is necessary to consider user emotions and preferences in the persona generation process, but no such means have been provided.

[1161] 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.

[1162] In this invention, the server includes means for a user to input information about a service, means for analyzing the input service information and extracting related data points, means for generating a plurality of persona proposals using an artificial intelligence model based on the extracted data points, means for presenting the generated persona proposals to the user, means for analyzing user emotion data in real time and reflecting the analysis result in the persona generation process, means for saving the persona proposal selected by the user and processing feedback, and means for performing ad targeting and delivering ad campaigns based on the generated persona proposals, thereby enabling real-time persona generation and targeting that reflects user emotions.

[1163] "Service Information" means details of the services you intend to provide, including your overall goals, target market, and product or service features.

[1164] "Means for analyzing the entered service information and extracting relevant data points" refers to the process of processing and analyzing the service information entered by the user to extract useful data points (e.g., age group, region, interests, etc.).

[1165] "Means for generating multiple persona proposals using an artificial intelligence model" refers to a technical means for generating multiple personas using AI technology based on extracted data points.

[1166] The "means for presenting the generated persona proposals to the user" is a technical process for presenting the generated multiple personas to the user visually or through an interface.

[1167] "Means for analyzing user emotional data in real time and reflecting it in the persona generation process" refers to a technical process for analyzing the emotional state of the user when entering service information and reflecting it in persona generation in real time.

[1168] "Means for storing user-selected persona proposals and processing feedback" refers to the technical means for storing user-selected persona proposals in a database and collecting and processing feedback from users.

[1169] "Means for targeting advertisements and delivering advertising campaigns based on the generated persona proposals" means the technical means for targeting advertisement campaigns and delivering the advertisements based on the generated personas.

[1170] The present invention is a system that recognizes user emotions and generates personas that take those emotions into account, thereby improving the targeting accuracy of advertising campaigns and enabling more effective marketing strategies.

[1171] System Overview

[1172] The system consists of the following major hardware and software components:

[1173] User devices: smartphones, tablets, etc.

[1174] Server: Data processing and persona generation

[1175] Emotion Engine: Software that analyzes user emotion data in real time

[1176] Generative AI model: Artificial intelligence that generates personas based on analytical data

[1177] Program processing

[1178] 1. Input on the user's terminal

[1179] Users use their smartphones or tablets to enter detailed information about the services they wish to offer, including, for example, the target market, product features, age group, and advertising objectives.

[1180] 2. Analysis by emotion engine

[1181] When a user inputs information, the device uses an emotion engine to collect real-time emotional data from the user, which is derived from facial expression analysis, voice analysis, touch speed, and other factors.

[1182] 3. Data processing and analysis on the server

[1183] The server receives the service information and emotion data entered by the user, converts it into structured data, and analyzes it. The extracted data points (e.g., age group, region, interests, etc.) become the basis for generating personas.

[1184] 4. Persona generation using generative AI models

[1185] The server then runs a generative AI model to generate multiple personas by inputting the analyzed data points and emotional data. The model generates personas taking the emotional data into account, providing a more realistic and useful portrayal of the target.

[1186] 5. Persona Presentation and Selection

[1187] The generated personas are presented to the user via their device, and the user can select the persona they think is most suitable. During this process, emotional data is analyzed and used as feedback.

[1188] 6. Persona-Based Ad Targeting

[1189] Based on the selected personas, advertising campaigns are designed and targeted. The ads are then linked to the appropriate distribution platforms and distributed. This targeting process allows for sophisticated strategies that reflect user sentiment.

[1190] 7. Gather feedback and refine the model

[1191] After the ad is delivered, user response data is collected and used as training data for the generative AI model, which will improve the accuracy of future persona generation.

[1192] Specific examples

[1193] Example: Advertising campaign for luxury urban bicycles

[1194] Step 1: The user enters information such as "Target market: urban areas," "Age group: 20-35 years old," and "Advertising purpose: brand awareness" into their smartphone.

[1195] Step 2: The device's emotion engine analyzes the emotion data entered by the user in real time.

[1196] Step 3: The server receives the information, converts it into structured data, and parses it.

[1197] Step 4: The generative AI model generates multiple personas based on the data.

[1198] Step 5: The generated personas are presented to the user, who then selects the most appropriate one.

[1199] Step 6: Ad targeting is performed based on the selected persona, and the actual ad campaign is delivered.

[1200] Prompt Sentence Examples

[1201] "Enter your advertising campaign information. Enter the data advertisers need for customer targeting. We also collect sentiment data in real time and generate multiple personas based on this. For example, the target audience for the "Premium Bicycle" advertising campaign is urban users aged 20-35. Based on this information, we generate appropriate personas and collect feedback."

[1202] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1203] Step 1:

[1204] Users input information about the services they wish to provide from their terminals. This information includes the target market, age group, advertising objectives, product features, etc. This information becomes the basic data for the entire system.

[1205] Input: Service information such as target market, age group, advertising purpose, product features, etc.

[1206] Output: Raw data entered by the user

[1207] Step 2:

[1208] The device sends the entered service information to the server. At the same time, the device's emotion engine analyzes the user's emotional data (facial expressions, voice, touch operation speed, etc.) in real time and sends this emotional data to the server.

[1209] Input: User service information, real-time emotion data

[1210] Output: Data points and sentiment data sent to the server

[1211] Step 3:

[1212] The server converts the received service information and emotional data into structured data and analyzes it. At this stage, data points such as target market, age group, and product features are extracted. Emotional data is also analyzed and integrated as information necessary for persona generation.

[1213] Input: Service information, raw emotion data

[1214] Output: Structured data points and parsed sentiment data

[1215] Step 4:

[1216] The server launches a generative AI model, inputting the analyzed data points and emotional data. The generative AI model generates multiple personas based on this data. This persona generation takes into account the user's emotional data to create a more specific target image.

[1217] Input: Structured data points, parsed sentiment data

[1218] Output: Multiple persona ideas generated

[1219] Step 5:

[1220] The generated persona proposals are sent from the server to the device, which then presents them to the user. The user can then select the most suitable persona, and this selection process is also analyzed by the emotion engine, with the results being fed back to the server.

[1221] Input: Generated persona ideas

[1222] Output: Persona proposals selected by the user and emotional data at the time of preference

[1223] Step 6:

[1224] The server stores the persona choices selected by the user and uses this information to target ads. An ad campaign is then set up and delivered to the target market. After the ad is delivered, user response data is also collected.

[1225] Input: Persona proposal selected by the user, emotional data at the time of preference

[1226] Output: Stored persona data, ad targeting information, and post-delivery response data

[1227] Step 7:

[1228] The server generates feedback based on the collected reaction data and uses this feedback information as training data for the generative AI model, thereby improving the accuracy of future persona generation.

[1229] Input: Post-distribution reaction data

[1230] Output: Updated training data, improved AI model

[1231] 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.

[1232] 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.

[1233] 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.

[1234] [Fourth embodiment]

[1235] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1236] 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.

[1237] 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).

[1238] 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.

[1239] 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.

[1240] 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).

[1241] 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.

[1242] 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.

[1243] 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.

[1244] 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.

[1245] 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.

[1246] 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.

[1247] 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."

[1248] System Overview

[1249] The present invention is a system that allows service planners to create effective personas while eliminating bias. This system involves a series of processes: inputting information about a service, generating multiple personas using artificial intelligence to overcome human biases and limitations, and presenting, selecting, and saving them to the user.

[1250] Explaining the program's processing

[1251] 1. The user enters the service details into the system

[1252] The user inputs detailed information about the service they wish to provide through the terminal. For example, if a user wants to provide a "luxury urban bicycle rental service," they would input details such as "target market: urban areas, age group: 20-35 years old, frequency of use: mostly on weekends." This information will be the basis for subsequent processing.

[1253] 2. The server processes the input data

[1254] The server receives the service information and parses it into structured data. Specifically, it converts the data into a format such as JSON and extracts relevant data points (e.g., age group, region, interests, etc.). The data obtained from this analysis process becomes the input for generating personas.

[1255] 3. The server starts the generated AI

[1256] The server runs a pre-trained generative AI model, which inputs the analyzed data points and generates multiple persona proposals. The personas generated are a combination of demographics (age, gender, occupation, etc.) and psychographics (interests, values, behavioral patterns, etc.).

[1257] 4. The server presents the persona proposal to the user

[1258] The server presents the user with multiple persona ideas generated by the generative AI, including detailed information such as "30-year-old male, engineer living in the city, bicycle commuter" and "33-year-old female, marketing, gym-goer on weekday evenings."

[1259] 5. Users choose the persona that best suits them

[1260] Users can select the persona they think is most suitable from the presented persona list. For example, they can choose the persona "33-year-old female, marketing staff, uses bicycle to go to the gym on weekday evenings."

[1261] 6. The server stores the persona information

[1262] The server stores the persona information selected by the user in a database and receives feedback provided by the user, which is used as training data for the AI ​​to improve the accuracy of future persona generation.

[1263] Specific examples

[1264] As a specific example, the case of a user who wishes to provide an "urban luxury bicycle rental service" will be described.

[1265] 1. The user enters details about the service: "Target market: urban areas," "Age range: 20-35 years old," "Frequency of use: mostly on weekends," etc.

[1266] 2. The server analyzes the input data: extracting data points such as "age group," "region," and "interests."

[1267] 3. The server launches the generation AI: The AI ​​generates persona proposals based on the extracted data.

[1268] 4. The server presents persona options: Multiple persona options (e.g., a 30-year-old male engineer living in an urban area who commutes by bicycle).

[1269] 5. User selects persona: A persona that fits (e.g., 33-year-old female, marketing).

[1270] 6. Server saves persona information: The selected persona is saved in the database and feedback is collected.

[1271] In this way, the present invention allows users to input the details of the service, and the server uses generation AI to generate and present a detailed persona, eliminating bias and efficiently forming personas, which enables the provision of better services.

[1272] The processing flow will be explained below.

[1273] Step 1:

[1274] The user inputs service information. Specifically, the user uses the interface on the device to input details about the service they plan to provide (e.g., "urban luxury bicycle rental service," "target market: urban areas," "age range: 20-35 years old," "usage frequency: mostly on weekends").

[1275] Step 2:

[1276] The server receives the input service information. Specifically, the server converts the information sent by the user into an analyzable data format and stores it in a database.

[1277] Step 3:

[1278] The server analyzes the input data. Specifically, the server analyzes the received service information and extracts relevant data points (e.g., age group, region, interests, etc.). This process uses natural language processing technology.

[1279] Step 4:

[1280] The server launches a generative AI model, which inputs the extracted data points into the model to generate persona suggestions. This AI model is pre-trained to generate multiple detailed personas based on the input data.

[1281] Step 5:

[1282] The server presents the generated persona proposals to the user. Specifically, the server visually displays multiple generated personas (e.g., "30-year-old male, engineer living in the city, bicycle commuter" and "33-year-old female, marketing, gym-goer on weekday evenings") on the user's device.

[1283] Step 6:

[1284] The user selects the most suitable persona. Specifically, the user selects the most suitable persona from the presented persona list and sends the selection result to the server.

[1285] Step 7:

[1286] The server saves the selected persona information. Specifically, the server stores the user-selected persona data in a database and uses it for future service planning. It also receives feedback from users and uses it as further training data for the generative AI model.

[1287] This series of processing steps allows users to efficiently create realistic and useful personas while eliminating bias, which will enable them to develop strategies that are more suited to the target market when planning and providing services.

[1288] Example 1

[1289] 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."

[1290] Traditional service design tends to rely on the biases and experiences of individuals in charge, making it difficult to generate objective and effective personas. Furthermore, there is often a lack of mechanisms for properly storing the personas and incorporating feedback. This creates challenges that make it difficult to maximize the effectiveness of services.

[1291] 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.

[1292] In this invention, the server includes means for a user to input information about a service, means for converting the input service information into structured data and analyzing it, means for using a generative AI model to generate multiple persona proposals based on the analyzed data points, means for presenting the generated persona proposals to the user, and means for saving the persona proposal selected by the user and processing feedback, thereby eliminating bias and enabling objective and effective persona generation, and further enabling continuous improvement of the service by incorporating feedback.

[1293] "Information about the service" refers to data such as details of the service provided by the user, target market, age group, frequency of use, etc.

[1294] "Structured data" is data that is organized in a certain format that is easy to analyze and process. Examples include JSON and CSV formats.

[1295] "Analysis" is the process of converting input data into an understandable format and extracting the necessary information.

[1296] A "data point" is an individual unit of information extracted from analyzed data, and includes information such as age group, region, and interests.

[1297] A "generative AI model" is a model that has been trained using artificial intelligence (AI) technology and is an algorithm that generates new information based on input data.

[1298] A "persona proposal" is a virtual user profile created by a generative AI model, combining demographic and psychographic information.

[1299] "Presentation" is the process of showing the generated persona proposals to the user, allowing the user to evaluate and select a persona.

[1300] "Saving" means recording the selected persona and related data in a storage device such as a database.

[1301] "Feedback" refers to evaluations and opinions provided by users, and is data used to improve generative AI models and optimize services.

[1302] A "system" is an integrated technology collection that combines the above means to carry out a series of processes.

[1303] System configuration

[1304] This invention is a system that allows service planners to create effective personas while eliminating bias. This system uses a generative AI model to generate multiple persona proposals based on service information entered by the user, and includes a series of processes for presenting, selecting, and saving the personas to the user.

[1305] Hardware and Software

[1306] The system consists of the following hardware and software:

[1307] Server: Receives data, analyzes it, launches the generated AI model, generates personas, and stores data. In this invention, a general web server (e.g., Apache) can be used.

[1308] Terminal: A device on which users input service information and view and select generated personas. A general PC or smartphone can be used.

[1309] Generative AI model: An artificial intelligence model that generates personas based on data entered by users. A specific example would be a natural language processing model such as GPT-4.

[1310] Operational Overview

[1311] Entering Service Information

[1312] Users use their own devices to input service details. The information input includes the name of the service, the target market, the expected age group, and frequency of use. For example, if a user wants to provide a "luxury urban bicycle rental service," they would input information such as "target market: urban areas, age group: 20-35 years old, frequency of use: mostly on weekends."

[1313] Data transmission and analysis

[1314] The device sends the entered data to a server, which converts it into structured data, such as JSON format, and extracts relevant data points, such as age group, location, and interests, facilitating subsequent data analysis.

[1315] Launching the generative AI model and generating personas

[1316] The server then runs a trained generative AI model and inputs the extracted data points to generate multiple personas, each of which includes demographic and psychographic information, providing an unbiased, objective portrayal of the user.

[1317] Persona Presentation and Selection

[1318] The server sends the generated persona proposals to the user's device, allowing the user to view and select the most suitable one from the presented persona list.

[1319] Data storage and feedback processing

[1320] The persona ideas selected by the user are stored in a database by the server, and user feedback is also collected to help improve the accuracy of future persona generation.

[1321] Specific examples

[1322] As a specific example, the procedure when a user wants to provide an "urban luxury bicycle rental service" will be shown.

[1323] Example of a prompt for user input:

[1324] "The target market is urban areas. The age range is 20-35, and usage is mostly on weekends."

[1325] Example of a server-generated persona:

[1326] 30-year-old male, engineer living in a city, commutes to work by bicycle on weekends

[1327] 33-year-old woman, marketing manager, weekday evening gym goer

[1328] In this way, users can efficiently generate and select personas targeted at specific markets and improve the quality of their services by obtaining appropriate feedback, thereby eliminating user bias and enabling objective and effective service design.

[1329] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1330] Step 1:

[1331] User enters service details

[1332] Users use their own devices to input detailed information about the service they wish to provide. Specifically, they input information such as the name of the service, target market, age group, and frequency of use into a form. Examples of information that can be input include "target market: urban areas," "age group: 20-35 years old," and "frequency of use: mostly on weekends."

[1333] Input and Output

[1334] Input: Service details

[1335] Output: Structured JSON format data

[1336] Specific actions

[1337] The user enters service information into an input form on the device.

[1338] After completing the input, press the submit button and the form data will be converted to JSON format.

[1339] Step 2:

[1340] The device sends the input data to the server

[1341] The user's device sends the input data to the server as structured data (JSON format), using HTTPS as the communication protocol.

[1342] Input and Output

[1343] Input: Structured JSON format data

[1344] Output: HTTP request to the server

[1345] Specific actions

[1346] The terminal converts the input data into JSON format.

[1347] When the submit button is pressed, an HTTP POST request is sent to the server.

[1348] Step 3:

[1349] The server receives and analyzes the input data

[1350] The server parses the received data, specifically the JSON format data, and extracts the necessary data points (e.g., age group, region, interests).

[1351] Input and Output

[1352] Input: Received JSON format data

[1353] Output: Extracted data points

[1354] Specific actions

[1355] Parse the JSON data received by the server.

[1356] Data points such as "age group," "region," and "interests" are extracted and stored in internal memory.

[1357] Step 4:

[1358] The server starts the generation AI and generates a persona.

[1359] The server then launches the trained generative AI model, inputting the extracted data points to generate multiple persona suggestions.

[1360] Input and Output

[1361] Input: Data points

[1362] Output: Multiple persona ideas generated

[1363] Specific actions

[1364] The server launches a generative AI model (e.g., GPT-4).

[1365] The extracted data points are input into a generative AI model.

[1366] The generative AI model generates multiple persona ideas and stores them in memory.

[1367] Step 5:

[1368] The server presents the generated persona ideas to the user

[1369] The server sends the generated persona proposals to the user's device, allowing the user to view and select from them.

[1370] Input and Output

[1371] Input: Multiple persona ideas generated

[1372] Output: Data presented to the user's device

[1373] Specific actions

[1374] The server sends the generated persona proposal to the user's device.

[1375] Display a list of personas on the user's device.

[1376] Step 6:

[1377] User selects persona

[1378] The user selects the most suitable persona from the presented persona list and sends the selection to the server.

[1379] Input and Output

[1380] Input: Personalist

[1381] Output: Data for selected personas

[1382] Specific actions

[1383] Users can view the persona list on their device and select the most suitable persona.

[1384] The data of the selected persona is sent to the server.

[1385] Step 7:

[1386] The server stores the selected persona information and processes the feedback

[1387] The server stores the user-selected persona information in a database and also collects user feedback to use as training data for the generative AI model.

[1388] Input and Output

[1389] Input: Selected persona information, feedback

[1390] Output: Saved persona information, updated generative AI model

[1391] Specific actions

[1392] The server stores the selected persona information in a database.

[1393] Collect user feedback and use it to improve generative AI models.

[1394] (Application example 1)

[1395] 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."

[1396] In conventional advertising campaigns, the creation of targeting personas often relies on the subjectivity and bias of marketers, which can lead to a high risk of missing the right target demographic. Another issue is that the persona creation process is time-consuming and inefficient. Therefore, there is a demand for a system that can eliminate bias and quickly and effectively generate multiple persona proposals.

[1397] 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.

[1398] In this invention, the server includes means for a user to input information about a service, means for analyzing the input service information and extracting relevant data points, means for using an artificial intelligence model to generate multiple persona proposals based on the extracted data points, means for presenting the generated persona proposals to the user, means for saving the persona proposals selected by the user and processing feedback, means for presenting the persona proposals generated by the analysis data to a smartphone application, and means for saving the persona proposals selected by the user in a cloud database. This makes it possible to quickly generate effective persona proposals that are free from bias and improve the targeting of advertising campaigns.

[1399] "Service" refers to the products or actions provided, and is an activity that provides value to users.

[1400] "Information" is a collection of data or knowledge that can be used for a specific purpose.

[1401] "User" refers to any individual or entity that uses the System or Services.

[1402] "Means" refers to a method or device for achieving a particular purpose.

[1403] "Input" refers to the act of taking data into the system from outside.

[1404] "Analysis" is the process of breaking down input data into an understandable form.

[1405] "Relevant data points" refer to elements of data that are important for analysis.

[1406] "Extraction" is the act of extracting the necessary information from a data set.

[1407] An "artificial intelligence model" refers to a combination of algorithms designed to perform a specific task using machine learning or deep learning.

[1408] A "persona" is a concrete representation of a specific typical customer, a virtual person who is the target of a service or advertisement.

[1409] "Generation" is the act of creating new data or information according to predetermined rules or algorithms.

[1410] "Presenting" is the act of displaying or providing information to a user.

[1411] "Selection" is the act of choosing a specific option from multiple options.

[1412] "Storage" is the act of keeping data in a usable state for a long period of time.

[1413] "Feedback" refers to the reaction or information obtained as a result of an action or operation.

[1414] "Processing" is the act of manipulating or transforming input information to make it suitable for a purpose.

[1415] "Smartphone application" refers to a software program that runs on a smartphone.

[1416] "Cloud database" refers to a collection of digital information stored on remote servers accessible via the internet.

[1417] The present invention provides a system for quickly generating target personas for advertising campaigns with high accuracy, which involves a process in which a user inputs information about a service through a smartphone application, and the information is analyzed to generate a persona.

[1418] System configuration

[1419] 1. User input:

[1420] Using a smartphone application, users enter details of the services they wish to offer, such as the objectives of their advertising campaign, their target market, age group, and interests.

[1421] 2. Data Analysis Methods:

[1422] The server receives the input information and converts it into structured data such as JSON format using the Python json library.

[1423] Extract relevant data points (e.g., age, gender, location, interests) from structured data.

[1424] 3. Using generative AI models:

[1425] The server runs a pre-trained generative AI model that generates multiple persona suggestions from the extracted data points based on a specific algorithm.

[1426] 4. How to present persona ideas:

[1427] The server presents the generated persona proposal to the user's smartphone application. For example, the proposed persona displays detailed information such as "25-year-old male, freelance designer, online shopping on weekday evenings."

[1428] 5. User Choice:

[1429] The user selects the persona that they think is most suitable from the persona proposals presented.

[1430] 6. How persona information is stored:

[1431] The selected personas are saved in a cloud database, which ensures data persistence.

[1432] Specific examples

[1433] Consider a case where a user wants to run an advertising campaign. For example, the user uses the system in the following steps:

[1434] Example of input prompt:

[1435] Product Category: High-end fashion

[1436] Target market: Big cities

[1437] Campaign Objective: Increase brand awareness

[1438] Age range: 20-35

[1439] Examples of generated persona ideas:

[1440] 1. 25-year-old male, freelance designer, online shopping on weekday evenings

[1441] 2. A 28-year-old woman, a marketing manager, visits the mall on weekends.

[1442] Users can select a persona and store it in a cloud database for efficient targeting of advertising campaigns. This system is a powerful tool for eliminating bias and providing scientifically based targeting strategies.

[1443] The specific hardware and software used include smartphones, cloud servers, and computing resources for running AI models (e.g., servers with GPUs). The software is based on Python, and the AI ​​model uses deep learning libraries such as TensorFlow and PyTorch.

[1444] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1445] Step 1:

[1446] Users enter service details for their advertising campaigns through a smartphone application, including product category, target market, campaign objectives, age group, etc. This information is the initial input data for the system.

[1447] Step 2:

[1448] The device (smartphone) receives the input information and sends it to the server, which converts it into structured data such as JSON. For example, the Python json library can be used to parse the input data and extract relevant data points (such as age, gender, region, and interests).

[1449] Step 3:

[1450] The server then launches a pre-trained generative AI model based on the analyzed data points. The generative AI model is built using deep learning libraries such as TensorFlow and PyTorch. The AI ​​model takes the analyzed data as input and generates persona suggestions. The output is a set of detailed personas.

[1451] Step 4:

[1452] The server sends the generated persona proposals to a smartphone application and presents them to the user. The user can check multiple persona proposals on the smartphone screen. For example, persona information such as "25-year-old male, freelance designer, online shopping on weekday evenings" is displayed.

[1453] Step 5:

[1454] The user selects the persona they think is most suitable from the proposed personas. The selected persona is sent from the device to the server. The user's selection is transmitted to the server as feedback and used to improve the proposed persona.

[1455] Step 6:

[1456] The server stores the selected persona information in a cloud database, which is used for future advertising campaigns and system improvements. User feedback data is also used as training data for generative AI models.

[1457] This will enable more effective targeting in advertising campaigns, improve the accuracy of persona generation, and further strengthen marketing strategies by providing unbiased, scientific persona proposals quickly.

[1458] 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.

[1459] System Overview

[1460] The present invention is a system that recognizes a user's emotions and generates a persona that takes those emotions into consideration. This system involves a series of processes: inputting information about a service, analyzing the user's emotional state using an emotion engine, generating and presenting multiple personas, and evaluating the user's preferences in real time and providing feedback.

[1461] Explaining the program's processing

[1462] 1. The user enters the service details into the system

[1463] The user inputs detailed information about the service they wish to provide through the terminal. For example, if a user wants to provide a "luxury urban bicycle rental service," they would input details such as "target market: urban areas, age group: 20-35 years old, frequency of use: mostly on weekends." This information will be the basis for subsequent processing.

[1464] 2. The server processes the input data

[1465] The server receives the service information and parses it into structured data. Specifically, it converts the data into a format such as JSON and extracts relevant data points (e.g., age group, region, interests, etc.). The data obtained from this analysis process becomes the input for generating personas.

[1466] 3. Recognize user emotions using an emotion engine

[1467] When a user enters service information, the emotional state of the user is analyzed through the emotion engine. The emotional data obtained through this analysis will be an important factor in later persona generation.

[1468] 4. The server launches the generative AI model

[1469] The server launches a pre-trained generative AI model, which inputs the analyzed data points and emotional data into the AI ​​model, and the artificial intelligence generates multiple persona proposals. The AI ​​model aims to generate a more appropriate persona by taking the emotional data into account.

[1470] 5. The server presents the generated persona to the user.

[1471] The server presents the user with multiple persona ideas generated by the generative AI, including detailed information such as "30-year-old male, engineer living in the city, bicycle commuter" and "33-year-old female, marketing, gym-goer on weekday evenings."

[1472] 6. Users choose the persona that best suits them

[1473] The user selects the persona they think is most suitable from the presented persona list, and the emotion engine evaluates the user's preferences in real time and collects emotional data based on the selection results as feedback.

[1474] 7. The server stores the persona information

[1475] The server stores the persona information selected by the user in a database, and also receives feedback provided by the user, which is used as training data for the AI ​​generator to improve the accuracy of future persona generation.

[1476] Specific examples

[1477] As a specific example, the case of a user who wishes to provide an "urban luxury bicycle rental service" will be described.

[1478] 1. The user enters details about the service: "Target market: urban areas," "Age range: 20-35 years old," "Frequency of use: mostly on weekends," etc.

[1479] 2. The server analyzes the input data: extracting data points such as "age group," "region," and "interests."

[1480] 3. The emotion engine recognizes the user's emotions and analyzes the data.

[1481] 4. The server launches the generation AI: The AI ​​generates a persona proposal based on the extracted data and emotional data.

[1482] 5. The server presents the generated persona ideas: multiple persona ideas (e.g., a 30-year-old male engineer living in an urban area who commutes by bicycle).

[1483] 6. User selects persona: A persona that fits (e.g., 33-year-old female, marketing).

[1484] 7. Server saves persona information: The selected persona is saved in the database and feedback is collected.

[1485] In this way, the present invention allows users to input the details of a service, and the server uses AI to generate and present a detailed persona. Real-time evaluation incorporating the user's emotions is then performed, eliminating bias and efficiently creating realistic and useful personas. This allows for the formulation of strategies that are more suited to the target market when planning and providing services.

[1486] The processing flow will be explained below.

[1487] Step 1:

[1488] The user inputs service information. Specifically, the user uses the interface on the device to input details about the service they plan to provide (e.g., "urban luxury bicycle rental service," "target market: urban areas," "age range: 20-35 years old," "usage frequency: mostly on weekends").

[1489] Step 2:

[1490] The server receives the input service information. Specifically, the server converts the information sent by the user into an analyzable data format and stores it in a database.

[1491] Step 3:

[1492] The server analyzes the input data. Specifically, the server analyzes the received service information and extracts relevant data points (e.g., age group, region, interests, etc.). This process uses natural language processing technology.

[1493] Step 4:

[1494] The emotion engine recognizes the user's emotions. Specifically, when the user enters service information, emotional data is collected and analyzed from facial expressions and tone of voice using sensors such as the camera and microphone installed on the device.

[1495] Step 5:

[1496] The server launches the generative AI model, which inputs the analyzed data points and emotional data into the AI ​​model to generate multiple persona candidates. The generated persona takes the emotional data into account and matches the user's emotional state.

[1497] Step 6:

[1498] The server presents the generated persona proposals to the user. Specifically, the server visually displays multiple generated personas (e.g., "30-year-old male, engineer living in the city, commutes by bicycle" and "33-year-old female, marketing, goes to the gym on weekday evenings") on the user's device.

[1499] Step 7:

[1500] The user selects the most suitable persona from the presented persona list and sends the selection result to the server. At this time, the emotion engine evaluates the user's preferences in real time and collects emotional data during the selection process as feedback.

[1501] Step 8:

[1502] The server saves the selected persona information. Specifically, the server stores the user-selected persona data in a database and uses it for future service planning. It also receives feedback from users and uses it as further training data for the generative AI model.

[1503] This series of processing steps allows users to efficiently create realistic and useful personas while eliminating bias. Using the emotion engine, more accurate personas are generated that take into account the user's emotional state, improving the quality and suitability of services.

[1504] Example 2

[1505] 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."

[1506] Conventional persona generation systems have typically generated personas simply based on service information entered by users. This does not take into account the user's emotional state, and the generated personas often do not reflect the user's true needs or emotions. This has led to problems such as services provided and marketing strategies not being optimized for the target market.

[1507] 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.

[1508] In this invention, the server includes means for a user to input information about a service, means for analyzing the input service information and extracting relevant data points, means for analyzing the emotional state of the user at the time of input, means for using an artificial intelligence model based on the extracted data points and emotional data to generate multiple persona proposals, means for presenting the generated persona proposals to the user, and means for saving the persona proposal selected by the user and processing feedback, thereby enabling the generation of more realistic and useful personas that take the user's emotions into consideration.

[1509] "Service-related information" is data about the details of the service that the user wishes to provide.

[1510] The "means for inputting" is an interface that allows a user to input information about a service into the system.

[1511] "Means for analysis" refers to the process or technology for analyzing input service information and converting it into structured data.

[1512] "Relevant data points" are data items extracted from the entered service information that are necessary for analysis, such as age group, region, and interests.

[1513] The "emotional state" refers to the emotional or psychological state of the user when inputting service information.

[1514] "Means of analysis (emotional state)" refers to the techniques and processes for analyzing the user's emotional state from their input data and behavior.

[1515] "Artificial Intelligence Model" refers to an AI algorithm and trained model for generating personas based on user input data and emotional data.

[1516] A "persona proposal" is a human figure created to virtually represent the target market or user group of a service.

[1517] "Presentation means" refers to the interface or technology used to visually display the generated persona proposal to the user.

[1518] The "means of selection" is an interface that allows the user to choose the most suitable persona from the presented persona proposals.

[1519] "Storage methods" are techniques and processes for long-term storage of user-selected persona proposals.

[1520] "Feedback processing means" are techniques and processes that collect emotional data based on user choices and use it to improve the system.

[1521] This invention is a system that recognizes user emotions and generates personas that take these emotions into consideration. The purpose of this system is to execute a series of processes: generate multiple personas based on emotion data from detailed service information input, present them to the user, and finally collect user preferences as feedback.

[1522] Overview of program processing

[1523] 1. User enters service details

[1524] The user uses a terminal to input detailed information about the service they wish to provide. For example, if a user wants to provide a "luxury urban bicycle rental service," they would input specific information such as "target market: urban areas, age group: 20-35 years old, frequency of use: mostly on weekends." This becomes the basic data entered into the system.

[1525] 2. The server receives the input data

[1526] The server receives the service information entered by the user and parses it into structured data using a database management system or data analysis tool. In a specific step, the entered data is converted into JSON format and data points (e.g., age group, region, interests, etc.) are extracted.

[1527] 3. Recognize user emotions using an emotion engine

[1528] The emotion engine analyzes the user's emotional state when they input text. This analysis uses natural language processing (NLP) technology and emotion analysis tools. For example, the emotion engine (for example, Microsoft Azure text analysis API) can be used to recognize the user's emotional state based on the text they input and their behavioral patterns.

[1529] 4. The server launches the generative AI model

[1530] The server launches a pre-trained generative AI model, which inputs the analyzed data points and emotional data to generate several persona candidates. This process uses deep learning frameworks such as TensorFlow and PyTorch.

[1531] 5. The server presents the generated persona to the user.

[1532] The server presents multiple persona proposals generated by the generative AI to the user. For presentation, a web application front-end framework (e.g., React or Vue.js) is used to display the persona proposals to the user through a UI. Specific examples include the following persona proposals:

[1533] "30-year-old male, engineer living in a city, bicycle commuter"

[1534] "33-year-old woman, marketing manager, goes to the gym on weekday evenings"

[1535] 6. Users choose the persona that best suits them

[1536] Users select the most suitable persona from a list of multiple personas. As the user makes their selection, the emotion engine evaluates them in real time and collects emotional data, allowing for a more detailed understanding of the user's true needs and emotions.

[1537] 7. The server stores the persona information

[1538] The server stores the persona information selected by the user in a database. It also receives user feedback and uses it as training data for the generative AI model. The database can be an SQL-based database (e.g., MySQL or PostgreSQL) or a NoSQL database (e.g., MongoDB or Firebase).

[1539] Specific examples

[1540] As a concrete example, we will describe in detail the case of a user who wants to provide an "urban luxury bicycle rental service."

[1541] 1. The user uses the terminal to enter the service details: "Target market: urban areas", "Age range: 20-35 years old", "Frequency of use: mostly on weekends".

[1542] 2. The server receives and analyzes the input data, extracting data points such as demographics, geography, and interests.

[1543] 3. The emotion engine recognizes the user's emotions and analyzes the data, such as excitement, interest, and doubt.

[1544] 4. The server launches the generation AI to generate persona proposals, such as "a 30-year-old male engineer who lives in the city and commutes by bicycle" or "a 33-year-old female in marketing who goes to the gym on weekday evenings."

[1545] 5. The server presents the generated persona proposal to the user. The persona proposal is displayed through the UI.

[1546] 6. User selects a persona. Emotional data is collected based on user preferences.

[1547] 7. The server stores the persona information and collects feedback. The selected persona is stored in a database and used as training data for the generative AI.

[1548] In this way, the system can generate more accurate personas that take user emotions into account, making it easier to formulate strategies suited to target markets when planning and providing services.

[1549] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1550] Step 1:

[1551] The user inputs detailed information about the service they wish to provide through their terminal. Specifically, they input information such as "target market: urban areas," "age group: 20-35 years old," and "frequency of use: mostly on weekends." This information is sent to the server as basic data for subsequent processing. Input data: detailed service information. Output data: service information as basic data.

[1552] Step 2:

[1553] The server receives the service information entered by the user and analyzes it as structured data. Specifically, it uses a database management system (DBMS) and data analysis tools to convert the received data into JSON format and extract data points (e.g., age group, region, interests, etc.). Input data: Service details information. Output data: Structured data and extracted data points.

[1554] Step 3:

[1555] The emotion engine analyzes the user's emotional state at the time of input. Analysis is performed using natural language processing (NLP) technology and emotion analysis tools based on the user's input text and reaction data. For example, the Microsoft Azure text analysis API is used to recognize the user's emotional state (excitement, interest, suspicion, etc.). Input data: User's input text and reaction data. Output data: Analyzed emotion data.

[1556] Step 4:

[1557] The server launches a pre-trained generative AI model. The server inputs the analyzed data points and emotion data into the generative AI model to generate several persona candidates. This process uses a deep learning framework (such as TensorFlow or PyTorch). Input data: structured data and emotion data. Output data: generated persona candidates.

[1558] Step 5:

[1559] The server presents the generated multiple persona proposals to the user. Specifically, the persona proposals are visually displayed to the user through a UI using a web application front-end framework (such as React or Vue.js). For example, persona proposals such as "30-year-old male, engineer living in the city, commutes by bicycle" and "33-year-old female, marketing staff, goes to the gym on weekday evenings" are presented. Input data: Generated persona proposals. Output data: Persona proposals presented to the user.

[1560] Step 6:

[1561] The user selects the persona they consider most suitable from the presented options. As the user makes their selection, the emotion engine evaluates it in real time and collects emotional data. This allows for a detailed understanding of the user's true needs and emotions. Input data: User's selection of persona options. Output data: Optimal persona selection results and emotional feedback data.

[1562] Step 7:

[1563] The server saves the persona information selected by the user in a database and collects feedback from the user. The saved data is used as training data for the generative AI model in subsequent persona generation attempts, improving the accuracy of the model. The database used is an SQL-based database (e.g., MySQL or PostgreSQL) or a NoSQL database (e.g., MongoDB or Firebase). Input data: User-selected persona information and feedback data. Output data: Saved persona information and updated AI model.

[1564] (Application example 2)

[1565] 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."

[1566] Conventional persona generation systems generate personas based on static data without considering user emotions. As a result, the generated personas may not reflect the user's actual emotions and preferences, limiting the effectiveness of targeting and marketing strategies. Furthermore, to maximize the effectiveness of advertising campaigns, it is necessary to consider user emotions and preferences in the persona generation process, but no such means have been provided.

[1567] 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.

[1568] In this invention, the server includes means for a user to input information about a service, means for analyzing the input service information and extracting related data points, means for generating a plurality of persona proposals using an artificial intelligence model based on the extracted data points, means for presenting the generated persona proposals to the user, means for analyzing user emotion data in real time and reflecting the analysis result in the persona generation process, means for saving the persona proposal selected by the user and processing feedback, and means for performing ad targeting and delivering ad campaigns based on the generated persona proposals, thereby enabling real-time persona generation and targeting that reflects user emotions.

[1569] "Service Information" means details of the services you intend to provide, including your overall goals, target market, and product or service features.

[1570] "Means for analyzing the entered service information and extracting relevant data points" refers to the process of processing and analyzing the service information entered by the user to extract useful data points (e.g., age group, region, interests, etc.).

[1571] "Means for generating multiple persona proposals using an artificial intelligence model" refers to a technical means for generating multiple personas using AI technology based on extracted data points.

[1572] The "means for presenting the generated persona proposals to the user" is a technical process for presenting the generated multiple personas to the user visually or through an interface.

[1573] "Means for analyzing user emotional data in real time and reflecting it in the persona generation process" refers to a technical process for analyzing the emotional state of the user when entering service information and reflecting it in persona generation in real time.

[1574] "Means for storing user-selected persona proposals and processing feedback" refers to the technical means for storing user-selected persona proposals in a database and collecting and processing feedback from users.

[1575] "Means for targeting advertisements and delivering advertising campaigns based on the generated persona proposals" means the technical means for targeting advertisement campaigns and delivering the advertisements based on the generated personas.

[1576] The present invention is a system that recognizes user emotions and generates personas that take those emotions into account, thereby improving the targeting accuracy of advertising campaigns and enabling more effective marketing strategies.

[1577] System Overview

[1578] The system consists of the following major hardware and software components:

[1579] User devices: smartphones, tablets, etc.

[1580] Server: Data processing and persona generation

[1581] Emotion Engine: Software that analyzes user emotion data in real time

[1582] Generative AI model: Artificial intelligence that generates personas based on analytical data

[1583] Program processing

[1584] 1. Input on the user's terminal

[1585] Users use their smartphones or tablets to enter detailed information about the services they wish to offer, including, for example, the target market, product features, age group, and advertising objectives.

[1586] 2. Analysis by emotion engine

[1587] When a user inputs information, the device uses an emotion engine to collect real-time emotional data from the user, which is derived from facial expression analysis, voice analysis, touch speed, and other factors.

[1588] 3. Data processing and analysis on the server

[1589] The server receives the service information and emotion data entered by the user, converts it into structured data, and analyzes it. The extracted data points (e.g., age group, region, interests, etc.) become the basis for generating personas.

[1590] 4. Persona generation using generative AI models

[1591] The server then runs a generative AI model to generate multiple personas by inputting the analyzed data points and emotional data. The model generates personas taking the emotional data into account, providing a more realistic and useful portrayal of the target.

[1592] 5. Persona Presentation and Selection

[1593] The generated personas are presented to the user via their device, and the user can select the persona they think is most suitable. During this process, emotional data is analyzed and used as feedback.

[1594] 6. Persona-Based Ad Targeting

[1595] Based on the selected personas, advertising campaigns are designed and targeted. The ads are then linked to the appropriate distribution platforms and distributed. This targeting process allows for sophisticated strategies that reflect user sentiment.

[1596] 7. Gather feedback and refine the model

[1597] After the ad is delivered, user response data is collected and used as training data for the generative AI model, which will improve the accuracy of future persona generation.

[1598] Specific examples

[1599] Example: Advertising campaign for luxury urban bicycles

[1600] Step 1: The user enters information such as "Target market: urban areas," "Age group: 20-35 years old," and "Advertising purpose: brand awareness" into their smartphone.

[1601] Step 2: The device's emotion engine analyzes the emotion data entered by the user in real time.

[1602] Step 3: The server receives the information, converts it into structured data, and parses it.

[1603] Step 4: The generative AI model generates multiple personas based on the data.

[1604] Step 5: The generated personas are presented to the user, who then selects the most appropriate one.

[1605] Step 6: Ad targeting is performed based on the selected persona, and the actual ad campaign is delivered.

[1606] Prompt Sentence Examples

[1607] "Enter your advertising campaign information. Enter the data advertisers need for customer targeting. We also collect sentiment data in real time and generate multiple personas based on this. For example, the target audience for the "Premium Bicycle" advertising campaign is urban users aged 20-35. Based on this information, we generate appropriate personas and collect feedback."

[1608] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1609] Step 1:

[1610] Users input information about the services they wish to provide from their terminals. This information includes the target market, age group, advertising objectives, product features, etc. This information becomes the basic data for the entire system.

[1611] Input: Service information such as target market, age group, advertising purpose, product features, etc.

[1612] Output: Raw data entered by the user

[1613] Step 2:

[1614] The device sends the entered service information to the server. At the same time, the device's emotion engine analyzes the user's emotional data (facial expressions, voice, touch operation speed, etc.) in real time and sends this emotional data to the server.

[1615] Input: User service information, real-time emotion data

[1616] Output: Data points and sentiment data sent to the server

[1617] Step 3:

[1618] The server converts the received service information and emotional data into structured data and analyzes it. At this stage, data points such as target market, age group, and product features are extracted. Emotional data is also analyzed and integrated as information necessary for persona generation.

[1619] Input: Service information, raw emotion data

[1620] Output: Structured data points and parsed sentiment data

[1621] Step 4:

[1622] The server launches a generative AI model, inputting the analyzed data points and emotional data. The generative AI model generates multiple personas based on this data. This persona generation takes into account the user's emotional data to create a more specific target image.

[1623] Input: Structured data points, parsed sentiment data

[1624] Output: Multiple persona ideas generated

[1625] Step 5:

[1626] The generated persona proposals are sent from the server to the device, which then presents them to the user. The user can then select the most suitable persona, and this selection process is also analyzed by the emotion engine, with the results being fed back to the server.

[1627] Input: Generated persona ideas

[1628] Output: Persona proposals selected by the user and emotional data at the time of preference

[1629] Step 6:

[1630] The server stores the persona choices selected by the user and uses this information to target ads. An ad campaign is then set up and delivered to the target market. After the ad is delivered, user response data is also collected.

[1631] Input: Persona proposal selected by the user, emotional data at the time of preference

[1632] Output: Stored persona data, ad targeting information, and post-delivery response data

[1633] Step 7:

[1634] The server generates feedback based on the collected reaction data and uses this feedback information as training data for the generative AI model, thereby improving the accuracy of future persona generation.

[1635] Input: Post-distribution reaction data

[1636] Output: Updated training data, improved AI model

[1637] 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.

[1638] 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.

[1639] 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.

[1640] 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.

[1641] 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.

[1642] 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.

[1643] 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).

[1644] 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.

[1645] 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."

[1646] 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.

[1647] 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).

[1648] 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.

[1649] 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.

[1650] 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.

[1651] 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.

[1652] 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.

[1653] 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.

[1654] 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.

[1655] 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.

[1656] 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.

[1657] 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.

[1658] The following is further disclosed regarding the above embodiment.

[1659] (Claim 1)

[1660] a means for a user to input information about the service;

[1661] means for parsing the input service information and extracting relevant data points;

[1662] a means for generating a plurality of persona alternatives using an artificial intelligence model based on the extracted data points; and

[1663] A means for presenting the generated persona proposal to a user;

[1664] a means for storing user-selected persona proposals and processing feedback;

[1665] A system including:

[1666] (Claim 2)

[1667] 10. The system of claim 1, wherein the system converts user input into structured data and parses it.

[1668] (Claim 3)

[1669] The system of claim 1, wherein services are improved and optimized based on the generated persona proposals.

[1670] "Example 1"

[1671] (Claim 1)

[1672] a means for a user to input information about the service;

[1673] A means for converting input service information into structured data and analyzing it;

[1674] a means for generating multiple persona alternatives using a generative AI model based on the analyzed data points; and

[1675] A means for presenting the generated persona proposal to a user;

[1676] a means for saving user-selected persona ideas and processing feedback;

[1677] A system including:

[1678] (Claim 2)

[1679] 2. The system of claim 1, wherein the system converts user input data into structured data, such as JSON format, and extracts data points.

[1680] (Claim 3)

[1681] The system of claim 1, wherein services are improved and optimized based on the generated persona proposals.

[1682] "Application Example 1"

[1683] (Claim 1)

[1684] a means for a user to input information about the service;

[1685] means for parsing the input service information and extracting relevant data points;

[1686] a means for generating a plurality of persona alternatives using an artificial intelligence model based on the extracted data points; and

[1687] A means for presenting the generated persona proposal to a user;

[1688] a means for storing user-selected persona proposals and processing feedback;

[1689] A means for presenting persona proposals generated from the analysis data to a smartphone application;

[1690] a means for storing the user-selected persona ideas in a cloud database;

[1691] A system including:

[1692] (Claim 2)

[1693] 10. The system of claim 1, wherein the system converts user input into structured data and parses it.

[1694] (Claim 3)

[1695] 10. The system of claim 1, further comprising: improving targeting of advertising campaigns based on the generated persona proposals.

[1696] "Example 2: Combining Emotion Engines"

[1697] (Claim 1)

[1698] a means for a user to input information about the service;

[1699] means for parsing the input service information and extracting relevant data points;

[1700] means for analyzing the emotional state of a user at the time of input;

[1701] a means for generating a plurality of proposed personas using an artificial intelligence model based on the extracted data points and sentiment data;

[1702] A means for presenting the generated persona proposal to a user;

[1703] a means for storing user-selected persona proposals and processing feedback;

[1704] A system including:

[1705] (Claim 2)

[1706] 10. The system of claim 1, wherein the system converts user input into structured data and parses it.

[1707] (Claim 3)

[1708] The system of claim 1, wherein services are improved and optimized based on the generated persona proposals.

[1709] "Application example 2 when combining emotion engines"

[1710] (Claim 1)

[1711] a means for a user to input information about the service;

[1712] means for parsing the input service information and extracting relevant data points;

[1713] a means for generating a plurality of persona alternatives using an artificial intelligence model based on the extracted data points; and

[1714] A means for presenting the generated persona proposal to a user;

[1715] A means of analyzing user emotional data in real time and reflecting it in the persona generation process;

[1716] a means for storing user-selected persona proposals and processing feedback;

[1717] A means for targeting advertisements based on the generated persona proposals and delivering advertisement campaigns;

[1718] A system including:

[1719] (Claim 2)

[1720] 10. The system of claim 1, wherein the system converts user input into structured data and parses it.

[1721] (Claim 3)

[1722] The system of claim 1, wherein services are improved and optimized based on the generated persona proposals. [Explanation of symbols]

[1723] 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 a user to input information about the service; means for parsing the input service information and extracting relevant data points; a means for generating a plurality of persona alternatives using an artificial intelligence model based on the extracted data points; and A means for presenting the generated persona proposal to a user; a means for storing user-selected persona proposals and processing feedback; A system including:

2. 10. The system of claim 1, wherein the user input is converted into structured data and parsed.

3. The system according to claim 1, wherein the system improves and optimizes services based on the generated persona proposals.

Images