System

Abstract

A system is provided.SOLUTION: A system comprising: means for inputting specific persona information; means for inputting question content; means for inputting the number of questionnaires to be generated; means for automatically generating a questionnaire using a generative AI model based on the input information; and means for outputting the generated questionnaire.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] Traditionally, it has been difficult for companies to efficiently collect surveys targeting specific personas. Finding specific personas requires a great deal of effort and expense, and designing and distributing surveys to gather the required sample size is also extremely time-consuming. It is also not easy to tailor the survey content to suit the target audience. This can delay data collection for product and service improvement and development, hindering the company's growth. The object of the present invention is to solve these problems and provide a means for efficiently and effectively generating and collecting surveys. [Means for solving the problem]

[0005] The present invention solves the aforementioned problems by the following means. The system includes a means for inputting specific persona information, a means for inputting question content, a means for inputting the number of questionnaires to be generated, a means for automatically generating questionnaires using a generative AI model based on the input information, and a means for outputting the generated questionnaires. Furthermore, the system includes a means for searching a database for similar personas based on the input persona information, generating related questionnaire items, and a means for adjusting the question content by associating it with the persona, thereby enabling efficient generation of targeted questionnaires. This system allows companies to effectively create and collect questionnaires without significant effort or expense, enabling them to quickly improve and develop products and services.

[0006] "Persona information" is detailed information about a fictional character who represents a specific target user, and is data that includes attributes such as "age," "occupation," and "hobbies."

[0007] "Question content" refers to a set of specific questions that are asked of respondents in a questionnaire.

[0008] "Number of questionnaires" is the total number of questionnaires that will be generated based on the specified sample size.

[0009] A "generative AI model" is an artificial intelligence model that automatically generates new questionnaires using training data from a database.

[0010] A "database" is a collection of information that is systematically collected and managed, such as persona information and past survey data.

[0011] A "survey item" refers to an individual question or option presented to a respondent.

[0012] The "output means" refers to a device or program that has functions such as display, printing, and downloading to provide the generated questionnaire to the user.

[0013] An "augmentation method" is a method or algorithm that tailors the input questions to match the target persona.

[0014] "Data collection" is the process of obtaining survey responses from respondents and storing them for organization and analysis. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0023] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0036] The system of the present invention uses a generative AI model to efficiently and automatically generate questionnaires by inputting specific persona information and specifying the question content and number of questionnaires to be generated. This system allows companies and marketers to quickly create targeted questionnaires while significantly reducing labor and costs.

[0037] Program processing

[0038] Entering persona information

[0039] The user connects to the system's input form using a terminal and enters specific persona information such as "age," "occupation," and "hobbies." This information is used for subsequent processing within the system.

[0040] Enter your question

[0041] The user enters the questions they want to ask in the survey in multiple lines into the input form. For example, they can enter specific questions such as "What is your favorite drink?" or "What is the most important thing about a cafe?"

[0042] Enter the number of questionnaires

[0043] The user inputs the number of surveys they want to generate, for example, "50" or "100," specifying the number of samples they require.

[0044] Calling the generative AI model and generating a survey

[0045] The server calls the generative AI model based on the persona information, question content, and number of pages to be generated obtained from the user. This model automatically generates new questionnaires based on learning data such as past survey data. The generative AI model searches for similar personas in an existing database related to the persona information and creates related questionnaire items. It then associates the entered questions with the persona and adjusts them to generate a diverse set of questionnaires.

[0046] Output of generated results

[0047] The generated questionnaire is saved on the server and the specified number of questionnaires are prepared. The questionnaires are presented to users in formats such as PDF or Excel, and can be downloaded by the users. The generated questionnaires can also be distributed physically or online.

[0048] Specific examples

[0049] A marketer for a coffee shop chain

[0050] 1. Enter persona information

[0051] The user (marketing staff) enters "female in her 20s," "university student," and "hobby is visiting cafes."

[0052] 2. Enter your question

[0053] Enter "What is your usual drink?" and "What is the most important thing for you in a cafe?"

[0054] 3. Enter the number of questionnaires

[0055] Enter "100" as the number of samples required.

[0056] 4. Generate a survey

[0057] The server calls the generative AI model and automatically generates 100 questionnaires based on the specified persona information and questions.

[0058] 5. Presentation of results

[0059] The generated questionnaire is provided to the user in a downloadable format, which the person in charge can use to start the survey.

[0060] Through the above process, it is possible to efficiently collect questionnaires suited to specific personas and use them to improve and develop products and services. This system provides a means for generating such questionnaires quickly and effectively.

[0061] The processing flow will be explained below.

[0062] Step 1:

[0063] The user accesses the system's input form using a terminal and enters specific persona information, such as attributes such as "age," "occupation," and "hobbies."

[0064] Step 2:

[0065] The user enters the questions they want to ask in the survey into the input form. Enter specific questions such as "What is your favorite drink?" or "What is the most important thing for you in a cafe?"

[0066] Step 3:

[0067] The user enters the number of surveys they want to generate, for example, "50" or "100," to specify the number of samples required.

[0068] Step 4:

[0069] The server receives the specific persona information, question content, and number of copies to be generated sent by the user.

[0070] Step 5:

[0071] The server calls the generative AI model, which learns from existing persona data and past survey data in the database.

[0072] Step 6:

[0073] The generative AI model searches the database for similar personas based on the persona information and generates related questionnaire items, resulting in the creation of initial questionnaire items according to the persona information.

[0074] Step 7:

[0075] The server uses a generative AI model to associate the questions entered by the user with the persona and adjust them, thereby generating questions optimized for each persona.

[0076] Step 8:

[0077] The server generates the specified number of questionnaires. The generative AI model automatically generates a diverse set of questionnaires based on the adjusted question content, adding variation to each questionnaire.

[0078] Step 9:

[0079] The server saves the generated questionnaire and prepares it for presentation to the user. The generated questionnaire is output in a common file format (PDF, Excel, etc.).

[0080] Step 10:

[0081] The user downloads the generated survey. The user accesses the results page of the system using a terminal and downloads the generated survey, which allows for physical distribution or online distribution of the survey.

[0082] Example 1

[0083] 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."

[0084] Traditional survey creation methods require a lot of time and effort for companies and marketers to create surveys that are appropriate for their target personas. Furthermore, creating surveys manually is prone to human error, making it difficult to operate efficiently.

[0085] 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.

[0086] In this invention, the server includes means for inputting specific attribute information, means for inputting question content, means for inputting the number of questionnaires to be generated, means for automatically generating questionnaires using a generative AI model based on the input information, means for saving and outputting the generated questionnaires, and means for making the generated questionnaires available for download. This enables companies and marketers to efficiently automatically generate high-quality questionnaires and quickly utilize them.

[0087] "Attribute information" refers to individual characteristics of a specific target person, such as age, occupation, hobbies, etc.

[0088] "Question content" refers to the specific content of the questions posed to the target person in the questionnaire.

[0089] A "generative AI model" refers to an artificial intelligence model that automatically generates new questionnaires based on past data and learning data.

[0090] A "database" refers to a system that stores information for searching for similar person images based on specific attribute information.

[0091] "Downloadable means" refers to the technical mechanism that allows a user to save the generated survey to a device.

[0092] "Means for storage and output" refers to the technical mechanism by which the generated survey is stored in a particular format and provided to the user.

[0093] The present invention relates to a system for efficiently generating questionnaires using a generative AI model. This system inputs attribute information, question content, and the number of questionnaires to be generated, automatically generates questionnaires based on the input information, and provides the generated questionnaires to users. Specific embodiments for implementing the present invention are described below.

[0094] The user accesses the system's web interface using a terminal and inputs attribute information (age, occupation, hobbies, etc.). Next, the user inputs the questions and then specifies the number of questionnaires to be generated. This web interface is provided through a browser.

[0095] Once the user has completed entering the attribute information, question content, and number of questionnaires, the server receives this data and calls the generative AI model. This generative AI model automatically generates new questionnaires based on past survey data. Specifically, the generative AI model searches for similar persona profiles from past data and automatically creates related question items. It also adjusts the entered question content by relating it to the persona information, generating a diverse set of questionnaires.

[0096] The generated survey is saved on the server and output in a specified format (usually PDF or Excel format). This output survey is provided in a format that users can download. Users can save the generated survey to their devices by accessing the system again and clicking the download link. Users can then print these surveys or distribute them online.

[0097] As a concrete example, consider a situation where the target audience is a marketing manager for a coffee shop chain. Below is an example of the concrete example and a prompt sentence.

[0098] Specific examples

[0099] 1. Enter persona information

[0100] The user (marketing staff) enters "female in her 20s," "university student," and "hobby is visiting cafes."

[0101] 2. Enter your question

[0102] Enter "What is your usual drink?" and "What is the most important thing for you in a cafe?"

[0103] 3. Enter the number of questionnaires

[0104] Enter "100" as the number of samples required.

[0105] 4. Generate a survey

[0106] The server calls the generative AI model and automatically generates 100 questionnaires based on the specified persona information and question content.

[0107] 5. Presentation of results

[0108] The generated questionnaire is provided to the user in a downloadable format, which the person in charge can use to start the survey.

[0109] Prompt Sentence Examples

[0110] prompt:

[0111] Generate your survey based on the following persona information:

[0112] Persona: Female in her 20s, university student, hobby is cafe hopping

[0113] Questions:

[0114] 1. What is your favorite drink?

[0115] 2. What is the most important thing to you about your cafe?

[0116] Number of cards generated: 100

[0117] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0118] Step 1: Enter your persona information

[0119] 1. The user uses a terminal to access the system's web interface.

[0120] 2. The user accesses a form to enter attribute information.

[0121] 3. The user enters attribute information such as "age," "occupation," and "hobbies," and clicks the "Submit" button.

[0122] 4. The server receives the entered attribute information and stores it in the database.

[0123] Specific operation: The user opens a browser and accesses the system's URL. He enters "25 years old" in the "Age" field, "University student" in the "Occupation" field, and "Cafe hopping" in the "Hobby" field, and clicks the submit button. The server saves this information in the database.

[0124] Step 2: Enter the question content

[0125] 1. After submitting the persona information, the user is redirected to a form where they can enter their questions.

[0126] 2. The user enters the questions they want to ask in the survey.

[0127] 3. The user enters the question content on multiple lines and clicks the "Submit" button.

[0128] 4. The server receives the entered questions, associates them with attribute information, and stores them in a database.

[0129] Specific operation: Enter "What is your usual drink?" in the "Question 1" field and "What is the most important thing for you in a cafe?" in the "Question 2" field, then click the submit button. The server associates these questions with attribute information and saves them in the database.

[0130] Step 3: Enter the number of surveys

[0131] 1. After submitting the questionnaire, the user is redirected to a form where they can enter the number of surveys.

[0132] 2. The user enters the number of questionnaires to be generated.

[0133] 3. The user confirms the number of copies entered and clicks the "Submit" button.

[0134] 4. The server receives the number of sheets entered and stores it in a database along with the attribute information and question content.

[0135] What happens: You enter "100" in the "Quantity" field and click the submit button. The server stores this information in a database.

[0136] Step 4: Invoke the generative AI model and generate a survey

[0137] 1. Once the user has entered all the data, the server calls the generative AI model based on the attribute information, question content, and number of sheets to be generated.

[0138] 2. The generative AI model references past survey data and automatically generates a new survey based on the input information.

[0139] 3. The generative AI model searches the database for similar person profiles based on attribute information and generates relevant questions.

[0140] 4. The entered questions are adjusted in relation to attribute information to generate a diverse questionnaire set.

[0141] Specific operation: The server passes the attribute information "25 years old," "university student," and "cafe hopping" along with the questions "What is your usual drink?" and "What is the most important thing for you in a cafe?" to the generative AI model. The generative AI model analyzes similar patterns from past survey data and generates 100 new surveys.

[0142] Step 5: Output the generated results

[0143] 1. The generated questionnaire is saved on the server and output in the specified format.

[0144] 2. The server saves the generated survey in PDF or Excel format.

[0145] 3. The user receives a notification from the server and retrieves the generated survey via a download link.

[0146] 4. Users download the survey to their devices and print or distribute it online as needed.

[0147] Specific operation: The server saves the generated 100 questionnaires in PDF format and sends a notification to the user. The user clicks the download link to download the questionnaire and use it within the company.

[0148] The above are the specific processing steps of this system.

[0149] (Application example 1)

[0150] 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."

[0151] Conventional survey generation systems have difficulty quickly and efficiently generating questions suited to specific personas, and lack the functionality to distribute, collect, and analyze the generated surveys via the Internet. This makes it difficult to effectively collect survey results from target demographics in advertising and marketing campaigns, resulting in the inability to maximize the effectiveness of the campaign.

[0152] 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.

[0153] In this invention, the server includes means for inputting specific persona information, means for inputting question content, means for inputting the number of questionnaires to be generated, means for automatically generating questionnaires using a generative AI model, means for distributing the generated questionnaires via the Internet, means for collecting and analyzing the results of the generated questionnaires, and means for outputting the generated questionnaires. This makes it possible to quickly and efficiently generate, distribute, collect, and analyze questionnaires tailored to targets.

[0154] "Specific persona information" is information about a specific target demographic, and includes attribute information such as age, gender, occupation, and hobbies.

[0155] "Question content" refers to the wording of the items asked to respondents in the questionnaire.

[0156] The "number of questionnaires to be generated" refers to the number of questionnaire sets to be generated, and more specifically, indicates the number of samples to be generated.

[0157] A "generative AI model" is an artificial intelligence model that automatically generates a questionnaire based on the input persona information and question content.

[0158] "Means of automatic generation" refers to the process of creating a questionnaire using a generative AI model, taking persona information and question content as input.

[0159] "Means of distribution via the Internet" refers to a method of sending the generated questionnaire to subjects via the Internet.

[0160] "Means of collection and analysis" refers to the process of receiving and analyzing the response data from the distributed questionnaire.

[0161] "Means of output" refers to a method of providing the generated questionnaire to the user in a format such as PDF or Excel.

[0162] This invention is a system that allows marketers and advertising agencies to efficiently generate, distribute, collect, and analyze targeted questionnaires. Specific methods for implementing this system are described below.

[0163] Hardware and Software Configuration

[0164] This system is realized mainly using the following hardware and software.

[0165] Hardware: smartphones, tablets, servers

[0166] Software: Python, TensorFlow, Flask (server-side framework)

[0167] System processing procedure

[0168] 1. User Input

[0169] Users connect to the system using a smartphone or tablet and enter specific persona information, questions, and the number of questionnaires to be generated. Persona information includes age, gender, occupation, and hobbies.

[0170] 2. Questionnaire generation

[0171] The server receives the information entered by the user and calls a generative AI model based on that information. This generative AI model automatically generates the specified number of questionnaires based on the entered persona information and questions. The generative AI model learns from past survey data, enabling it to generate highly accurate surveys.

[0172] 3. Survey distribution

[0173] The server distributes the generated survey to the designated target audience via the Internet, using email, social media, advertising platforms, etc.

[0174] 4. Collection and analysis of survey results

[0175] The response data from the distributed survey is sent to a server where it is collected and analyzed. The collected data is analyzed using statistical analysis tools to be used in marketing strategies.

[0176] 5. Output of generated results

[0177] The generated questionnaire is provided to the user in formats such as PDF or Excel, and can be downloaded and used.

[0178] Specific examples

[0179] A marketer wants to generate 100 questionnaires for an advertising campaign targeting a persona of a man in his 20s whose hobby is sports:

[0180] 1. Enter persona information

[0181] The user enters "Persona information: 20s, male, sports."

[0182] 2. Enter your question

[0183] Enter the questions "Which sports brand do you like?" and "What is the most important thing to consider when choosing sportswear?"

[0184] 3. Enter the number of questionnaires

[0185] The user enters "Number of surveys to generate: 100".

[0186] 4. Examples of prompt sentences

[0187] Enter the following as the prompt:

[0188] Persona information: 20s, male, sports

[0189] Questions asked:

[0190] 1. Which sports brand do you like?

[0191] 2. What is the most important thing to consider when choosing sportswear?

[0192] Number of copies generated: 100

[0193] By distributing the questionnaires generated in this way via the Internet and collecting and analyzing the results, an effective advertising campaign can be realized.

[0194] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0195] Step 1:

[0196] Users connect to the system's input form using a smartphone or tablet and enter specific persona information such as age, gender, occupation, and hobbies. The persona information entered by the user becomes the reference data for identifying targets in subsequent processing.

[0197] Step 2:

[0198] The user inputs questions based on the information they want to obtain. Questions include specific questions such as, "Which brand of clothing do you usually buy?" or "What is the most important point when choosing sportswear?" The input questions are sent to the server as data to be used in generating the questionnaire.

[0199] Step 3:

[0200] The user inputs the number of surveys they want to generate, for example, a sample size such as "50" or "100." This number is sent to the server to determine the number of survey sets to generate.

[0201] Step 4:

[0202] The server calls the generative AI model based on the persona information, question content, and number of questionnaires received from the user. The generative AI model searches for similar personas from an existing database related to persona information, adjusts the input questions, and automatically generates a diverse set of questionnaires. The generative AI model uses TensorFlow and utilizes past survey data as learning data.

[0203] Step 5:

[0204] The server distributes the generated survey via the Internet, using email, social media, advertising platforms, etc., to send the survey to the designated target audience. The distribution method is realized through the Flask framework.

[0205] Step 6:

[0206] The user's device receives the survey results. The server collects the data and analyzes it using statistical analysis tools. This provides insights into the preferences and opinions of the target demographic.

[0207] Step 7:

[0208] The server converts the generated survey into PDF or Excel format and provides it for users to download, so that users can use the survey in their advertising campaigns and marketing strategies.

[0209] 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.

[0210] This invention combines an emotion engine with a system that automatically generates questionnaires using a generative AI model by inputting specific persona information and specifying the question content and number of questionnaires to be generated. This system recognizes the user's emotions and further optimizes the questionnaire content based on those emotions.

[0211] Program processing

[0212] Entering persona information

[0213] The user accesses the system's input form using a terminal and enters specific persona information, including attribute information such as "age," "occupation," and "hobbies."

[0214] Enter your question

[0215] The user enters the questions they want to ask in the survey into the input form. Enter specific questions such as "What is your favorite drink?" or "What is the most important thing for you in a cafe?"

[0216] Enter the number of questionnaires

[0217] The user inputs the number of surveys they want to generate. For example, they specify the required sample size, such as "50" or "100."

[0218] emotion recognition

[0219] The device is equipped with an emotion engine that recognizes the user's emotions from facial expressions and voice input. For example, it analyzes data obtained through a camera and microphone to detect emotions such as whether the user is relaxed or stressed.

[0220] Using sentiment data

[0221] The server receives the emotion data recognized by the emotion engine. Based on the received emotion data, persona information, question content, and number of pages to be generated, it calls a generative AI model. This model optimizes the questionnaire content by reflecting the emotion data.

[0222] Generate questionnaire items

[0223] The generative AI model uses persona information to search a database for similar profiles and generate relevant survey questions, adjusting the tone and difficulty of the questions based on perceived emotions.

[0224] Adjustment of survey content

[0225] The generative AI model adjusts the questions entered by the user by linking them to persona information and emotional data, optimizing the questions to make them easier for the user to answer by relaxing the questions or asking more detailed questions depending on the emotion.

[0226] Generate a survey

[0227] The server generates the specified number of questionnaires, and the generative AI model creates a set of variations, each of which reflects persona information and emotional data.

[0228] Output of generated results

[0229] The generated questionnaire is stored on the server and prepared for presentation to the user. The generated results are output in formats such as PDF or Excel, which the user can download.

[0230] Specific examples

[0231] A marketer for a coffee shop chain

[0232] 1. Enter persona information

[0233] The user (marketing staff) enters "female in her 20s," "university student," and "hobby is visiting cafes."

[0234] 2. Enter your question

[0235] Enter "What is your usual drink?" and "What is the most important thing for you in a cafe?"

[0236] 3. Enter the number of questionnaires

[0237] Enter "100" as the number of samples required.

[0238] 4. Emotion recognition

[0239] The device analyzes the user's facial expressions and voice to recognize relaxed emotions.

[0240] 5. Use of Emotional Data

[0241] The server receives the emotion data and invokes a generative AI model, which uses the emotion data to adjust the tone of the question to be a little friendlier.

[0242] 6. Generate questionnaire items

[0243] Generate relevant questionnaire items from the database based on persona information.

[0244] 7. Adjustment of survey content

[0245] Tailor the questions to relate to the user's emotional data, making them more specific, such as "What do you like to drink when you want to relax?"

[0246] 8. Generate a survey

[0247] Generate 100 different questionnaires.

[0248] 9. Output of generated results

[0249] The user downloads the survey and begins the survey.

[0250] In this way, by generating questionnaires that combine emotion recognition functions, this system makes it easier for users to answer and achieves highly accurate data collection.

[0251] The processing flow will be explained below.

[0252] Step 1:

[0253] The user accesses the system's input form using a terminal and enters specific persona information, specifically attribute information such as "age," "occupation," and "hobbies."

[0254] Step 2:

[0255] The user enters the questions they want to ask in the survey into the input form. For example, they enter specific questions such as "What is your favorite drink?" or "What is the most important thing about a cafe?"

[0256] Step 3:

[0257] The user inputs the number of surveys they want to generate. For example, they specify the required sample size, such as "50" or "100."

[0258] Step 4:

[0259] The device monitors the user's emotional state within the input form, capturing the user's facial expressions through the camera and collecting audio data through the microphone.

[0260] Step 5:

[0261] The device's built-in emotion engine analyzes the captured facial and voice data to recognize the user's emotions, such as whether the user is relaxed or stressed.

[0262] Step 6:

[0263] The device sends the recognized emotion data to the server, which receives the emotion data along with the user's persona information, question content, and number of images generated.

[0264] Step 7:

[0265] The server calls the generative AI model, which prepares to automatically generate a questionnaire based on persona information, question content, and emotion data.

[0266] Step 8:

[0267] The server uses a generated AI model to search a database for similar profiles based on the persona information and generate relevant questionnaire items, adjusting the tone and difficulty of the questions based on the perceived emotions.

[0268] Step 9:

[0269] The server uses a generated AI model to correlate the questions entered by the user with persona information and emotional data, adjusting the questions to a more relaxed tone or more detailed questions depending on the emotion.

[0270] Step 10:

[0271] The server generates the specified number of questionnaires, and the generative AI model creates a set of variations, each of which reflects persona information and emotional data.

[0272] Step 11:

[0273] The server saves the generated questionnaire and prepares it for delivery to the user. The generated results are output in a format such as PDF or Excel, and can be downloaded by the user.

[0274] Step 12:

[0275] The user accesses the system's results page using a terminal and downloads the generated survey, which can then be distributed physically or online.

[0276] Example 2

[0277] 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."

[0278] Conventional survey generation systems are unable to optimize survey content taking user emotions into account, which can affect response rates and response quality. Even when using a generation AI model based on persona information and question content, it is difficult to generate a survey that appropriately reflects emotional data. It is necessary to solve these problems and generate more accurate surveys.

[0279] 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.

[0280] In this invention, the server includes a means for inputting specific person information, a means for inputting question content, a means for inputting the number of surveys to be generated, a means for recognizing the user's emotions and optimizing the survey content based on the emotions, a means for automatically generating a survey using a generative artificial intelligence model based on the input information, and a means for outputting the generated survey, thereby enabling the generation of a survey optimized according to the user's emotions.

[0281] "Specific personal information" is attribute information about the survey subject, such as the user's age, occupation, hobbies, etc.

[0282] "Questions" are specific questions you want to ask in the survey.

[0283] The "number of surveys to be generated" is the specific number of questionnaires you want to generate, and the number of samples you need.

[0284] A "generative artificial intelligence model" is an AI model that automatically generates a questionnaire based on input information.

[0285] "Means to recognize emotions and optimize survey content based on that" refers to a function that acquires and analyzes users' emotional data in real time and adjusts the tone and difficulty of the survey content to reflect that.

[0286] "Means for outputting the generated survey" is a function that provides the generated questionnaire to the user in a format that can be used by the user (such as PDF or Excel).

[0287] "Means for searching for similar person profiles from a database" is a function for searching for similar data entries in a database based on persona information.

[0288] The "means for adjusting the question content by relating it to personal information" is a function for optimizing the question content based on the input personal information and adjusting it to a format that is easy for the user to answer.

[0289] The present invention relates to a system that automatically generates an optimized questionnaire by inputting specific personal information and question content and recognizing the user's emotions. This system is realized through interactions between a server, terminals, and users.

[0290] System configuration

[0291] The system consists of the following main components:

[0292] 1. Terminal

[0293] The device is equipped with an interface that allows users to access an input form and enter the necessary information. The device is also equipped with an emotion engine that captures and analyzes the user's facial expressions and voice in real time through a camera and microphone. The specific hardware used includes a camera, microphone, and display.

[0294] 2. Server

[0295] The server includes a function for generating questionnaires using a generative artificial intelligence model based on the emotion data recognized by the emotion engine, the input personal information, the question content, and the number of questionnaires to be generated. The server also includes an output means for providing the generated questionnaires to users. Related software includes a database management system and an AI model execution environment.

[0296] Operational Overview

[0297] The user uses a terminal to access the system's input form and enters specific personal information (e.g., age, occupation, hobbies). Next, the user enters the specific questions they want to ask in the survey and also specifies the number of surveys they want to generate. The terminal uses a camera and microphone to capture the user's facial expressions and voice, which is then analyzed by an emotion engine to generate emotional data for the user. This emotional data is sent to the server and input into the generative artificial intelligence model along with the persona information, questions, and number of surveys to be generated.

[0298] The generative AI model searches a database for similar personas based on persona information and generates relevant questionnaire items. The tone and difficulty of the questions are adjusted based on the recognized emotional data. The generated questionnaire is stored on a server and provided to users in downloadable formats (PDF or Excel).

[0299] Specific examples

[0300] For example, consider the following scenario where a marketer for a coffee shop chain types:

[0301] 1. Enter your persona information:

[0302] The user enters "female in her 20s," "university student," and "hobby is visiting cafes."

[0303] 2. Enter your question:

[0304] Enter "What is your usual drink?" and "What is the most important thing for you in a cafe?"

[0305] 3. Enter the number of surveys:

[0306] Enter "100" as the number of samples required.

[0307] 4. Emotion recognition:

[0308] The device analyzes the user's facial expressions and voice to recognize relaxed emotions.

[0309] 5. Use of Emotional Data:

[0310] The server receives the emotion data and invokes a generative AI model, which uses the emotion data to adjust the tone of the question to be a little friendlier.

[0311] 6. Generate questionnaire items:

[0312] Generate relevant questionnaire items from the database based on persona information.

[0313] 7. Survey Content Adjustment:

[0314] Tailor the questions to relate to the user's emotional data, making them more specific, such as "What do you like to drink when you want to relax?"

[0315] 8. Generate the survey:

[0316] Generate 100 different questionnaires.

[0317] 9. Generated output:

[0318] The user downloads the survey and begins the survey.

[0319] Prompt Sentence Examples

[0320] "Persona information: Female, university student in her 20s, whose hobby is visiting cafes. Questions: What is her usual drink? What is the most important thing about a cafe? Emotional data: Relaxed. Number of surveys to generate: 100. Based on this information, please generate 100 surveys in a friendly tone."

[0321] In this way, the system utilizes user input information and emotional data to automatically generate optimized questionnaires.

[0322] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0323] Step 1:

[0324] The terminal displays the system's input form to the user and asks them to enter specific personal information (e.g., age, occupation, hobbies). Specifically, input fields on the display are used to collect information such as "25 years old," "office worker," and "reading." The entered personal information is then sent to the server by the terminal.

[0325] Step 2:

[0326] The terminal displays a field for the user to enter questions. The user enters the specific questions they want to ask in the survey. For example, they can enter questions such as "How do you usually spend your holidays?" or "What is your favorite genre of book?" The entered questions are then sent to the server.

[0327] Step 3:

[0328] The terminal displays a field for the user to enter the number of surveys they want to generate. The user enters the number of surveys to generate (e.g., "100"). This information is also sent to the server.

[0329] Step 4:

[0330] The device uses a camera and microphone to capture the user's facial expressions and voice in real time, which are then analyzed by an emotion engine. This analysis generates emotion data such as relaxation or stress, which is then sent from the device to a server.

[0331] Step 5:

[0332] The server calls the generative AI model based on the received emotion data, person information, question content, and number of pages to be generated, and generates a prompt. For example, a prompt might include "Persona information: 25 years old, office worker, hobby is reading. Question content: How do you usually spend your holidays? Emotion data: Relaxed. Number of questionnaires to be generated: 100." This prompt is input into the generative AI model.

[0333] Step 6:

[0334] The generative AI model searches a database for similar profiles based on the prompt and generates relevant questionnaire items, such as "specific activities you usually do on your vacation" or "the genre of books you read when relaxing." The generated questionnaire items are saved on the server.

[0335] Step 7:

[0336] The generative AI model adjusts the tone and difficulty of the questions based on the emotional data. For example, if you are feeling relaxed, the question might be, "What books do you read when you want to relax?" This adjustment is also saved on the server.

[0337] Step 8:

[0338] The server generates the specified number of questionnaires. For example, 100 questionnaires are generated, each containing different questions and tones. This generated data is stored on the server.

[0339] Step 9:

[0340] The server outputs the generated survey in PDF or Excel format and provides a download link to the user, who clicks the link to download the survey and begin the survey.

[0341] (Application example 2)

[0342] 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."

[0343] Conventional questionnaire generation systems generate a uniform questionnaire based on the persona information and question content entered by the user, which does not take into account the user's emotional state or ease of response, making it difficult to collect accurate data. Furthermore, the questionnaire questions are not optimized to match the user's emotions, which can cause respondents to feel stressed or less motivated to answer. Furthermore, there is a lack of systems that can efficiently generate a variety of questionnaires.

[0344] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting specific person attribute information, means for inputting question content, means for inputting the number of questionnaires to be generated, means for recognizing emotions during input using an emotion recognition engine installed in the terminal, means for optimizing question content based on the recognized emotions, means for automatically generating questionnaires using a generative AI model based on the input information, and means for outputting the generated questionnaire. As a result, by recognizing the user's emotions and optimizing the question content based on them, it is possible to generate questionnaires that are easy to answer and have high accuracy.

[0345] "Specific person attribute information" is attribute information related to a specific individual, such as age, occupation, and hobbies.

[0346] The "question content" refers to the specific questions you want to ask in the questionnaire.

[0347] "Number of questionnaires to generate" is the number of questionnaires that the generative AI model will automatically generate, as specified by the user.

[0348] An "emotion recognition engine" is an engine that analyzes the user's facial expressions and voice while inputting data and recognizes their emotions.

[0349] "Optimizing question content" means adjusting the tone and difficulty of questions based on perceived sentiment.

[0350] A "generative AI model" is an artificial intelligence model that automatically generates a questionnaire based on input information.

[0351] "Automatically generating a questionnaire" means that the generative AI model creates a questionnaire based on the input personal attribute information, question content, and recognized emotion data.

[0352] "Outputting a questionnaire" means generating data in a format such as PDF or Excel in order to present the generated questionnaire to the user.

[0353] The present invention relates to a system that automatically generates an optimized questionnaire by inputting specific person attribute information and question content and utilizing an emotion recognition engine. The system configuration and examples of the present invention will be described in detail below.

[0354] System Configuration

[0355] The system of the present invention includes the following major components:

[0356] 1. Terminal: A device that allows a user to input information. Examples include tablets and interactive displays, and are equipped with a camera and microphone.

[0357] 2. Emotion Recognition Engine: Software that analyzes the user's facial expressions and voice to recognize emotions. Specifically, it uses the Hugging Face Transformers emotion analysis pipeline and OpenCV.

[0358] 3. Server: Calls the generative AI model based on persona information, question content, number of sheets to be generated, and emotional data, and automatically generates an optimized questionnaire.

[0359] 4. Generative AI model: An artificial intelligence model that automatically generates questionnaires based on user-entered information and emotion data. Hugging Face Transformers and TextBlob are used.

[0360] 5. Database: A database for searching for similar person images based on the entered person attribute information.

[0361] Data processing and calculation

[0362] The server processes the data in the following steps:

[0363] 1. Collecting personal attribute information: The user enters personal attribute information such as age, occupation, and hobbies into an input form on the terminal.

[0364] 2. Collecting questions: Users input the questions they want to ask.

[0365] 3. Emotion recognition: The device's camera and microphone capture the user's facial expressions and voice, and the emotion recognition engine analyzes them to recognize emotions.

[0366] 4. Question Optimization: Optimize questions and adjust the tone and difficulty of questions based on perceived sentiment.

[0367] 5. Questionnaire generation: Use generative AI models to automatically generate questionnaires.

[0368] 6. Questionnaire output: The generated questionnaire can be output in formats such as PDF or Excel and made available for download by users.

[0369] Examples of specific examples and prompts

[0370] As a concrete example, consider the case where a marketing manager at a brick-and-mortar store wants to survey customers at a cafe.

[0371] The marketing staff enters the following information into the input form on the terminal:

[0372] Persona information: "Female in her 20s," "University student," "Hobby is visiting cafes"

[0373] Questions included: "What is your usual drink?" and "What is the most important thing for you in a cafe?"

[0374] The emotion recognition engine recognizes the agent's relaxed emotions and adjusts the tone of the questions to be a little friendlier. Based on the information and emotional data entered by the user, the generative AI model automatically generates 50 optimized questionnaires.

[0375] An example prompt is:

[0376] Persona information: Female in her 20s, university student, enjoys visiting cafes

[0377] Questions: What is your favorite drink? What is the most important thing for you in a cafe?

[0378] Emotion: Relaxed

[0379] Number of questionnaires: 50

[0380] This makes it possible to recognize the user's emotions and optimize the content of the questions based on them, thereby generating highly accurate questionnaires that are easy to answer.

[0381] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0382] Step 1:

[0383] The user accesses an input form on the terminal and inputs personal attribute information such as age, occupation, hobbies, etc. This allows the system to collect basic information about the user and sends this information to the server for use in the next step. The input data is text information such as age, occupation, hobbies, etc., and the server saves it as personal attribute information.

[0384] Step 2:

[0385] The user enters the question they want to ask into the input form on the device. At this time, the question is a specific text question, such as "What is your usual drink?" or "What is the most important thing for you in a cafe?" This is also sent to the server. The server saves this input data as the question.

[0386] Step 3:

[0387] The user inputs the number of questionnaires to be generated in a numerical format. For example, "50" or "100" is specified. This numerical data is also sent to the server, and the server saves it as the number of questionnaires to be generated.

[0388] Step 4:

[0389] The device's emotion recognition engine analyzes the user's facial expressions and voice to recognize their emotions in real time. Specifically, the device's camera and microphone are used to capture the user's facial expression data and voice data, which are then analyzed by an emotion recognition algorithm (e.g., the Hugging Face Transformers emotion analysis pipeline). The results of this analysis are sent to the server as emotion labels, such as relaxed, stressed, or excited. The server then stores this data as emotion data.

[0390] Step 5:

[0391] The server calls a generative AI model based on the received personal attribute information, question content, number of pages to be generated, and emotional data, and optimizes the question content based on the emotion. This process adjusts the tone (e.g., friendly, formal) and difficulty of the question depending on the emotional data. The generative AI model receives input data in text format and generates optimized question content.

[0392] Step 6:

[0393] The generative AI model automatically generates a specified number of questionnaires based on the optimized question content. These questionnaires reflect personal attribute information, question content, and emotional data, and the server generates them as a series of text-format questionnaires.

[0394] Step 7:

[0395] The generated questionnaire is output in a file format such as PDF or Excel and saved on the server. A notification is sent to the user's device so that the file can be downloaded. The user clicks the download link to obtain the generated questionnaire.

[0396] Through these steps, we have achieved a system that recognizes users' emotions and automatically generates an optimized questionnaire that reflects those emotions. This process makes it possible to collect questionnaire data that is easy to respond to and highly accurate.

[0397] 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.

[0398] 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.

[0399] 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.

[0400] [Second embodiment]

[0401] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0402] 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.

[0403] 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).

[0404] 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.

[0405] 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.

[0406] 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).

[0407] 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.

[0408] 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.

[0409] 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.

[0410] 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.

[0411] 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.

[0412] 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."

[0413] The system of the present invention uses a generative AI model to efficiently and automatically generate questionnaires by inputting specific persona information and specifying the question content and number of questionnaires to be generated. This system allows companies and marketers to quickly create targeted questionnaires while significantly reducing labor and costs.

[0414] Program processing

[0415] Entering persona information

[0416] The user connects to the system's input form using a terminal and enters specific persona information such as "age," "occupation," and "hobbies." This information is used for subsequent processing within the system.

[0417] Enter your question

[0418] The user enters the questions they want to ask in the survey in multiple lines into the input form. For example, they can enter specific questions such as "What is your favorite drink?" or "What is the most important thing about a cafe?"

[0419] Enter the number of questionnaires

[0420] The user inputs the number of surveys they want to generate, for example, "50" or "100," specifying the number of samples they require.

[0421] Calling the generative AI model and generating a survey

[0422] The server calls the generative AI model based on the persona information, question content, and number of pages to be generated obtained from the user. This model automatically generates new questionnaires based on learning data such as past survey data. The generative AI model searches for similar personas in an existing database related to the persona information and creates related questionnaire items. It then associates the entered questions with the persona and adjusts them to generate a diverse set of questionnaires.

[0423] Output of generated results

[0424] The generated questionnaire is saved on the server and the specified number of questionnaires are prepared. The questionnaires are presented to users in formats such as PDF or Excel, and can be downloaded by the users. The generated questionnaires can also be distributed physically or online.

[0425] Specific examples

[0426] A marketer for a coffee shop chain

[0427] 1. Enter persona information

[0428] The user (marketing staff) enters "female in her 20s," "university student," and "hobby is visiting cafes."

[0429] 2. Enter your question

[0430] Enter "What is your usual drink?" and "What is the most important thing for you in a cafe?"

[0431] 3. Enter the number of questionnaires

[0432] Enter "100" as the number of samples required.

[0433] 4. Generate a survey

[0434] The server calls the generative AI model and automatically generates 100 questionnaires based on the specified persona information and questions.

[0435] 5. Presentation of results

[0436] The generated questionnaire is provided to the user in a downloadable format, which the person in charge can use to start the survey.

[0437] Through the above process, it is possible to efficiently collect questionnaires suited to specific personas and use them to improve and develop products and services. This system provides a means for generating such questionnaires quickly and effectively.

[0438] The processing flow will be explained below.

[0439] Step 1:

[0440] The user accesses the system's input form using a terminal and enters specific persona information, such as attributes such as "age," "occupation," and "hobbies."

[0441] Step 2:

[0442] The user enters the questions they want to ask in the survey into the input form. Enter specific questions such as "What is your favorite drink?" or "What is the most important thing for you in a cafe?"

[0443] Step 3:

[0444] The user enters the number of surveys they want to generate, for example, "50" or "100," to specify the number of samples required.

[0445] Step 4:

[0446] The server receives the specific persona information, question content, and number of copies to be generated sent by the user.

[0447] Step 5:

[0448] The server calls the generative AI model, which learns from existing persona data and past survey data in the database.

[0449] Step 6:

[0450] The generative AI model searches the database for similar personas based on the persona information and generates related questionnaire items, resulting in the creation of initial questionnaire items according to the persona information.

[0451] Step 7:

[0452] The server uses a generative AI model to associate the questions entered by the user with the persona and adjust them, thereby generating questions optimized for each persona.

[0453] Step 8:

[0454] The server generates the specified number of questionnaires. The generative AI model automatically generates a diverse set of questionnaires based on the adjusted question content, adding variation to each questionnaire.

[0455] Step 9:

[0456] The server saves the generated questionnaire and prepares it for presentation to the user. The generated questionnaire is output in a common file format (PDF, Excel, etc.).

[0457] Step 10:

[0458] The user downloads the generated survey. The user accesses the results page of the system using a terminal and downloads the generated survey, which allows for physical distribution or online distribution of the survey.

[0459] Example 1

[0460] 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."

[0461] Traditional survey creation methods require a lot of time and effort for companies and marketers to create surveys that are appropriate for their target personas. Furthermore, creating surveys manually is prone to human error, making it difficult to operate efficiently.

[0462] 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.

[0463] In this invention, the server includes means for inputting specific attribute information, means for inputting question content, means for inputting the number of questionnaires to be generated, means for automatically generating questionnaires using a generative AI model based on the input information, means for saving and outputting the generated questionnaires, and means for making the generated questionnaires available for download. This enables companies and marketers to efficiently automatically generate high-quality questionnaires and quickly utilize them.

[0464] "Attribute information" refers to individual characteristics of a specific target person, such as age, occupation, hobbies, etc.

[0465] "Question content" refers to the specific content of the questions posed to the target person in the questionnaire.

[0466] A "generative AI model" refers to an artificial intelligence model that automatically generates new questionnaires based on past data and learning data.

[0467] A "database" refers to a system that stores information for searching for similar person images based on specific attribute information.

[0468] "Downloadable means" refers to the technical mechanism that allows a user to save the generated survey to a device.

[0469] "Means for storage and output" refers to the technical mechanism by which the generated survey is stored in a particular format and provided to the user.

[0470] The present invention relates to a system for efficiently generating questionnaires using a generative AI model. This system inputs attribute information, question content, and the number of questionnaires to be generated, automatically generates questionnaires based on the input information, and provides the generated questionnaires to users. Specific embodiments for implementing the present invention are described below.

[0471] The user accesses the system's web interface using a terminal and inputs attribute information (age, occupation, hobbies, etc.). Next, the user inputs the questions and then specifies the number of questionnaires to be generated. This web interface is provided through a browser.

[0472] Once the user has completed entering the attribute information, question content, and number of questionnaires, the server receives this data and calls the generative AI model. This generative AI model automatically generates new questionnaires based on past survey data. Specifically, the generative AI model searches for similar persona profiles from past data and automatically creates related question items. It also adjusts the entered question content by relating it to the persona information, generating a diverse set of questionnaires.

[0473] The generated survey is saved on the server and output in a specified format (usually PDF or Excel format). This output survey is provided in a format that users can download. Users can save the generated survey to their devices by accessing the system again and clicking the download link. Users can then print these surveys or distribute them online.

[0474] As a concrete example, consider a situation where the target audience is a marketing manager for a coffee shop chain. Below is an example of the concrete example and a prompt sentence.

[0475] Specific examples

[0476] 1. Enter persona information

[0477] The user (marketing staff) enters "female in her 20s," "university student," and "hobby is visiting cafes."

[0478] 2. Enter your question

[0479] Enter "What is your usual drink?" and "What is the most important thing for you in a cafe?"

[0480] 3. Enter the number of questionnaires

[0481] Enter "100" as the number of samples required.

[0482] 4. Generate a survey

[0483] The server calls the generative AI model and automatically generates 100 questionnaires based on the specified persona information and question content.

[0484] 5. Presentation of results

[0485] The generated questionnaire is provided to the user in a downloadable format, which the person in charge can use to start the survey.

[0486] Prompt Sentence Examples

[0487] prompt:

[0488] Generate your survey based on the following persona information:

[0489] Persona: Female in her 20s, university student, hobby is cafe hopping

[0490] Questions:

[0491] 1. What is your favorite drink?

[0492] 2. What is the most important thing to you about your cafe?

[0493] Number of cards generated: 100

[0494] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0495] Step 1: Enter your persona information

[0496] 1. The user uses a terminal to access the system's web interface.

[0497] 2. The user accesses a form to enter attribute information.

[0498] 3. The user enters attribute information such as "age," "occupation," and "hobbies," and clicks the "Submit" button.

[0499] 4. The server receives the entered attribute information and stores it in the database.

[0500] Specific operation: The user opens a browser and accesses the system's URL. He enters "25 years old" in the "Age" field, "University student" in the "Occupation" field, and "Cafe hopping" in the "Hobby" field, and clicks the submit button. The server saves this information in the database.

[0501] Step 2: Enter the question content

[0502] 1. After submitting the persona information, the user is redirected to a form where they can enter their questions.

[0503] 2. The user enters the questions they want to ask in the survey.

[0504] 3. The user enters the question content on multiple lines and clicks the "Submit" button.

[0505] 4. The server receives the entered questions, associates them with attribute information, and stores them in a database.

[0506] Specific operation: Enter "What is your usual drink?" in the "Question 1" field and "What is the most important thing for you in a cafe?" in the "Question 2" field, then click the submit button. The server associates these questions with attribute information and saves them in the database.

[0507] Step 3: Enter the number of surveys

[0508] 1. After submitting the questionnaire, the user is redirected to a form where they can enter the number of surveys.

[0509] 2. The user enters the number of questionnaires to be generated.

[0510] 3. The user confirms the number of copies entered and clicks the "Submit" button.

[0511] 4. The server receives the number of sheets entered and stores it in a database along with the attribute information and question content.

[0512] What happens: You enter "100" in the "Quantity" field and click the submit button. The server stores this information in a database.

[0513] Step 4: Invoke the generative AI model and generate a survey

[0514] 1. Once the user has entered all the data, the server calls the generative AI model based on the attribute information, question content, and number of sheets to be generated.

[0515] 2. The generative AI model references past survey data and automatically generates a new survey based on the input information.

[0516] 3. The generative AI model searches the database for similar person profiles based on attribute information and generates relevant questions.

[0517] 4. The entered questions are adjusted in relation to attribute information to generate a diverse questionnaire set.

[0518] Specific operation: The server passes the attribute information "25 years old," "university student," and "cafe hopping" along with the questions "What is your usual drink?" and "What is the most important thing for you in a cafe?" to the generative AI model. The generative AI model analyzes similar patterns from past survey data and generates 100 new surveys.

[0519] Step 5: Output the generated results

[0520] 1. The generated questionnaire is saved on the server and output in the specified format.

[0521] 2. The server saves the generated survey in PDF or Excel format.

[0522] 3. The user receives a notification from the server and retrieves the generated survey via a download link.

[0523] 4. Users download the survey to their devices and print or distribute it online as needed.

[0524] Specific operation: The server saves the generated 100 questionnaires in PDF format and sends a notification to the user. The user clicks the download link to download the questionnaire and use it within the company.

[0525] The above are the specific processing steps of this system.

[0526] (Application example 1)

[0527] 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."

[0528] Conventional survey generation systems have difficulty quickly and efficiently generating questions suited to specific personas, and lack the functionality to distribute, collect, and analyze the generated surveys via the Internet. This makes it difficult to effectively collect survey results from target demographics in advertising and marketing campaigns, resulting in the inability to maximize the effectiveness of the campaign.

[0529] 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.

[0530] In this invention, the server includes means for inputting specific persona information, means for inputting question content, means for inputting the number of questionnaires to be generated, means for automatically generating questionnaires using a generative AI model, means for distributing the generated questionnaires via the Internet, means for collecting and analyzing the results of the generated questionnaires, and means for outputting the generated questionnaires. This makes it possible to quickly and efficiently generate, distribute, collect, and analyze questionnaires tailored to targets.

[0531] "Specific persona information" is information about a specific target demographic, and includes attribute information such as age, gender, occupation, and hobbies.

[0532] "Question content" refers to the wording of the items asked to respondents in the questionnaire.

[0533] The "number of questionnaires to be generated" refers to the number of questionnaire sets to be generated, and more specifically, indicates the number of samples to be generated.

[0534] A "generative AI model" is an artificial intelligence model that automatically generates a questionnaire based on the input persona information and question content.

[0535] "Means of automatic generation" refers to the process of creating a questionnaire using a generative AI model, taking persona information and question content as input.

[0536] "Means of distribution via the Internet" refers to a method of sending the generated questionnaire to subjects via the Internet.

[0537] "Means of collection and analysis" refers to the process of receiving and analyzing the response data from the distributed questionnaire.

[0538] "Means of output" refers to a method of providing the generated questionnaire to the user in a format such as PDF or Excel.

[0539] This invention is a system that allows marketers and advertising agencies to efficiently generate, distribute, collect, and analyze targeted questionnaires. Specific methods for implementing this system are described below.

[0540] Hardware and Software Configuration

[0541] This system is realized mainly using the following hardware and software.

[0542] Hardware: smartphones, tablets, servers

[0543] Software: Python, TensorFlow, Flask (server-side framework)

[0544] System processing procedure

[0545] 1. User Input

[0546] Users connect to the system using a smartphone or tablet and enter specific persona information, questions, and the number of questionnaires to be generated. Persona information includes age, gender, occupation, and hobbies.

[0547] 2. Questionnaire generation

[0548] The server receives the information entered by the user and calls a generative AI model based on that information. This generative AI model automatically generates the specified number of questionnaires based on the entered persona information and questions. The generative AI model learns from past survey data, enabling it to generate highly accurate surveys.

[0549] 3. Survey distribution

[0550] The server distributes the generated survey to the designated target audience via the Internet, using email, social media, advertising platforms, etc.

[0551] 4. Collection and analysis of survey results

[0552] The response data from the distributed survey is sent to a server where it is collected and analyzed. The collected data is analyzed using statistical analysis tools to be used in marketing strategies.

[0553] 5. Output of generated results

[0554] The generated questionnaire is provided to the user in formats such as PDF or Excel, and can be downloaded and used.

[0555] Specific examples

[0556] A marketer wants to generate 100 questionnaires for an advertising campaign targeting a persona of a man in his 20s whose hobby is sports:

[0557] 1. Enter persona information

[0558] The user enters "Persona information: 20s, male, sports."

[0559] 2. Enter your question

[0560] Enter the questions "Which sports brand do you like?" and "What is the most important thing to consider when choosing sportswear?"

[0561] 3. Enter the number of questionnaires

[0562] The user enters "Number of surveys to generate: 100".

[0563] 4. Examples of prompt sentences

[0564] Enter the following as the prompt:

[0565] Persona information: 20s, male, sports

[0566] Questions asked:

[0567] 1. Which sports brand do you like?

[0568] 2. What is the most important thing to consider when choosing sportswear?

[0569] Number of copies generated: 100

[0570] By distributing the questionnaires generated in this way via the Internet and collecting and analyzing the results, an effective advertising campaign can be realized.

[0571] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0572] Step 1:

[0573] Users connect to the system's input form using a smartphone or tablet and enter specific persona information such as age, gender, occupation, and hobbies. The persona information entered by the user becomes the reference data for identifying targets in subsequent processing.

[0574] Step 2:

[0575] The user inputs questions based on the information they want to obtain. Questions include specific questions such as, "Which brand of clothing do you usually buy?" or "What is the most important point when choosing sportswear?" The input questions are sent to the server as data to be used in generating the questionnaire.

[0576] Step 3:

[0577] The user inputs the number of surveys they want to generate, for example, a sample size such as "50" or "100." This number is sent to the server to determine the number of survey sets to generate.

[0578] Step 4:

[0579] The server calls the generative AI model based on the persona information, question content, and number of questionnaires received from the user. The generative AI model searches for similar personas from an existing database related to persona information, adjusts the input questions, and automatically generates a diverse set of questionnaires. The generative AI model uses TensorFlow and utilizes past survey data as learning data.

[0580] Step 5:

[0581] The server distributes the generated survey via the Internet, using email, social media, advertising platforms, etc., to send the survey to the designated target audience. The distribution method is realized through the Flask framework.

[0582] Step 6:

[0583] The user's device receives the survey results. The server collects the data and analyzes it using statistical analysis tools. This provides insights into the preferences and opinions of the target demographic.

[0584] Step 7:

[0585] The server converts the generated survey into PDF or Excel format and provides it for users to download, so that users can use the survey in their advertising campaigns and marketing strategies.

[0586] 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.

[0587] This invention combines an emotion engine with a system that automatically generates questionnaires using a generative AI model by inputting specific persona information and specifying the question content and number of questionnaires to be generated. This system recognizes the user's emotions and further optimizes the questionnaire content based on those emotions.

[0588] Program processing

[0589] Entering persona information

[0590] The user accesses the system's input form using a terminal and enters specific persona information, including attribute information such as "age," "occupation," and "hobbies."

[0591] Enter your question

[0592] The user enters the questions they want to ask in the survey into the input form. Enter specific questions such as "What is your favorite drink?" or "What is the most important thing for you in a cafe?"

[0593] Enter the number of questionnaires

[0594] The user inputs the number of surveys they want to generate. For example, they specify the required sample size, such as "50" or "100."

[0595] emotion recognition

[0596] The device is equipped with an emotion engine that recognizes the user's emotions from facial expressions and voice input. For example, it analyzes data obtained through a camera and microphone to detect emotions such as whether the user is relaxed or stressed.

[0597] Using sentiment data

[0598] The server receives the emotion data recognized by the emotion engine. Based on the received emotion data, persona information, question content, and number of pages to be generated, it calls a generative AI model. This model optimizes the questionnaire content by reflecting the emotion data.

[0599] Generate questionnaire items

[0600] The generative AI model uses persona information to search a database for similar profiles and generate relevant survey questions, adjusting the tone and difficulty of the questions based on perceived emotions.

[0601] Adjustment of survey content

[0602] The generative AI model adjusts the questions entered by the user by linking them to persona information and emotional data, optimizing the questions to make them easier for the user to answer by relaxing the questions or asking more detailed questions depending on the emotion.

[0603] Generate a survey

[0604] The server generates the specified number of questionnaires, and the generative AI model creates a set of variations, each of which reflects persona information and emotional data.

[0605] Output of generated results

[0606] The generated questionnaire is stored on the server and prepared for presentation to the user. The generated results are output in formats such as PDF or Excel, which the user can download.

[0607] Specific examples

[0608] A marketer for a coffee shop chain

[0609] 1. Enter persona information

[0610] The user (marketing staff) enters "female in her 20s," "university student," and "hobby is visiting cafes."

[0611] 2. Enter your question

[0612] Enter "What is your usual drink?" and "What is the most important thing for you in a cafe?"

[0613] 3. Enter the number of questionnaires

[0614] Enter "100" as the number of samples required.

[0615] 4. Emotion recognition

[0616] The device analyzes the user's facial expressions and voice to recognize relaxed emotions.

[0617] 5. Use of Emotional Data

[0618] The server receives the emotion data and invokes a generative AI model, which uses the emotion data to adjust the tone of the question to be a little friendlier.

[0619] 6. Generate questionnaire items

[0620] Generate relevant questionnaire items from the database based on persona information.

[0621] 7. Adjustment of survey content

[0622] Tailor the questions to relate to the user's emotional data, making them more specific, such as "What do you like to drink when you want to relax?"

[0623] 8. Generate a survey

[0624] Generate 100 different questionnaires.

[0625] 9. Output of generated results

[0626] The user downloads the survey and begins the survey.

[0627] In this way, by generating questionnaires that combine emotion recognition functions, this system makes it easier for users to answer and achieves highly accurate data collection.

[0628] The processing flow will be explained below.

[0629] Step 1:

[0630] The user accesses the system's input form using a terminal and enters specific persona information, specifically attribute information such as "age," "occupation," and "hobbies."

[0631] Step 2:

[0632] The user enters the questions they want to ask in the survey into the input form. For example, they enter specific questions such as "What is your favorite drink?" or "What is the most important thing about a cafe?"

[0633] Step 3:

[0634] The user inputs the number of surveys they want to generate. For example, they specify the required sample size, such as "50" or "100."

[0635] Step 4:

[0636] The device monitors the user's emotional state within the input form, capturing the user's facial expressions through the camera and collecting audio data through the microphone.

[0637] Step 5:

[0638] The device's built-in emotion engine analyzes the captured facial and voice data to recognize the user's emotions, such as whether the user is relaxed or stressed.

[0639] Step 6:

[0640] The device sends the recognized emotion data to the server, which receives the emotion data along with the user's persona information, question content, and number of images generated.

[0641] Step 7:

[0642] The server calls the generative AI model, which prepares to automatically generate a questionnaire based on persona information, question content, and emotion data.

[0643] Step 8:

[0644] The server uses a generated AI model to search a database for similar profiles based on the persona information and generate relevant questionnaire items, adjusting the tone and difficulty of the questions based on the perceived emotions.

[0645] Step 9:

[0646] The server uses a generated AI model to correlate the questions entered by the user with persona information and emotional data, adjusting the questions to a more relaxed tone or more detailed questions depending on the emotion.

[0647] Step 10:

[0648] The server generates the specified number of questionnaires, and the generative AI model creates a set of variations, each of which reflects persona information and emotional data.

[0649] Step 11:

[0650] The server saves the generated questionnaire and prepares it for delivery to the user. The generated results are output in a format such as PDF or Excel, and can be downloaded by the user.

[0651] Step 12:

[0652] The user accesses the system's results page using a terminal and downloads the generated survey, which can then be distributed physically or online.

[0653] Example 2

[0654] 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."

[0655] Conventional survey generation systems are unable to optimize survey content taking user emotions into account, which can affect response rates and response quality. Even when using a generation AI model based on persona information and question content, it is difficult to generate a survey that appropriately reflects emotional data. It is necessary to solve these problems and generate more accurate surveys.

[0656] 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.

[0657] In this invention, the server includes a means for inputting specific person information, a means for inputting question content, a means for inputting the number of surveys to be generated, a means for recognizing the user's emotions and optimizing the survey content based on the emotions, a means for automatically generating a survey using a generative artificial intelligence model based on the input information, and a means for outputting the generated survey, thereby enabling the generation of a survey optimized according to the user's emotions.

[0658] "Specific personal information" is attribute information about the survey subject, such as the user's age, occupation, hobbies, etc.

[0659] "Questions" are specific questions you want to ask in the survey.

[0660] The "number of surveys to be generated" is the specific number of questionnaires you want to generate, and the number of samples you need.

[0661] A "generative artificial intelligence model" is an AI model that automatically generates a questionnaire based on input information.

[0662] "Means to recognize emotions and optimize survey content based on that" refers to a function that acquires and analyzes users' emotional data in real time and adjusts the tone and difficulty of the survey content to reflect that.

[0663] "Means for outputting the generated survey" is a function that provides the generated questionnaire to the user in a format that can be used by the user (such as PDF or Excel).

[0664] "Means for searching for similar person profiles from a database" is a function for searching for similar data entries in a database based on persona information.

[0665] The "means for adjusting the question content by relating it to personal information" is a function for optimizing the question content based on the input personal information and adjusting it to a format that is easy for the user to answer.

[0666] The present invention relates to a system that automatically generates an optimized questionnaire by inputting specific personal information and question content and recognizing the user's emotions. This system is realized through interactions between a server, terminals, and users.

[0667] System configuration

[0668] The system consists of the following main components:

[0669] 1. Terminal

[0670] The device is equipped with an interface that allows users to access an input form and enter the necessary information. The device is also equipped with an emotion engine that captures and analyzes the user's facial expressions and voice in real time through a camera and microphone. The specific hardware used includes a camera, microphone, and display.

[0671] 2. Server

[0672] The server includes a function for generating questionnaires using a generative artificial intelligence model based on the emotion data recognized by the emotion engine, the input personal information, the question content, and the number of questionnaires to be generated. The server also includes an output means for providing the generated questionnaires to users. Related software includes a database management system and an AI model execution environment.

[0673] Operational Overview

[0674] The user uses a terminal to access the system's input form and enters specific personal information (e.g., age, occupation, hobbies). Next, the user enters the specific questions they want to ask in the survey and also specifies the number of surveys they want to generate. The terminal uses a camera and microphone to capture the user's facial expressions and voice, which is then analyzed by an emotion engine to generate emotional data for the user. This emotional data is sent to the server and input into the generative artificial intelligence model along with the persona information, questions, and number of surveys to be generated.

[0675] The generative AI model searches a database for similar personas based on persona information and generates relevant questionnaire items. The tone and difficulty of the questions are adjusted based on the recognized emotional data. The generated questionnaire is stored on a server and provided to users in downloadable formats (PDF or Excel).

[0676] Specific examples

[0677] For example, consider the following scenario where a marketer for a coffee shop chain types:

[0678] 1. Enter your persona information:

[0679] The user enters "female in her 20s," "university student," and "hobby is visiting cafes."

[0680] 2. Enter your question:

[0681] Enter "What is your usual drink?" and "What is the most important thing for you in a cafe?"

[0682] 3. Enter the number of surveys:

[0683] Enter "100" as the number of samples required.

[0684] 4. Emotion recognition:

[0685] The device analyzes the user's facial expressions and voice to recognize relaxed emotions.

[0686] 5. Use of Emotional Data:

[0687] The server receives the emotion data and invokes a generative AI model, which uses the emotion data to adjust the tone of the question to be a little friendlier.

[0688] 6. Generate questionnaire items:

[0689] Generate relevant questionnaire items from the database based on persona information.

[0690] 7. Survey Content Adjustment:

[0691] Tailor the questions to relate to the user's emotional data, making them more specific, such as "What do you like to drink when you want to relax?"

[0692] 8. Generate the survey:

[0693] Generate 100 different questionnaires.

[0694] 9. Generated output:

[0695] The user downloads the survey and begins the survey.

[0696] Prompt Sentence Examples

[0697] "Persona information: Female, university student in her 20s, whose hobby is visiting cafes. Questions: What is her usual drink? What is the most important thing about a cafe? Emotional data: Relaxed. Number of surveys to generate: 100. Based on this information, please generate 100 surveys in a friendly tone."

[0698] In this way, the system utilizes user input information and emotional data to automatically generate optimized questionnaires.

[0699] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0700] Step 1:

[0701] The terminal displays the system's input form to the user and asks them to enter specific personal information (e.g., age, occupation, hobbies). Specifically, input fields on the display are used to collect information such as "25 years old," "office worker," and "reading." The entered personal information is then sent to the server by the terminal.

[0702] Step 2:

[0703] The terminal displays a field for the user to enter questions. The user enters the specific questions they want to ask in the survey. For example, they can enter questions such as "How do you usually spend your holidays?" or "What is your favorite genre of book?" The entered questions are then sent to the server.

[0704] Step 3:

[0705] The terminal displays a field for the user to enter the number of surveys they want to generate. The user enters the number of surveys to generate (e.g., "100"). This information is also sent to the server.

[0706] Step 4:

[0707] The device uses a camera and microphone to capture the user's facial expressions and voice in real time, which are then analyzed by an emotion engine. This analysis generates emotion data such as relaxation or stress, which is then sent from the device to a server.

[0708] Step 5:

[0709] The server calls the generative AI model based on the received emotion data, person information, question content, and number of pages to be generated, and generates a prompt. For example, a prompt might include "Persona information: 25 years old, office worker, hobby is reading. Question content: How do you usually spend your holidays? Emotion data: Relaxed. Number of questionnaires to be generated: 100." This prompt is input into the generative AI model.

[0710] Step 6:

[0711] The generative AI model searches a database for similar profiles based on the prompt and generates relevant questionnaire items, such as "specific activities you usually do on your vacation" or "the genre of books you read when relaxing." The generated questionnaire items are saved on the server.

[0712] Step 7:

[0713] The generative AI model adjusts the tone and difficulty of the questions based on the emotional data. For example, if you are feeling relaxed, the question might be, "What books do you read when you want to relax?" This adjustment is also saved on the server.

[0714] Step 8:

[0715] The server generates the specified number of questionnaires. For example, 100 questionnaires are generated, each containing different questions and tones. This generated data is stored on the server.

[0716] Step 9:

[0717] The server outputs the generated survey in PDF or Excel format and provides a download link to the user, who clicks the link to download the survey and begin the survey.

[0718] (Application example 2)

[0719] 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."

[0720] Conventional questionnaire generation systems generate a uniform questionnaire based on the persona information and question content entered by the user, which does not take into account the user's emotional state or ease of response, making it difficult to collect accurate data. Furthermore, the questionnaire questions are not optimized to match the user's emotions, which can cause respondents to feel stressed or less motivated to answer. Furthermore, there is a lack of systems that can efficiently generate a variety of questionnaires.

[0721] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting specific person attribute information, means for inputting question content, means for inputting the number of questionnaires to be generated, means for recognizing emotions during input using an emotion recognition engine installed in the terminal, means for optimizing question content based on the recognized emotions, means for automatically generating questionnaires using a generative AI model based on the input information, and means for outputting the generated questionnaire. As a result, by recognizing the user's emotions and optimizing the question content based on them, it is possible to generate questionnaires that are easy to answer and have high accuracy.

[0722] "Specific person attribute information" is attribute information related to a specific individual, such as age, occupation, and hobbies.

[0723] The "question content" refers to the specific questions you want to ask in the questionnaire.

[0724] "Number of questionnaires to generate" is the number of questionnaires that the generative AI model will automatically generate, as specified by the user.

[0725] An "emotion recognition engine" is an engine that analyzes the user's facial expressions and voice while inputting data and recognizes their emotions.

[0726] "Optimizing question content" means adjusting the tone and difficulty of questions based on perceived sentiment.

[0727] A "generative AI model" is an artificial intelligence model that automatically generates a questionnaire based on input information.

[0728] "Automatically generating a questionnaire" means that the generative AI model creates a questionnaire based on the input personal attribute information, question content, and recognized emotion data.

[0729] "Outputting a questionnaire" means generating data in a format such as PDF or Excel in order to present the generated questionnaire to the user.

[0730] The present invention relates to a system that automatically generates an optimized questionnaire by inputting specific person attribute information and question content and utilizing an emotion recognition engine. The system configuration and examples of the present invention will be described in detail below.

[0731] System Configuration

[0732] The system of the present invention includes the following major components:

[0733] 1. Terminal: A device that allows a user to input information. Examples include tablets and interactive displays, and are equipped with a camera and microphone.

[0734] 2. Emotion Recognition Engine: Software that analyzes the user's facial expressions and voice to recognize emotions. Specifically, it uses the Hugging Face Transformers emotion analysis pipeline and OpenCV.

[0735] 3. Server: Calls the generative AI model based on persona information, question content, number of sheets to be generated, and emotional data, and automatically generates an optimized questionnaire.

[0736] 4. Generative AI model: An artificial intelligence model that automatically generates questionnaires based on user-entered information and emotion data. Hugging Face Transformers and TextBlob are used.

[0737] 5. Database: A database for searching for similar person images based on the entered person attribute information.

[0738] Data processing and calculation

[0739] The server processes the data in the following steps:

[0740] 1. Collecting personal attribute information: The user enters personal attribute information such as age, occupation, and hobbies into an input form on the terminal.

[0741] 2. Collecting questions: Users input the questions they want to ask.

[0742] 3. Emotion recognition: The device's camera and microphone capture the user's facial expressions and voice, and the emotion recognition engine analyzes them to recognize emotions.

[0743] 4. Question Optimization: Optimize questions and adjust the tone and difficulty of questions based on perceived sentiment.

[0744] 5. Questionnaire generation: Use generative AI models to automatically generate questionnaires.

[0745] 6. Questionnaire output: The generated questionnaire can be output in formats such as PDF or Excel and made available for download by users.

[0746] Examples of specific examples and prompts

[0747] As a concrete example, consider the case where a marketing manager at a brick-and-mortar store wants to survey customers at a cafe.

[0748] The marketing staff enters the following information into the input form on the terminal:

[0749] Persona information: "Female in her 20s," "University student," "Hobby is visiting cafes"

[0750] Questions included: "What is your usual drink?" and "What is the most important thing for you in a cafe?"

[0751] The emotion recognition engine recognizes the agent's relaxed emotions and adjusts the tone of the questions to be a little friendlier. Based on the information and emotional data entered by the user, the generative AI model automatically generates 50 optimized questionnaires.

[0752] An example prompt is:

[0753] Persona information: Female in her 20s, university student, enjoys visiting cafes

[0754] Questions: What is your favorite drink? What is the most important thing for you in a cafe?

[0755] Emotion: Relaxed

[0756] Number of questionnaires: 50

[0757] This makes it possible to recognize the user's emotions and optimize the content of the questions based on them, thereby generating highly accurate questionnaires that are easy to answer.

[0758] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0759] Step 1:

[0760] The user accesses an input form on the terminal and inputs personal attribute information such as age, occupation, hobbies, etc. This allows the system to collect basic information about the user and sends this information to the server for use in the next step. The input data is text information such as age, occupation, hobbies, etc., and the server saves it as personal attribute information.

[0761] Step 2:

[0762] The user enters the question they want to ask into the input form on the device. At this time, the question is a specific text question, such as "What is your usual drink?" or "What is the most important thing for you in a cafe?" This is also sent to the server. The server saves this input data as the question.

[0763] Step 3:

[0764] The user inputs the number of questionnaires to be generated in a numerical format. For example, "50" or "100" is specified. This numerical data is also sent to the server, and the server saves it as the number of questionnaires to be generated.

[0765] Step 4:

[0766] The device's emotion recognition engine analyzes the user's facial expressions and voice to recognize their emotions in real time. Specifically, the device's camera and microphone are used to capture the user's facial expression data and voice data, which are then analyzed by an emotion recognition algorithm (e.g., the Hugging Face Transformers emotion analysis pipeline). The results of this analysis are sent to the server as emotion labels, such as relaxed, stressed, or excited. The server then stores this data as emotion data.

[0767] Step 5:

[0768] The server calls a generative AI model based on the received personal attribute information, question content, number of pages to be generated, and emotional data, and optimizes the question content based on the emotion. This process adjusts the tone (e.g., friendly, formal) and difficulty of the question depending on the emotional data. The generative AI model receives input data in text format and generates optimized question content.

[0769] Step 6:

[0770] The generative AI model automatically generates a specified number of questionnaires based on the optimized question content. These questionnaires reflect personal attribute information, question content, and emotional data, and the server generates them as a series of text-format questionnaires.

[0771] Step 7:

[0772] The generated questionnaire is output in a file format such as PDF or Excel and saved on the server. A notification is sent to the user's device so that the file can be downloaded. The user clicks the download link to obtain the generated questionnaire.

[0773] Through these steps, we have achieved a system that recognizes users' emotions and automatically generates an optimized questionnaire that reflects those emotions. This process makes it possible to collect questionnaire data that is easy to respond to and highly accurate.

[0774] 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.

[0775] 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.

[0776] 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.

[0777] [Third embodiment]

[0778] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0779] 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.

[0780] 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).

[0781] 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.

[0782] 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.

[0783] 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).

[0784] 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.

[0785] 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.

[0786] 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.

[0787] 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.

[0788] 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.

[0789] 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."

[0790] The system of the present invention uses a generative AI model to efficiently and automatically generate questionnaires by inputting specific persona information and specifying the question content and number of questionnaires to be generated. This system allows companies and marketers to quickly create targeted questionnaires while significantly reducing labor and costs.

[0791] Program processing

[0792] Entering persona information

[0793] The user connects to the system's input form using a terminal and enters specific persona information such as "age," "occupation," and "hobbies." This information is used for subsequent processing within the system.

[0794] Enter your question

[0795] The user enters the questions they want to ask in the survey in multiple lines into the input form. For example, they can enter specific questions such as "What is your favorite drink?" or "What is the most important thing about a cafe?"

[0796] Enter the number of questionnaires

[0797] The user inputs the number of surveys they want to generate, for example, "50" or "100," specifying the number of samples they require.

[0798] Calling the generative AI model and generating a survey

[0799] The server calls the generative AI model based on the persona information, question content, and number of pages to be generated obtained from the user. This model automatically generates new questionnaires based on learning data such as past survey data. The generative AI model searches for similar personas in an existing database related to the persona information and creates related questionnaire items. It then associates the entered questions with the persona and adjusts them to generate a diverse set of questionnaires.

[0800] Output of generated results

[0801] The generated questionnaire is saved on the server and the specified number of questionnaires are prepared. The questionnaires are presented to users in formats such as PDF or Excel, and can be downloaded by the users. The generated questionnaires can also be distributed physically or online.

[0802] Specific examples

[0803] A marketer for a coffee shop chain

[0804] 1. Enter persona information

[0805] The user (marketing staff) enters "female in her 20s," "university student," and "hobby is visiting cafes."

[0806] 2. Enter your question

[0807] Enter "What is your usual drink?" and "What is the most important thing for you in a cafe?"

[0808] 3. Enter the number of questionnaires

[0809] Enter "100" as the number of samples required.

[0810] 4. Generate a survey

[0811] The server calls the generative AI model and automatically generates 100 questionnaires based on the specified persona information and questions.

[0812] 5. Presentation of results

[0813] The generated questionnaire is provided to the user in a downloadable format, which the person in charge can use to start the survey.

[0814] Through the above process, it is possible to efficiently collect questionnaires suited to specific personas and use them to improve and develop products and services. This system provides a means for generating such questionnaires quickly and effectively.

[0815] The processing flow will be explained below.

[0816] Step 1:

[0817] The user accesses the system's input form using a terminal and enters specific persona information, such as attributes such as "age," "occupation," and "hobbies."

[0818] Step 2:

[0819] The user enters the questions they want to ask in the survey into the input form. Enter specific questions such as "What is your favorite drink?" or "What is the most important thing for you in a cafe?"

[0820] Step 3:

[0821] The user enters the number of surveys they want to generate, for example, "50" or "100," to specify the number of samples required.

[0822] Step 4:

[0823] The server receives the specific persona information, question content, and number of copies to be generated sent by the user.

[0824] Step 5:

[0825] The server calls the generative AI model, which learns from existing persona data and past survey data in the database.

[0826] Step 6:

[0827] The generative AI model searches the database for similar personas based on the persona information and generates related questionnaire items, resulting in the creation of initial questionnaire items according to the persona information.

[0828] Step 7:

[0829] The server uses a generative AI model to associate the questions entered by the user with the persona and adjust them, thereby generating questions optimized for each persona.

[0830] Step 8:

[0831] The server generates the specified number of questionnaires. The generative AI model automatically generates a diverse set of questionnaires based on the adjusted question content, adding variation to each questionnaire.

[0832] Step 9:

[0833] The server saves the generated questionnaire and prepares it for presentation to the user. The generated questionnaire is output in a common file format (PDF, Excel, etc.).

[0834] Step 10:

[0835] The user downloads the generated survey. The user accesses the results page of the system using a terminal and downloads the generated survey, which allows for physical distribution or online distribution of the survey.

[0836] Example 1

[0837] 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."

[0838] Traditional survey creation methods require a lot of time and effort for companies and marketers to create surveys that are appropriate for their target personas. Furthermore, creating surveys manually is prone to human error, making it difficult to operate efficiently.

[0839] 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.

[0840] In this invention, the server includes means for inputting specific attribute information, means for inputting question content, means for inputting the number of questionnaires to be generated, means for automatically generating questionnaires using a generative AI model based on the input information, means for saving and outputting the generated questionnaires, and means for making the generated questionnaires available for download. This enables companies and marketers to efficiently automatically generate high-quality questionnaires and quickly utilize them.

[0841] "Attribute information" refers to individual characteristics of a specific target person, such as age, occupation, hobbies, etc.

[0842] "Question content" refers to the specific content of the questions posed to the target person in the questionnaire.

[0843] A "generative AI model" refers to an artificial intelligence model that automatically generates new questionnaires based on past data and learning data.

[0844] A "database" refers to a system that stores information for searching for similar person images based on specific attribute information.

[0845] "Downloadable means" refers to the technical mechanism that allows a user to save the generated survey to a device.

[0846] "Means for storage and output" refers to the technical mechanism by which the generated survey is stored in a particular format and provided to the user.

[0847] The present invention relates to a system for efficiently generating questionnaires using a generative AI model. This system inputs attribute information, question content, and the number of questionnaires to be generated, automatically generates questionnaires based on the input information, and provides the generated questionnaires to users. Specific embodiments for implementing the present invention are described below.

[0848] The user accesses the system's web interface using a terminal and inputs attribute information (age, occupation, hobbies, etc.). Next, the user inputs the questions and then specifies the number of questionnaires to be generated. This web interface is provided through a browser.

[0849] Once the user has completed entering the attribute information, question content, and number of questionnaires, the server receives this data and calls the generative AI model. This generative AI model automatically generates new questionnaires based on past survey data. Specifically, the generative AI model searches for similar persona profiles from past data and automatically creates related question items. It also adjusts the entered question content by relating it to the persona information, generating a diverse set of questionnaires.

[0850] The generated survey is saved on the server and output in a specified format (usually PDF or Excel format). This output survey is provided in a format that users can download. Users can save the generated survey to their devices by accessing the system again and clicking the download link. Users can then print these surveys or distribute them online.

[0851] As a concrete example, consider a situation where the target audience is a marketing manager for a coffee shop chain. Below is an example of the concrete example and a prompt sentence.

[0852] Specific examples

[0853] 1. Enter persona information

[0854] The user (marketing staff) enters "female in her 20s," "university student," and "hobby is visiting cafes."

[0855] 2. Enter your question

[0856] Enter "What is your usual drink?" and "What is the most important thing for you in a cafe?"

[0857] 3. Enter the number of questionnaires

[0858] Enter "100" as the number of samples required.

[0859] 4. Generate a survey

[0860] The server calls the generative AI model and automatically generates 100 questionnaires based on the specified persona information and question content.

[0861] 5. Presentation of results

[0862] The generated questionnaire is provided to the user in a downloadable format, which the person in charge can use to start the survey.

[0863] Prompt Sentence Examples

[0864] prompt:

[0865] Generate your survey based on the following persona information:

[0866] Persona: Female in her 20s, university student, hobby is cafe hopping

[0867] Questions:

[0868] 1. What is your favorite drink?

[0869] 2. What is the most important thing to you about your cafe?

[0870] Number of cards generated: 100

[0871] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0872] Step 1: Enter your persona information

[0873] 1. The user uses a terminal to access the system's web interface.

[0874] 2. The user accesses a form to enter attribute information.

[0875] 3. The user enters attribute information such as "age," "occupation," and "hobbies," and clicks the "Submit" button.

[0876] 4. The server receives the entered attribute information and stores it in the database.

[0877] Specific operation: The user opens a browser and accesses the system's URL. He enters "25 years old" in the "Age" field, "University student" in the "Occupation" field, and "Cafe hopping" in the "Hobby" field, and clicks the submit button. The server saves this information in the database.

[0878] Step 2: Enter the question content

[0879] 1. After submitting the persona information, the user is redirected to a form where they can enter their questions.

[0880] 2. The user enters the questions they want to ask in the survey.

[0881] 3. The user enters the question content on multiple lines and clicks the "Submit" button.

[0882] 4. The server receives the entered questions, associates them with attribute information, and stores them in a database.

[0883] Specific operation: Enter "What is your usual drink?" in the "Question 1" field and "What is the most important thing for you in a cafe?" in the "Question 2" field, then click the submit button. The server associates these questions with attribute information and saves them in the database.

[0884] Step 3: Enter the number of surveys

[0885] 1. After submitting the questionnaire, the user is redirected to a form where they can enter the number of surveys.

[0886] 2. The user enters the number of questionnaires to be generated.

[0887] 3. The user confirms the number of copies entered and clicks the "Submit" button.

[0888] 4. The server receives the number of sheets entered and stores it in a database along with the attribute information and question content.

[0889] What happens: You enter "100" in the "Quantity" field and click the submit button. The server stores this information in a database.

[0890] Step 4: Invoke the generative AI model and generate a survey

[0891] 1. Once the user has entered all the data, the server calls the generative AI model based on the attribute information, question content, and number of sheets to be generated.

[0892] 2. The generative AI model references past survey data and automatically generates a new survey based on the input information.

[0893] 3. The generative AI model searches the database for similar person profiles based on attribute information and generates relevant questions.

[0894] 4. The entered questions are adjusted in relation to attribute information to generate a diverse questionnaire set.

[0895] Specific operation: The server passes the attribute information "25 years old," "university student," and "cafe hopping" along with the questions "What is your usual drink?" and "What is the most important thing for you in a cafe?" to the generative AI model. The generative AI model analyzes similar patterns from past survey data and generates 100 new surveys.

[0896] Step 5: Output the generated results

[0897] 1. The generated questionnaire is saved on the server and output in the specified format.

[0898] 2. The server saves the generated survey in PDF or Excel format.

[0899] 3. The user receives a notification from the server and retrieves the generated survey via a download link.

[0900] 4. Users download the survey to their devices and print or distribute it online as needed.

[0901] Specific operation: The server saves the generated 100 questionnaires in PDF format and sends a notification to the user. The user clicks the download link to download the questionnaire and use it within the company.

[0902] The above are the specific processing steps of this system.

[0903] (Application example 1)

[0904] 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."

[0905] Conventional survey generation systems have difficulty quickly and efficiently generating questions suited to specific personas, and lack the functionality to distribute, collect, and analyze the generated surveys via the Internet. This makes it difficult to effectively collect survey results from target demographics in advertising and marketing campaigns, resulting in the inability to maximize the effectiveness of the campaign.

[0906] 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.

[0907] In this invention, the server includes means for inputting specific persona information, means for inputting question content, means for inputting the number of questionnaires to be generated, means for automatically generating questionnaires using a generative AI model, means for distributing the generated questionnaires via the Internet, means for collecting and analyzing the results of the generated questionnaires, and means for outputting the generated questionnaires. This makes it possible to quickly and efficiently generate, distribute, collect, and analyze questionnaires tailored to targets.

[0908] "Specific persona information" is information about a specific target demographic, and includes attribute information such as age, gender, occupation, and hobbies.

[0909] "Question content" refers to the wording of the items asked to respondents in the questionnaire.

[0910] The "number of questionnaires to be generated" refers to the number of questionnaire sets to be generated, and more specifically, indicates the number of samples to be generated.

[0911] A "generative AI model" is an artificial intelligence model that automatically generates a questionnaire based on the input persona information and question content.

[0912] "Means of automatic generation" refers to the process of creating a questionnaire using a generative AI model, taking persona information and question content as input.

[0913] "Means of distribution via the Internet" refers to a method of sending the generated questionnaire to subjects via the Internet.

[0914] "Means of collection and analysis" refers to the process of receiving and analyzing the response data from the distributed questionnaire.

[0915] "Means of output" refers to a method of providing the generated questionnaire to the user in a format such as PDF or Excel.

[0916] This invention is a system that allows marketers and advertising agencies to efficiently generate, distribute, collect, and analyze targeted questionnaires. Specific methods for implementing this system are described below.

[0917] Hardware and Software Configuration

[0918] This system is realized mainly using the following hardware and software.

[0919] Hardware: smartphones, tablets, servers

[0920] Software: Python, TensorFlow, Flask (server-side framework)

[0921] System processing procedure

[0922] 1. User Input

[0923] Users connect to the system using a smartphone or tablet and enter specific persona information, questions, and the number of questionnaires to be generated. Persona information includes age, gender, occupation, and hobbies.

[0924] 2. Questionnaire generation

[0925] The server receives the information entered by the user and calls a generative AI model based on that information. This generative AI model automatically generates the specified number of questionnaires based on the entered persona information and questions. The generative AI model learns from past survey data, enabling it to generate highly accurate surveys.

[0926] 3. Survey distribution

[0927] The server distributes the generated survey to the designated target audience via the Internet, using email, social media, advertising platforms, etc.

[0928] 4. Collection and analysis of survey results

[0929] The response data from the distributed survey is sent to a server where it is collected and analyzed. The collected data is analyzed using statistical analysis tools to be used in marketing strategies.

[0930] 5. Output of generated results

[0931] The generated questionnaire is provided to the user in formats such as PDF or Excel, and can be downloaded and used.

[0932] Specific examples

[0933] A marketer wants to generate 100 questionnaires for an advertising campaign targeting a persona of a man in his 20s whose hobby is sports:

[0934] 1. Enter persona information

[0935] The user enters "Persona information: 20s, male, sports."

[0936] 2. Enter your question

[0937] Enter the questions "Which sports brand do you like?" and "What is the most important thing to consider when choosing sportswear?"

[0938] 3. Enter the number of questionnaires

[0939] The user enters "Number of surveys to generate: 100".

[0940] 4. Examples of prompt sentences

[0941] Enter the following as the prompt:

[0942] Persona information: 20s, male, sports

[0943] Questions asked:

[0944] 1. Which sports brand do you like?

[0945] 2. What is the most important thing to consider when choosing sportswear?

[0946] Number of copies generated: 100

[0947] By distributing the questionnaires generated in this way via the Internet and collecting and analyzing the results, an effective advertising campaign can be realized.

[0948] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0949] Step 1:

[0950] Users connect to the system's input form using a smartphone or tablet and enter specific persona information such as age, gender, occupation, and hobbies. The persona information entered by the user becomes the reference data for identifying targets in subsequent processing.

[0951] Step 2:

[0952] The user inputs questions based on the information they want to obtain. Questions include specific questions such as, "Which brand of clothing do you usually buy?" or "What is the most important point when choosing sportswear?" The input questions are sent to the server as data to be used in generating the questionnaire.

[0953] Step 3:

[0954] The user inputs the number of surveys they want to generate, for example, a sample size such as "50" or "100." This number is sent to the server to determine the number of survey sets to generate.

[0955] Step 4:

[0956] The server calls the generative AI model based on the persona information, question content, and number of questionnaires received from the user. The generative AI model searches for similar personas from an existing database related to persona information, adjusts the input questions, and automatically generates a diverse set of questionnaires. The generative AI model uses TensorFlow and utilizes past survey data as learning data.

[0957] Step 5:

[0958] The server distributes the generated survey via the Internet, using email, social media, advertising platforms, etc., to send the survey to the designated target audience. The distribution method is realized through the Flask framework.

[0959] Step 6:

[0960] The user's device receives the survey results. The server collects the data and analyzes it using statistical analysis tools. This provides insights into the preferences and opinions of the target demographic.

[0961] Step 7:

[0962] The server converts the generated survey into PDF or Excel format and provides it for users to download, so that users can use the survey in their advertising campaigns and marketing strategies.

[0963] 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.

[0964] This invention combines an emotion engine with a system that automatically generates questionnaires using a generative AI model by inputting specific persona information and specifying the question content and number of questionnaires to be generated. This system recognizes the user's emotions and further optimizes the questionnaire content based on those emotions.

[0965] Program processing

[0966] Entering persona information

[0967] The user accesses the system's input form using a terminal and enters specific persona information, including attribute information such as "age," "occupation," and "hobbies."

[0968] Enter your question

[0969] The user enters the questions they want to ask in the survey into the input form. Enter specific questions such as "What is your favorite drink?" or "What is the most important thing for you in a cafe?"

[0970] Enter the number of questionnaires

[0971] The user inputs the number of surveys they want to generate. For example, they specify the required sample size, such as "50" or "100."

[0972] emotion recognition

[0973] The device is equipped with an emotion engine that recognizes the user's emotions from facial expressions and voice input. For example, it analyzes data obtained through a camera and microphone to detect emotions such as whether the user is relaxed or stressed.

[0974] Using sentiment data

[0975] The server receives the emotion data recognized by the emotion engine. Based on the received emotion data, persona information, question content, and number of pages to be generated, it calls a generative AI model. This model optimizes the questionnaire content by reflecting the emotion data.

[0976] Generate questionnaire items

[0977] The generative AI model uses persona information to search a database for similar profiles and generate relevant survey questions, adjusting the tone and difficulty of the questions based on perceived emotions.

[0978] Adjustment of survey content

[0979] The generative AI model adjusts the questions entered by the user by linking them to persona information and emotional data, optimizing the questions to make them easier for the user to answer by relaxing the questions or asking more detailed questions depending on the emotion.

[0980] Generate a survey

[0981] The server generates the specified number of questionnaires, and the generative AI model creates a set of variations, each of which reflects persona information and emotional data.

[0982] Output of generated results

[0983] The generated questionnaire is stored on the server and prepared for presentation to the user. The generated results are output in formats such as PDF or Excel, which the user can download.

[0984] Specific examples

[0985] A marketer for a coffee shop chain

[0986] 1. Enter persona information

[0987] The user (marketing staff) enters "female in her 20s," "university student," and "hobby is visiting cafes."

[0988] 2. Enter your question

[0989] Enter "What is your usual drink?" and "What is the most important thing for you in a cafe?"

[0990] 3. Enter the number of questionnaires

[0991] Enter "100" as the number of samples required.

[0992] 4. Emotion recognition

[0993] The device analyzes the user's facial expressions and voice to recognize relaxed emotions.

[0994] 5. Use of Emotional Data

[0995] The server receives the emotion data and invokes a generative AI model, which uses the emotion data to adjust the tone of the question to be a little friendlier.

[0996] 6. Generate questionnaire items

[0997] Generate relevant questionnaire items from the database based on persona information.

[0998] 7. Adjustment of survey content

[0999] Tailor the questions to relate to the user's emotional data, making them more specific, such as "What do you like to drink when you want to relax?"

[1000] 8. Generate a survey

[1001] Generate 100 different questionnaires.

[1002] 9. Output of generated results

[1003] The user downloads the survey and begins the survey.

[1004] In this way, by generating questionnaires that combine emotion recognition functions, this system makes it easier for users to answer and achieves highly accurate data collection.

[1005] The processing flow will be explained below.

[1006] Step 1:

[1007] The user accesses the system's input form using a terminal and enters specific persona information, specifically attribute information such as "age," "occupation," and "hobbies."

[1008] Step 2:

[1009] The user enters the questions they want to ask in the survey into the input form. For example, they enter specific questions such as "What is your favorite drink?" or "What is the most important thing about a cafe?"

[1010] Step 3:

[1011] The user inputs the number of surveys they want to generate. For example, they specify the required sample size, such as "50" or "100."

[1012] Step 4:

[1013] The device monitors the user's emotional state within the input form, capturing the user's facial expressions through the camera and collecting audio data through the microphone.

[1014] Step 5:

[1015] The device's built-in emotion engine analyzes the captured facial and voice data to recognize the user's emotions, such as whether the user is relaxed or stressed.

[1016] Step 6:

[1017] The device sends the recognized emotion data to the server, which receives the emotion data along with the user's persona information, question content, and number of images generated.

[1018] Step 7:

[1019] The server calls the generative AI model, which prepares to automatically generate a questionnaire based on persona information, question content, and emotion data.

[1020] Step 8:

[1021] The server uses a generated AI model to search a database for similar profiles based on the persona information and generate relevant questionnaire items, adjusting the tone and difficulty of the questions based on the perceived emotions.

[1022] Step 9:

[1023] The server uses a generated AI model to correlate the questions entered by the user with persona information and emotional data, adjusting the questions to a more relaxed tone or more detailed questions depending on the emotion.

[1024] Step 10:

[1025] The server generates the specified number of questionnaires, and the generative AI model creates a set of variations, each of which reflects persona information and emotional data.

[1026] Step 11:

[1027] The server saves the generated questionnaire and prepares it for delivery to the user. The generated results are output in a format such as PDF or Excel, and can be downloaded by the user.

[1028] Step 12:

[1029] The user accesses the system's results page using a terminal and downloads the generated survey, which can then be distributed physically or online.

[1030] Example 2

[1031] 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."

[1032] Conventional survey generation systems are unable to optimize survey content taking user emotions into account, which can affect response rates and response quality. Even when using a generation AI model based on persona information and question content, it is difficult to generate a survey that appropriately reflects emotional data. It is necessary to solve these problems and generate more accurate surveys.

[1033] 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.

[1034] In this invention, the server includes a means for inputting specific person information, a means for inputting question content, a means for inputting the number of surveys to be generated, a means for recognizing the user's emotions and optimizing the survey content based on the emotions, a means for automatically generating a survey using a generative artificial intelligence model based on the input information, and a means for outputting the generated survey, thereby enabling the generation of a survey optimized according to the user's emotions.

[1035] "Specific personal information" is attribute information about the survey subject, such as the user's age, occupation, hobbies, etc.

[1036] "Questions" are specific questions you want to ask in the survey.

[1037] The "number of surveys to be generated" is the specific number of questionnaires you want to generate, and the number of samples you need.

[1038] A "generative artificial intelligence model" is an AI model that automatically generates a questionnaire based on input information.

[1039] "Means to recognize emotions and optimize survey content based on that" refers to a function that acquires and analyzes users' emotional data in real time and adjusts the tone and difficulty of the survey content to reflect that.

[1040] "Means for outputting the generated survey" is a function that provides the generated questionnaire to the user in a format that can be used by the user (such as PDF or Excel).

[1041] "Means for searching for similar person profiles from a database" is a function for searching for similar data entries in a database based on persona information.

[1042] The "means for adjusting the question content by relating it to personal information" is a function for optimizing the question content based on the input personal information and adjusting it to a format that is easy for the user to answer.

[1043] The present invention relates to a system that automatically generates an optimized questionnaire by inputting specific personal information and question content and recognizing the user's emotions. This system is realized through interactions between a server, terminals, and users.

[1044] System configuration

[1045] The system consists of the following main components:

[1046] 1. Terminal

[1047] The device is equipped with an interface that allows users to access an input form and enter the necessary information. The device is also equipped with an emotion engine that captures and analyzes the user's facial expressions and voice in real time through a camera and microphone. The specific hardware used includes a camera, microphone, and display.

[1048] 2. Server

[1049] The server includes a function for generating questionnaires using a generative artificial intelligence model based on the emotion data recognized by the emotion engine, the input personal information, the question content, and the number of questionnaires to be generated. The server also includes an output means for providing the generated questionnaires to users. Related software includes a database management system and an AI model execution environment.

[1050] Operational Overview

[1051] The user uses a terminal to access the system's input form and enters specific personal information (e.g., age, occupation, hobbies). Next, the user enters the specific questions they want to ask in the survey and also specifies the number of surveys they want to generate. The terminal uses a camera and microphone to capture the user's facial expressions and voice, which is then analyzed by an emotion engine to generate emotional data for the user. This emotional data is sent to the server and input into the generative artificial intelligence model along with the persona information, questions, and number of surveys to be generated.

[1052] The generative AI model searches a database for similar personas based on persona information and generates relevant questionnaire items. The tone and difficulty of the questions are adjusted based on the recognized emotional data. The generated questionnaire is stored on a server and provided to users in downloadable formats (PDF or Excel).

[1053] Specific examples

[1054] For example, consider the following scenario where a marketer for a coffee shop chain types:

[1055] 1. Enter your persona information:

[1056] The user enters "female in her 20s," "university student," and "hobby is visiting cafes."

[1057] 2. Enter your question:

[1058] Enter "What is your usual drink?" and "What is the most important thing for you in a cafe?"

[1059] 3. Enter the number of surveys:

[1060] Enter "100" as the number of samples required.

[1061] 4. Emotion recognition:

[1062] The device analyzes the user's facial expressions and voice to recognize relaxed emotions.

[1063] 5. Use of Emotional Data:

[1064] The server receives the emotion data and invokes a generative AI model, which uses the emotion data to adjust the tone of the question to be a little friendlier.

[1065] 6. Generate questionnaire items:

[1066] Generate relevant questionnaire items from the database based on persona information.

[1067] 7. Survey Content Adjustment:

[1068] Tailor the questions to relate to the user's emotional data, making them more specific, such as "What do you like to drink when you want to relax?"

[1069] 8. Generate the survey:

[1070] Generate 100 different questionnaires.

[1071] 9. Generated output:

[1072] The user downloads the survey and begins the survey.

[1073] Prompt Sentence Examples

[1074] "Persona information: Female, university student in her 20s, whose hobby is visiting cafes. Questions: What is her usual drink? What is the most important thing about a cafe? Emotional data: Relaxed. Number of surveys to generate: 100. Based on this information, please generate 100 surveys in a friendly tone."

[1075] In this way, the system utilizes user input information and emotional data to automatically generate optimized questionnaires.

[1076] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1077] Step 1:

[1078] The terminal displays the system's input form to the user and asks them to enter specific personal information (e.g., age, occupation, hobbies). Specifically, input fields on the display are used to collect information such as "25 years old," "office worker," and "reading." The entered personal information is then sent to the server by the terminal.

[1079] Step 2:

[1080] The terminal displays a field for the user to enter questions. The user enters the specific questions they want to ask in the survey. For example, they can enter questions such as "How do you usually spend your holidays?" or "What is your favorite genre of book?" The entered questions are then sent to the server.

[1081] Step 3:

[1082] The terminal displays a field for the user to enter the number of surveys they want to generate. The user enters the number of surveys to generate (e.g., "100"). This information is also sent to the server.

[1083] Step 4:

[1084] The device uses a camera and microphone to capture the user's facial expressions and voice in real time, which are then analyzed by an emotion engine. This analysis generates emotion data such as relaxation or stress, which is then sent from the device to a server.

[1085] Step 5:

[1086] The server calls the generative AI model based on the received emotion data, person information, question content, and number of pages to be generated, and generates a prompt. For example, a prompt might include "Persona information: 25 years old, office worker, hobby is reading. Question content: How do you usually spend your holidays? Emotion data: Relaxed. Number of questionnaires to be generated: 100." This prompt is input into the generative AI model.

[1087] Step 6:

[1088] The generative AI model searches a database for similar profiles based on the prompt and generates relevant questionnaire items, such as "specific activities you usually do on your vacation" or "the genre of books you read when relaxing." The generated questionnaire items are saved on the server.

[1089] Step 7:

[1090] The generative AI model adjusts the tone and difficulty of the questions based on the emotional data. For example, if you are feeling relaxed, the question might be, "What books do you read when you want to relax?" This adjustment is also saved on the server.

[1091] Step 8:

[1092] The server generates the specified number of questionnaires. For example, 100 questionnaires are generated, each containing different questions and tones. This generated data is stored on the server.

[1093] Step 9:

[1094] The server outputs the generated survey in PDF or Excel format and provides a download link to the user, who clicks the link to download the survey and begin the survey.

[1095] (Application example 2)

[1096] 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."

[1097] Conventional questionnaire generation systems generate a uniform questionnaire based on the persona information and question content entered by the user, which does not take into account the user's emotional state or ease of response, making it difficult to collect accurate data. Furthermore, the questionnaire questions are not optimized to match the user's emotions, which can cause respondents to feel stressed or less motivated to answer. Furthermore, there is a lack of systems that can efficiently generate a variety of questionnaires.

[1098] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting specific person attribute information, means for inputting question content, means for inputting the number of questionnaires to be generated, means for recognizing emotions during input using an emotion recognition engine installed in the terminal, means for optimizing question content based on the recognized emotions, means for automatically generating questionnaires using a generative AI model based on the input information, and means for outputting the generated questionnaire. As a result, by recognizing the user's emotions and optimizing the question content based on them, it is possible to generate questionnaires that are easy to answer and have high accuracy.

[1099] "Specific person attribute information" is attribute information related to a specific individual, such as age, occupation, and hobbies.

[1100] The "question content" refers to the specific questions you want to ask in the questionnaire.

[1101] "Number of questionnaires to generate" is the number of questionnaires that the generative AI model will automatically generate, as specified by the user.

[1102] An "emotion recognition engine" is an engine that analyzes the user's facial expressions and voice while inputting data and recognizes their emotions.

[1103] "Optimizing question content" means adjusting the tone and difficulty of questions based on perceived sentiment.

[1104] A "generative AI model" is an artificial intelligence model that automatically generates a questionnaire based on input information.

[1105] "Automatically generating a questionnaire" means that the generative AI model creates a questionnaire based on the input personal attribute information, question content, and recognized emotion data.

[1106] "Outputting a questionnaire" means generating data in a format such as PDF or Excel in order to present the generated questionnaire to the user.

[1107] The present invention relates to a system that automatically generates an optimized questionnaire by inputting specific person attribute information and question content and utilizing an emotion recognition engine. The system configuration and examples of the present invention will be described in detail below.

[1108] System Configuration

[1109] The system of the present invention includes the following major components:

[1110] 1. Terminal: A device that allows a user to input information. Examples include tablets and interactive displays, and are equipped with a camera and microphone.

[1111] 2. Emotion Recognition Engine: Software that analyzes the user's facial expressions and voice to recognize emotions. Specifically, it uses the Hugging Face Transformers emotion analysis pipeline and OpenCV.

[1112] 3. Server: Calls the generative AI model based on persona information, question content, number of sheets to be generated, and emotional data, and automatically generates an optimized questionnaire.

[1113] 4. Generative AI model: An artificial intelligence model that automatically generates questionnaires based on user-entered information and emotion data. Hugging Face Transformers and TextBlob are used.

[1114] 5. Database: A database for searching for similar person images based on the entered person attribute information.

[1115] Data processing and calculation

[1116] The server processes the data in the following steps:

[1117] 1. Collecting personal attribute information: The user enters personal attribute information such as age, occupation, and hobbies into an input form on the terminal.

[1118] 2. Collecting questions: Users input the questions they want to ask.

[1119] 3. Emotion recognition: The device's camera and microphone capture the user's facial expressions and voice, and the emotion recognition engine analyzes them to recognize emotions.

[1120] 4. Question Optimization: Optimize questions and adjust the tone and difficulty of questions based on perceived sentiment.

[1121] 5. Questionnaire generation: Use generative AI models to automatically generate questionnaires.

[1122] 6. Questionnaire output: The generated questionnaire can be output in formats such as PDF or Excel and made available for download by users.

[1123] Examples of specific examples and prompts

[1124] As a concrete example, consider the case where a marketing manager at a brick-and-mortar store wants to survey customers at a cafe.

[1125] The marketing staff enters the following information into the input form on the terminal:

[1126] Persona information: "Female in her 20s," "University student," "Hobby is visiting cafes"

[1127] Questions included: "What is your usual drink?" and "What is the most important thing for you in a cafe?"

[1128] The emotion recognition engine recognizes the agent's relaxed emotions and adjusts the tone of the questions to be a little friendlier. Based on the information and emotional data entered by the user, the generative AI model automatically generates 50 optimized questionnaires.

[1129] An example prompt is:

[1130] Persona information: Female in her 20s, university student, enjoys visiting cafes

[1131] Questions: What is your favorite drink? What is the most important thing for you in a cafe?

[1132] Emotion: Relaxed

[1133] Number of questionnaires: 50

[1134] This makes it possible to recognize the user's emotions and optimize the content of the questions based on them, thereby generating highly accurate questionnaires that are easy to answer.

[1135] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1136] Step 1:

[1137] The user accesses an input form on the terminal and inputs personal attribute information such as age, occupation, hobbies, etc. This allows the system to collect basic information about the user and sends this information to the server for use in the next step. The input data is text information such as age, occupation, hobbies, etc., and the server saves it as personal attribute information.

[1138] Step 2:

[1139] The user enters the question they want to ask into the input form on the device. At this time, the question is a specific text question, such as "What is your usual drink?" or "What is the most important thing for you in a cafe?" This is also sent to the server. The server saves this input data as the question.

[1140] Step 3:

[1141] The user inputs the number of questionnaires to be generated in a numerical format. For example, "50" or "100" is specified. This numerical data is also sent to the server, and the server saves it as the number of questionnaires to be generated.

[1142] Step 4:

[1143] The device's emotion recognition engine analyzes the user's facial expressions and voice to recognize their emotions in real time. Specifically, the device's camera and microphone are used to capture the user's facial expression data and voice data, which are then analyzed by an emotion recognition algorithm (e.g., the Hugging Face Transformers emotion analysis pipeline). The results of this analysis are sent to the server as emotion labels, such as relaxed, stressed, or excited. The server then stores this data as emotion data.

[1144] Step 5:

[1145] The server calls a generative AI model based on the received personal attribute information, question content, number of pages to be generated, and emotional data, and optimizes the question content based on the emotion. This process adjusts the tone (e.g., friendly, formal) and difficulty of the question depending on the emotional data. The generative AI model receives input data in text format and generates optimized question content.

[1146] Step 6:

[1147] The generative AI model automatically generates a specified number of questionnaires based on the optimized question content. These questionnaires reflect personal attribute information, question content, and emotional data, and the server generates them as a series of text-format questionnaires.

[1148] Step 7:

[1149] The generated questionnaire is output in a file format such as PDF or Excel and saved on the server. A notification is sent to the user's device so that the file can be downloaded. The user clicks the download link to obtain the generated questionnaire.

[1150] Through these steps, we have achieved a system that recognizes users' emotions and automatically generates an optimized questionnaire that reflects those emotions. This process makes it possible to collect questionnaire data that is easy to respond to and highly accurate.

[1151] 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.

[1152] 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.

[1153] 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.

[1154] [Fourth embodiment]

[1155] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1156] 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.

[1157] 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).

[1158] 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.

[1159] 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.

[1160] 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).

[1161] 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.

[1162] 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.

[1163] 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.

[1164] 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.

[1165] 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.

[1166] 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.

[1167] 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."

[1168] The system of the present invention uses a generative AI model to efficiently and automatically generate questionnaires by inputting specific persona information and specifying the question content and number of questionnaires to be generated. This system allows companies and marketers to quickly create targeted questionnaires while significantly reducing labor and costs.

[1169] Program processing

[1170] Entering persona information

[1171] The user connects to the system's input form using a terminal and enters specific persona information such as "age," "occupation," and "hobbies." This information is used for subsequent processing within the system.

[1172] Enter your question

[1173] The user enters the questions they want to ask in the survey in multiple lines into the input form. For example, they can enter specific questions such as "What is your favorite drink?" or "What is the most important thing about a cafe?"

[1174] Enter the number of questionnaires

[1175] The user inputs the number of surveys they want to generate, for example, "50" or "100," specifying the number of samples they require.

[1176] Calling the generative AI model and generating a survey

[1177] The server calls the generative AI model based on the persona information, question content, and number of pages to be generated obtained from the user. This model automatically generates new questionnaires based on learning data such as past survey data. The generative AI model searches for similar personas in an existing database related to the persona information and creates related questionnaire items. It then associates the entered questions with the persona and adjusts them to generate a diverse set of questionnaires.

[1178] Output of generated results

[1179] The generated questionnaire is saved on the server and the specified number of questionnaires are prepared. The questionnaires are presented to users in formats such as PDF or Excel, and can be downloaded by the users. The generated questionnaires can also be distributed physically or online.

[1180] Specific examples

[1181] A marketer for a coffee shop chain

[1182] 1. Enter persona information

[1183] The user (marketing staff) enters "female in her 20s," "university student," and "hobby is visiting cafes."

[1184] 2. Enter your question

[1185] Enter "What is your usual drink?" and "What is the most important thing for you in a cafe?"

[1186] 3. Enter the number of questionnaires

[1187] Enter "100" as the number of samples required.

[1188] 4. Generate a survey

[1189] The server calls the generative AI model and automatically generates 100 questionnaires based on the specified persona information and questions.

[1190] 5. Presentation of results

[1191] The generated questionnaire is provided to the user in a downloadable format, which the person in charge can use to start the survey.

[1192] Through the above process, it is possible to efficiently collect questionnaires suited to specific personas and use them to improve and develop products and services. This system provides a means for generating such questionnaires quickly and effectively.

[1193] The processing flow will be explained below.

[1194] Step 1:

[1195] The user accesses the system's input form using a terminal and enters specific persona information, such as attributes such as "age," "occupation," and "hobbies."

[1196] Step 2:

[1197] The user enters the questions they want to ask in the survey into the input form. Enter specific questions such as "What is your favorite drink?" or "What is the most important thing for you in a cafe?"

[1198] Step 3:

[1199] The user enters the number of surveys they want to generate, for example, "50" or "100," to specify the number of samples required.

[1200] Step 4:

[1201] The server receives the specific persona information, question content, and number of copies to be generated sent by the user.

[1202] Step 5:

[1203] The server calls the generative AI model, which learns from existing persona data and past survey data in the database.

[1204] Step 6:

[1205] The generative AI model searches the database for similar personas based on the persona information and generates related questionnaire items, resulting in the creation of initial questionnaire items according to the persona information.

[1206] Step 7:

[1207] The server uses a generative AI model to associate the questions entered by the user with the persona and adjust them, thereby generating questions optimized for each persona.

[1208] Step 8:

[1209] The server generates the specified number of questionnaires. The generative AI model automatically generates a diverse set of questionnaires based on the adjusted question content, adding variation to each questionnaire.

[1210] Step 9:

[1211] The server saves the generated questionnaire and prepares it for presentation to the user. The generated questionnaire is output in a common file format (PDF, Excel, etc.).

[1212] Step 10:

[1213] The user downloads the generated survey. The user accesses the results page of the system using a terminal and downloads the generated survey, which allows for physical distribution or online distribution of the survey.

[1214] Example 1

[1215] 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."

[1216] Traditional survey creation methods require a lot of time and effort for companies and marketers to create surveys that are appropriate for their target personas. Furthermore, creating surveys manually is prone to human error, making it difficult to operate efficiently.

[1217] 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.

[1218] In this invention, the server includes means for inputting specific attribute information, means for inputting question content, means for inputting the number of questionnaires to be generated, means for automatically generating questionnaires using a generative AI model based on the input information, means for saving and outputting the generated questionnaires, and means for making the generated questionnaires available for download. This enables companies and marketers to efficiently automatically generate high-quality questionnaires and quickly utilize them.

[1219] "Attribute information" refers to individual characteristics of a specific target person, such as age, occupation, hobbies, etc.

[1220] "Question content" refers to the specific content of the questions posed to the target person in the questionnaire.

[1221] A "generative AI model" refers to an artificial intelligence model that automatically generates new questionnaires based on past data and learning data.

[1222] A "database" refers to a system that stores information for searching for similar person images based on specific attribute information.

[1223] "Downloadable means" refers to the technical mechanism that allows a user to save the generated survey to a device.

[1224] "Means for storage and output" refers to the technical mechanism by which the generated survey is stored in a particular format and provided to the user.

[1225] The present invention relates to a system for efficiently generating questionnaires using a generative AI model. This system inputs attribute information, question content, and the number of questionnaires to be generated, automatically generates questionnaires based on the input information, and provides the generated questionnaires to users. Specific embodiments for implementing the present invention are described below.

[1226] The user accesses the system's web interface using a terminal and inputs attribute information (age, occupation, hobbies, etc.). Next, the user inputs the questions and then specifies the number of questionnaires to be generated. This web interface is provided through a browser.

[1227] Once the user has completed entering the attribute information, question content, and number of questionnaires, the server receives this data and calls the generative AI model. This generative AI model automatically generates new questionnaires based on past survey data. Specifically, the generative AI model searches for similar persona profiles from past data and automatically creates related question items. It also adjusts the entered question content by relating it to the persona information, generating a diverse set of questionnaires.

[1228] The generated survey is saved on the server and output in a specified format (usually PDF or Excel format). This output survey is provided in a format that users can download. Users can save the generated survey to their devices by accessing the system again and clicking the download link. Users can then print these surveys or distribute them online.

[1229] As a concrete example, consider a situation where the target audience is a marketing manager for a coffee shop chain. Below is an example of the concrete example and a prompt sentence.

[1230] Specific examples

[1231] 1. Enter persona information

[1232] The user (marketing staff) enters "female in her 20s," "university student," and "hobby is visiting cafes."

[1233] 2. Enter your question

[1234] Enter "What is your usual drink?" and "What is the most important thing for you in a cafe?"

[1235] 3. Enter the number of questionnaires

[1236] Enter "100" as the number of samples required.

[1237] 4. Generate a survey

[1238] The server calls the generative AI model and automatically generates 100 questionnaires based on the specified persona information and question content.

[1239] 5. Presentation of results

[1240] The generated questionnaire is provided to the user in a downloadable format, which the person in charge can use to start the survey.

[1241] Prompt Sentence Examples

[1242] prompt:

[1243] Generate your survey based on the following persona information:

[1244] Persona: Female in her 20s, university student, hobby is cafe hopping

[1245] Questions:

[1246] 1. What is your favorite drink?

[1247] 2. What is the most important thing to you about your cafe?

[1248] Number of cards generated: 100

[1249] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1250] Step 1: Enter your persona information

[1251] 1. The user uses a terminal to access the system's web interface.

[1252] 2. The user accesses a form to enter attribute information.

[1253] 3. The user enters attribute information such as "age," "occupation," and "hobbies," and clicks the "Submit" button.

[1254] 4. The server receives the entered attribute information and stores it in the database.

[1255] Specific operation: The user opens a browser and accesses the system's URL. He enters "25 years old" in the "Age" field, "University student" in the "Occupation" field, and "Cafe hopping" in the "Hobby" field, and clicks the submit button. The server saves this information in the database.

[1256] Step 2: Enter the question content

[1257] 1. After submitting the persona information, the user is redirected to a form where they can enter their questions.

[1258] 2. The user enters the questions they want to ask in the survey.

[1259] 3. The user enters the question content on multiple lines and clicks the "Submit" button.

[1260] 4. The server receives the entered questions, associates them with attribute information, and stores them in a database.

[1261] Specific operation: Enter "What is your usual drink?" in the "Question 1" field and "What is the most important thing for you in a cafe?" in the "Question 2" field, then click the submit button. The server associates these questions with attribute information and saves them in the database.

[1262] Step 3: Enter the number of surveys

[1263] 1. After submitting the questionnaire, the user is redirected to a form where they can enter the number of surveys.

[1264] 2. The user enters the number of questionnaires to be generated.

[1265] 3. The user confirms the number of copies entered and clicks the "Submit" button.

[1266] 4. The server receives the number of sheets entered and stores it in a database along with the attribute information and question content.

[1267] What happens: You enter "100" in the "Quantity" field and click the submit button. The server stores this information in a database.

[1268] Step 4: Invoke the generative AI model and generate a survey

[1269] 1. Once the user has entered all the data, the server calls the generative AI model based on the attribute information, question content, and number of sheets to be generated.

[1270] 2. The generative AI model references past survey data and automatically generates a new survey based on the input information.

[1271] 3. The generative AI model searches the database for similar person profiles based on attribute information and generates relevant questions.

[1272] 4. The entered questions are adjusted in relation to attribute information to generate a diverse questionnaire set.

[1273] Specific operation: The server passes the attribute information "25 years old," "university student," and "cafe hopping" along with the questions "What is your usual drink?" and "What is the most important thing for you in a cafe?" to the generative AI model. The generative AI model analyzes similar patterns from past survey data and generates 100 new surveys.

[1274] Step 5: Output the generated results

[1275] 1. The generated questionnaire is saved on the server and output in the specified format.

[1276] 2. The server saves the generated survey in PDF or Excel format.

[1277] 3. The user receives a notification from the server and retrieves the generated survey via a download link.

[1278] 4. Users download the survey to their devices and print or distribute it online as needed.

[1279] Specific operation: The server saves the generated 100 questionnaires in PDF format and sends a notification to the user. The user clicks the download link to download the questionnaire and use it within the company.

[1280] The above are the specific processing steps of this system.

[1281] (Application example 1)

[1282] 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."

[1283] Conventional survey generation systems have difficulty quickly and efficiently generating questions suited to specific personas, and lack the functionality to distribute, collect, and analyze the generated surveys via the Internet. This makes it difficult to effectively collect survey results from target demographics in advertising and marketing campaigns, resulting in the inability to maximize the effectiveness of the campaign.

[1284] 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.

[1285] In this invention, the server includes means for inputting specific persona information, means for inputting question content, means for inputting the number of questionnaires to be generated, means for automatically generating questionnaires using a generative AI model, means for distributing the generated questionnaires via the Internet, means for collecting and analyzing the results of the generated questionnaires, and means for outputting the generated questionnaires. This makes it possible to quickly and efficiently generate, distribute, collect, and analyze questionnaires tailored to targets.

[1286] "Specific persona information" is information about a specific target demographic, and includes attribute information such as age, gender, occupation, and hobbies.

[1287] "Question content" refers to the wording of the items asked to respondents in the questionnaire.

[1288] The "number of questionnaires to be generated" refers to the number of questionnaire sets to be generated, and more specifically, indicates the number of samples to be generated.

[1289] A "generative AI model" is an artificial intelligence model that automatically generates a questionnaire based on the input persona information and question content.

[1290] "Means of automatic generation" refers to the process of creating a questionnaire using a generative AI model, taking persona information and question content as input.

[1291] "Means of distribution via the Internet" refers to a method of sending the generated questionnaire to subjects via the Internet.

[1292] "Means of collection and analysis" refers to the process of receiving and analyzing the response data from the distributed questionnaire.

[1293] "Means of output" refers to a method of providing the generated questionnaire to the user in a format such as PDF or Excel.

[1294] This invention is a system that allows marketers and advertising agencies to efficiently generate, distribute, collect, and analyze targeted questionnaires. Specific methods for implementing this system are described below.

[1295] Hardware and Software Configuration

[1296] This system is realized mainly using the following hardware and software.

[1297] Hardware: smartphones, tablets, servers

[1298] Software: Python, TensorFlow, Flask (server-side framework)

[1299] System processing procedure

[1300] 1. User Input

[1301] Users connect to the system using a smartphone or tablet and enter specific persona information, questions, and the number of questionnaires to be generated. Persona information includes age, gender, occupation, and hobbies.

[1302] 2. Questionnaire generation

[1303] The server receives the information entered by the user and calls a generative AI model based on that information. This generative AI model automatically generates the specified number of questionnaires based on the entered persona information and questions. The generative AI model learns from past survey data, enabling it to generate highly accurate surveys.

[1304] 3. Survey distribution

[1305] The server distributes the generated survey to the designated target audience via the Internet, using email, social media, advertising platforms, etc.

[1306] 4. Collection and analysis of survey results

[1307] The response data from the distributed survey is sent to a server where it is collected and analyzed. The collected data is analyzed using statistical analysis tools to be used in marketing strategies.

[1308] 5. Output of generated results

[1309] The generated questionnaire is provided to the user in formats such as PDF or Excel, and can be downloaded and used.

[1310] Specific examples

[1311] A marketer wants to generate 100 questionnaires for an advertising campaign targeting a persona of a man in his 20s whose hobby is sports:

[1312] 1. Enter persona information

[1313] The user enters "Persona information: 20s, male, sports."

[1314] 2. Enter your question

[1315] Enter the questions "Which sports brand do you like?" and "What is the most important thing to consider when choosing sportswear?"

[1316] 3. Enter the number of questionnaires

[1317] The user enters "Number of surveys to generate: 100".

[1318] 4. Examples of prompt sentences

[1319] Enter the following as the prompt:

[1320] Persona information: 20s, male, sports

[1321] Questions asked:

[1322] 1. Which sports brand do you like?

[1323] 2. What is the most important thing to consider when choosing sportswear?

[1324] Number of copies generated: 100

[1325] By distributing the questionnaires generated in this way via the Internet and collecting and analyzing the results, an effective advertising campaign can be realized.

[1326] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1327] Step 1:

[1328] Users connect to the system's input form using a smartphone or tablet and enter specific persona information such as age, gender, occupation, and hobbies. The persona information entered by the user becomes the reference data for identifying targets in subsequent processing.

[1329] Step 2:

[1330] The user inputs questions based on the information they want to obtain. Questions include specific questions such as, "Which brand of clothing do you usually buy?" or "What is the most important point when choosing sportswear?" The input questions are sent to the server as data to be used in generating the questionnaire.

[1331] Step 3:

[1332] The user inputs the number of surveys they want to generate, for example, a sample size such as "50" or "100." This number is sent to the server to determine the number of survey sets to generate.

[1333] Step 4:

[1334] The server calls the generative AI model based on the persona information, question content, and number of questionnaires received from the user. The generative AI model searches for similar personas from an existing database related to persona information, adjusts the input questions, and automatically generates a diverse set of questionnaires. The generative AI model uses TensorFlow and utilizes past survey data as learning data.

[1335] Step 5:

[1336] The server distributes the generated survey via the Internet, using email, social media, advertising platforms, etc., to send the survey to the designated target audience. The distribution method is realized through the Flask framework.

[1337] Step 6:

[1338] The user's device receives the survey results. The server collects the data and analyzes it using statistical analysis tools. This provides insights into the preferences and opinions of the target demographic.

[1339] Step 7:

[1340] The server converts the generated survey into PDF or Excel format and provides it for users to download, so that users can use the survey in their advertising campaigns and marketing strategies.

[1341] 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.

[1342] This invention combines an emotion engine with a system that automatically generates questionnaires using a generative AI model by inputting specific persona information and specifying the question content and number of questionnaires to be generated. This system recognizes the user's emotions and further optimizes the questionnaire content based on those emotions.

[1343] Program processing

[1344] Entering persona information

[1345] The user accesses the system's input form using a terminal and enters specific persona information, including attribute information such as "age," "occupation," and "hobbies."

[1346] Enter your question

[1347] The user enters the questions they want to ask in the survey into the input form. Enter specific questions such as "What is your favorite drink?" or "What is the most important thing for you in a cafe?"

[1348] Enter the number of questionnaires

[1349] The user inputs the number of surveys they want to generate. For example, they specify the required sample size, such as "50" or "100."

[1350] emotion recognition

[1351] The device is equipped with an emotion engine that recognizes the user's emotions from facial expressions and voice input. For example, it analyzes data obtained through a camera and microphone to detect emotions such as whether the user is relaxed or stressed.

[1352] Using sentiment data

[1353] The server receives the emotion data recognized by the emotion engine. Based on the received emotion data, persona information, question content, and number of pages to be generated, it calls a generative AI model. This model optimizes the questionnaire content by reflecting the emotion data.

[1354] Generate questionnaire items

[1355] The generative AI model uses persona information to search a database for similar profiles and generate relevant survey questions, adjusting the tone and difficulty of the questions based on perceived emotions.

[1356] Adjustment of survey content

[1357] The generative AI model adjusts the questions entered by the user by linking them to persona information and emotional data, optimizing the questions to make them easier for the user to answer by relaxing the questions or asking more detailed questions depending on the emotion.

[1358] Generate a survey

[1359] The server generates the specified number of questionnaires, and the generative AI model creates a set of variations, each of which reflects persona information and emotional data.

[1360] Output of generated results

[1361] The generated questionnaire is stored on the server and prepared for presentation to the user. The generated results are output in formats such as PDF or Excel, which the user can download.

[1362] Specific examples

[1363] A marketer for a coffee shop chain

[1364] 1. Enter persona information

[1365] The user (marketing staff) enters "female in her 20s," "university student," and "hobby is visiting cafes."

[1366] 2. Enter your question

[1367] Enter "What is your usual drink?" and "What is the most important thing for you in a cafe?"

[1368] 3. Enter the number of questionnaires

[1369] Enter "100" as the number of samples required.

[1370] 4. Emotion recognition

[1371] The device analyzes the user's facial expressions and voice to recognize relaxed emotions.

[1372] 5. Use of Emotional Data

[1373] The server receives the emotion data and invokes a generative AI model, which uses the emotion data to adjust the tone of the question to be a little friendlier.

[1374] 6. Generate questionnaire items

[1375] Generate relevant questionnaire items from the database based on persona information.

[1376] 7. Adjustment of survey content

[1377] Tailor the questions to relate to the user's emotional data, making them more specific, such as "What do you like to drink when you want to relax?"

[1378] 8. Generate a survey

[1379] Generate 100 different questionnaires.

[1380] 9. Output of generated results

[1381] The user downloads the survey and begins the survey.

[1382] In this way, by generating questionnaires that combine emotion recognition functions, this system makes it easier for users to answer and achieves highly accurate data collection.

[1383] The processing flow will be explained below.

[1384] Step 1:

[1385] The user accesses the system's input form using a terminal and enters specific persona information, specifically attribute information such as "age," "occupation," and "hobbies."

[1386] Step 2:

[1387] The user enters the questions they want to ask in the survey into the input form. For example, they enter specific questions such as "What is your favorite drink?" or "What is the most important thing about a cafe?"

[1388] Step 3:

[1389] The user inputs the number of surveys they want to generate. For example, they specify the required sample size, such as "50" or "100."

[1390] Step 4:

[1391] The device monitors the user's emotional state within the input form, capturing the user's facial expressions through the camera and collecting audio data through the microphone.

[1392] Step 5:

[1393] The device's built-in emotion engine analyzes the captured facial and voice data to recognize the user's emotions, such as whether the user is relaxed or stressed.

[1394] Step 6:

[1395] The device sends the recognized emotion data to the server, which receives the emotion data along with the user's persona information, question content, and number of images generated.

[1396] Step 7:

[1397] The server calls the generative AI model, which prepares to automatically generate a questionnaire based on persona information, question content, and emotion data.

[1398] Step 8:

[1399] The server uses a generated AI model to search a database for similar profiles based on the persona information and generate relevant questionnaire items, adjusting the tone and difficulty of the questions based on the perceived emotions.

[1400] Step 9:

[1401] The server uses a generated AI model to correlate the questions entered by the user with persona information and emotional data, adjusting the questions to a more relaxed tone or more detailed questions depending on the emotion.

[1402] Step 10:

[1403] The server generates the specified number of questionnaires, and the generative AI model creates a set of variations, each of which reflects persona information and emotional data.

[1404] Step 11:

[1405] The server saves the generated questionnaire and prepares it for delivery to the user. The generated results are output in a format such as PDF or Excel, and can be downloaded by the user.

[1406] Step 12:

[1407] The user accesses the system's results page using a terminal and downloads the generated survey, which can then be distributed physically or online.

[1408] Example 2

[1409] 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."

[1410] Conventional survey generation systems are unable to optimize survey content taking user emotions into account, which can affect response rates and response quality. Even when using a generation AI model based on persona information and question content, it is difficult to generate a survey that appropriately reflects emotional data. It is necessary to solve these problems and generate more accurate surveys.

[1411] 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.

[1412] In this invention, the server includes a means for inputting specific person information, a means for inputting question content, a means for inputting the number of surveys to be generated, a means for recognizing the user's emotions and optimizing the survey content based on the emotions, a means for automatically generating a survey using a generative artificial intelligence model based on the input information, and a means for outputting the generated survey, thereby enabling the generation of a survey optimized according to the user's emotions.

[1413] "Specific personal information" is attribute information about the survey subject, such as the user's age, occupation, hobbies, etc.

[1414] "Questions" are specific questions you want to ask in the survey.

[1415] The "number of surveys to be generated" is the specific number of questionnaires you want to generate, and the number of samples you need.

[1416] A "generative artificial intelligence model" is an AI model that automatically generates a questionnaire based on input information.

[1417] "Means to recognize emotions and optimize survey content based on that" refers to a function that acquires and analyzes users' emotional data in real time and adjusts the tone and difficulty of the survey content to reflect that.

[1418] "Means for outputting the generated survey" is a function that provides the generated questionnaire to the user in a format that can be used by the user (such as PDF or Excel).

[1419] "Means for searching for similar person profiles from a database" is a function for searching for similar data entries in a database based on persona information.

[1420] The "means for adjusting the question content by relating it to personal information" is a function for optimizing the question content based on the input personal information and adjusting it to a format that is easy for the user to answer.

[1421] The present invention relates to a system that automatically generates an optimized questionnaire by inputting specific personal information and question content and recognizing the user's emotions. This system is realized through interactions between a server, terminals, and users.

[1422] System configuration

[1423] The system consists of the following main components:

[1424] 1. Terminal

[1425] The device is equipped with an interface that allows users to access an input form and enter the necessary information. The device is also equipped with an emotion engine that captures and analyzes the user's facial expressions and voice in real time through a camera and microphone. The specific hardware used includes a camera, microphone, and display.

[1426] 2. Server

[1427] The server includes a function for generating questionnaires using a generative artificial intelligence model based on the emotion data recognized by the emotion engine, the input personal information, the question content, and the number of questionnaires to be generated. The server also includes an output means for providing the generated questionnaires to users. Related software includes a database management system and an AI model execution environment.

[1428] Operational Overview

[1429] The user uses a terminal to access the system's input form and enters specific personal information (e.g., age, occupation, hobbies). Next, the user enters the specific questions they want to ask in the survey and also specifies the number of surveys they want to generate. The terminal uses a camera and microphone to capture the user's facial expressions and voice, which is then analyzed by an emotion engine to generate emotional data for the user. This emotional data is sent to the server and input into the generative artificial intelligence model along with the persona information, questions, and number of surveys to be generated.

[1430] The generative AI model searches a database for similar personas based on persona information and generates relevant questionnaire items. The tone and difficulty of the questions are adjusted based on the recognized emotional data. The generated questionnaire is stored on a server and provided to users in downloadable formats (PDF or Excel).

[1431] Specific examples

[1432] For example, consider the following scenario where a marketer for a coffee shop chain types:

[1433] 1. Enter your persona information:

[1434] The user enters "female in her 20s," "university student," and "hobby is visiting cafes."

[1435] 2. Enter your question:

[1436] Enter "What is your usual drink?" and "What is the most important thing for you in a cafe?"

[1437] 3. Enter the number of surveys:

[1438] Enter "100" as the number of samples required.

[1439] 4. Emotion recognition:

[1440] The device analyzes the user's facial expressions and voice to recognize relaxed emotions.

[1441] 5. Use of Emotional Data:

[1442] The server receives the emotion data and invokes a generative AI model, which uses the emotion data to adjust the tone of the question to be a little friendlier.

[1443] 6. Generate questionnaire items:

[1444] Generate relevant questionnaire items from the database based on persona information.

[1445] 7. Survey Content Adjustment:

[1446] Tailor the questions to relate to the user's emotional data, making them more specific, such as "What do you like to drink when you want to relax?"

[1447] 8. Generate the survey:

[1448] Generate 100 different questionnaires.

[1449] 9. Generated output:

[1450] The user downloads the survey and begins the survey.

[1451] Prompt Sentence Examples

[1452] "Persona information: Female, university student in her 20s, whose hobby is visiting cafes. Questions: What is her usual drink? What is the most important thing about a cafe? Emotional data: Relaxed. Number of surveys to generate: 100. Based on this information, please generate 100 surveys in a friendly tone."

[1453] In this way, the system utilizes user input information and emotional data to automatically generate optimized questionnaires.

[1454] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1455] Step 1:

[1456] The terminal displays the system's input form to the user and asks them to enter specific personal information (e.g., age, occupation, hobbies). Specifically, input fields on the display are used to collect information such as "25 years old," "office worker," and "reading." The entered personal information is then sent to the server by the terminal.

[1457] Step 2:

[1458] The terminal displays a field for the user to enter questions. The user enters the specific questions they want to ask in the survey. For example, they can enter questions such as "How do you usually spend your holidays?" or "What is your favorite genre of book?" The entered questions are then sent to the server.

[1459] Step 3:

[1460] The terminal displays a field for the user to enter the number of surveys they want to generate. The user enters the number of surveys to generate (e.g., "100"). This information is also sent to the server.

[1461] Step 4:

[1462] The device uses a camera and microphone to capture the user's facial expressions and voice in real time, which are then analyzed by an emotion engine. This analysis generates emotion data such as relaxation or stress, which is then sent from the device to a server.

[1463] Step 5:

[1464] The server calls the generative AI model based on the received emotion data, person information, question content, and number of pages to be generated, and generates a prompt. For example, a prompt might include "Persona information: 25 years old, office worker, hobby is reading. Question content: How do you usually spend your holidays? Emotion data: Relaxed. Number of questionnaires to be generated: 100." This prompt is input into the generative AI model.

[1465] Step 6:

[1466] The generative AI model searches a database for similar profiles based on the prompt and generates relevant questionnaire items, such as "specific activities you usually do on your vacation" or "the genre of books you read when relaxing." The generated questionnaire items are saved on the server.

[1467] Step 7:

[1468] The generative AI model adjusts the tone and difficulty of the questions based on the emotional data. For example, if you are feeling relaxed, the question might be, "What books do you read when you want to relax?" This adjustment is also saved on the server.

[1469] Step 8:

[1470] The server generates the specified number of questionnaires. For example, 100 questionnaires are generated, each containing different questions and tones. This generated data is stored on the server.

[1471] Step 9:

[1472] The server outputs the generated survey in PDF or Excel format and provides a download link to the user, who clicks the link to download the survey and begin the survey.

[1473] (Application example 2)

[1474] 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."

[1475] Conventional questionnaire generation systems generate a uniform questionnaire based on the persona information and question content entered by the user, which does not take into account the user's emotional state or ease of response, making it difficult to collect accurate data. Furthermore, the questionnaire questions are not optimized to match the user's emotions, which can cause respondents to feel stressed or less motivated to answer. Furthermore, there is a lack of systems that can efficiently generate a variety of questionnaires.

[1476] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting specific person attribute information, means for inputting question content, means for inputting the number of questionnaires to be generated, means for recognizing emotions during input using an emotion recognition engine installed in the terminal, means for optimizing question content based on the recognized emotions, means for automatically generating questionnaires using a generative AI model based on the input information, and means for outputting the generated questionnaire. As a result, by recognizing the user's emotions and optimizing the question content based on them, it is possible to generate questionnaires that are easy to answer and have high accuracy.

[1477] "Specific person attribute information" is attribute information related to a specific individual, such as age, occupation, and hobbies.

[1478] The "question content" refers to the specific questions you want to ask in the questionnaire.

[1479] "Number of questionnaires to generate" is the number of questionnaires that the generative AI model will automatically generate, as specified by the user.

[1480] An "emotion recognition engine" is an engine that analyzes the user's facial expressions and voice while inputting data and recognizes their emotions.

[1481] "Optimizing question content" means adjusting the tone and difficulty of questions based on perceived sentiment.

[1482] A "generative AI model" is an artificial intelligence model that automatically generates a questionnaire based on input information.

[1483] "Automatically generating a questionnaire" means that the generative AI model creates a questionnaire based on the input personal attribute information, question content, and recognized emotion data.

[1484] "Outputting a questionnaire" means generating data in a format such as PDF or Excel in order to present the generated questionnaire to the user.

[1485] The present invention relates to a system that automatically generates an optimized questionnaire by inputting specific person attribute information and question content and utilizing an emotion recognition engine. The system configuration and examples of the present invention will be described in detail below.

[1486] System Configuration

[1487] The system of the present invention includes the following major components:

[1488] 1. Terminal: A device that allows a user to input information. Examples include tablets and interactive displays, and are equipped with a camera and microphone.

[1489] 2. Emotion Recognition Engine: Software that analyzes the user's facial expressions and voice to recognize emotions. Specifically, it uses the Hugging Face Transformers emotion analysis pipeline and OpenCV.

[1490] 3. Server: Calls the generative AI model based on persona information, question content, number of sheets to be generated, and emotional data, and automatically generates an optimized questionnaire.

[1491] 4. Generative AI model: An artificial intelligence model that automatically generates questionnaires based on user-entered information and emotion data. Hugging Face Transformers and TextBlob are used.

[1492] 5. Database: A database for searching for similar person images based on the entered person attribute information.

[1493] Data processing and calculation

[1494] The server processes the data in the following steps:

[1495] 1. Collecting personal attribute information: The user enters personal attribute information such as age, occupation, and hobbies into an input form on the terminal.

[1496] 2. Collecting questions: Users input the questions they want to ask.

[1497] 3. Emotion recognition: The device's camera and microphone capture the user's facial expressions and voice, and the emotion recognition engine analyzes them to recognize emotions.

[1498] 4. Question Optimization: Optimize questions and adjust the tone and difficulty of questions based on perceived sentiment.

[1499] 5. Questionnaire generation: Use generative AI models to automatically generate questionnaires.

[1500] 6. Questionnaire output: The generated questionnaire can be output in formats such as PDF or Excel and made available for download by users.

[1501] Examples of specific examples and prompts

[1502] As a concrete example, consider the case where a marketing manager at a brick-and-mortar store wants to survey customers at a cafe.

[1503] The marketing staff enters the following information into the input form on the terminal:

[1504] Persona information: "Female in her 20s," "University student," "Hobby is visiting cafes"

[1505] Questions included: "What is your usual drink?" and "What is the most important thing for you in a cafe?"

[1506] The emotion recognition engine recognizes the agent's relaxed emotions and adjusts the tone of the questions to be a little friendlier. Based on the information and emotional data entered by the user, the generative AI model automatically generates 50 optimized questionnaires.

[1507] An example prompt is:

[1508] Persona information: Female in her 20s, university student, enjoys visiting cafes

[1509] Questions: What is your favorite drink? What is the most important thing for you in a cafe?

[1510] Emotion: Relaxed

[1511] Number of questionnaires: 50

[1512] This makes it possible to recognize the user's emotions and optimize the content of the questions based on them, thereby generating highly accurate questionnaires that are easy to answer.

[1513] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1514] Step 1:

[1515] The user accesses an input form on the terminal and inputs personal attribute information such as age, occupation, hobbies, etc. This allows the system to collect basic information about the user and sends this information to the server for use in the next step. The input data is text information such as age, occupation, hobbies, etc., and the server saves it as personal attribute information.

[1516] Step 2:

[1517] The user enters the question they want to ask into the input form on the device. At this time, the question is a specific text question, such as "What is your usual drink?" or "What is the most important thing for you in a cafe?" This is also sent to the server. The server saves this input data as the question.

[1518] Step 3:

[1519] The user inputs the number of questionnaires to be generated in a numerical format. For example, "50" or "100" is specified. This numerical data is also sent to the server, and the server saves it as the number of questionnaires to be generated.

[1520] Step 4:

[1521] The device's emotion recognition engine analyzes the user's facial expressions and voice to recognize their emotions in real time. Specifically, the device's camera and microphone are used to capture the user's facial expression data and voice data, which are then analyzed by an emotion recognition algorithm (e.g., the Hugging Face Transformers emotion analysis pipeline). The results of this analysis are sent to the server as emotion labels, such as relaxed, stressed, or excited. The server then stores this data as emotion data.

[1522] Step 5:

[1523] The server calls a generative AI model based on the received personal attribute information, question content, number of pages to be generated, and emotional data, and optimizes the question content based on the emotion. This process adjusts the tone (e.g., friendly, formal) and difficulty of the question depending on the emotional data. The generative AI model receives input data in text format and generates optimized question content.

[1524] Step 6:

[1525] The generative AI model automatically generates a specified number of questionnaires based on the optimized question content. These questionnaires reflect personal attribute information, question content, and emotional data, and the server generates them as a series of text-format questionnaires.

[1526] Step 7:

[1527] The generated questionnaire is output in a file format such as PDF or Excel and saved on the server. A notification is sent to the user's device so that the file can be downloaded. The user clicks the download link to obtain the generated questionnaire.

[1528] Through these steps, we have achieved a system that recognizes users' emotions and automatically generates an optimized questionnaire that reflects those emotions. This process makes it possible to collect questionnaire data that is easy to respond to and highly accurate.

[1529] 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.

[1530] 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.

[1531] 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 robot 414.

[1532] 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.

[1533] 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.

[1534] 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.

[1535] 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).

[1536] 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.

[1537] 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."

[1538] 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.

[1539] 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).

[1540] 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.

[1541] 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.

[1542] 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.

[1543] 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.

[1544] 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.

[1545] 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.

[1546] 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.

[1547] 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.

[1548] 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.

[1549] 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.

[1550] The following is further disclosed regarding the above embodiment.

[1551] (Claim 1)

[1552] a means for inputting specific persona information;

[1553] A means for inputting the content of a question;

[1554] a means for inputting the number of questionnaires to be generated;

[1555] A means for automatically generating a questionnaire using a generative AI model based on input information; and

[1556] means for outputting the generated questionnaire;

[1557] A system including:

[1558] (Claim 2)

[1559] The system according to claim 1, further comprising means for searching a database for a similar persona based on the input persona information and generating related questionnaire items.

[1560] (Claim 3)

[1561] 10. The system of claim 1, further comprising means for tailoring question content to relate to a persona.

[1562] "Example 1"

[1563] (Claim 1)

[1564] a means for inputting specific attribute information;

[1565] A means for inputting question content;

[1566] a means for inputting the number of surveys to be generated;

[1567] A means for automatically generating a questionnaire using a generative AI model based on input information; and

[1568] means for saving and outputting the generated questionnaire;

[1569] a means for making the generated survey available for download;

[1570] A system including:

[1571] (Claim 2)

[1572] 2. The system according to claim 1, further comprising means for searching a database for a similar person profile based on the attribute information acquired from the means for inputting specific attribute information, and generating related question items.

[1573] (Claim 3)

[1574] 2. The system according to claim 1, further comprising means for adjusting question content in association with specific attribute information.

[1575] "Application Example 1"

[1576] (Claim 1)

[1577] a means for inputting specific persona information;

[1578] A means for inputting the content of a question;

[1579] a means for inputting the number of questionnaires to be generated;

[1580] A means for automatically generating a questionnaire using a generative AI model based on input information; and

[1581] means for distributing the generated survey via the Internet;

[1582] A means for collecting and analyzing the results of the generated survey;

[1583] means for outputting the generated questionnaire;

[1584] A system including:

[1585] (Claim 2)

[1586] The system according to claim 1, further comprising means for searching a database for a similar persona based on the input persona information and generating related questionnaire items.

[1587] (Claim 3)

[1588] 10. The system of claim 1, further comprising means for tailoring question content to relate to a persona.

[1589] "Example 2: Combining Emotion Engines"

[1590] (Claim 1)

[1591] a means for inputting specific person information;

[1592] A means for inputting the content of a question;

[1593] a means to input the number of surveys to be generated;

[1594] means for automatically generating a survey using a generative artificial intelligence model based on input information;

[1595] a means for recognizing user sentiment and optimizing survey content accordingly;

[1596] means for outputting the generated survey;

[1597] A system including:

[1598] (Claim 2)

[1599] 2. The system according to claim 1, further comprising means for searching a database for a similar person profile based on the input person information and generating related survey items.

[1600] (Claim 3)

[1601] 10. The system of claim 1, further comprising means for adjusting question content in association with personal information.

[1602] "Application example 2 when combining emotion engines"

[1603] (Claim 1)

[1604] A means for inputting specific person attribute information;

[1605] A means for inputting the content of a question;

[1606] a means for inputting the number of questionnaires to be generated;

[1607] A means for recognizing emotions during input using an emotion recognition engine installed in the terminal;

[1608] a means for optimizing question content based on the recognized sentiment;

[1609] A means for automatically generating a questionnaire using a generative AI model based on input information;

[1610] a means for outputting the generated questionnaire;

[1611] A system including:

[1612] (Claim 2)

[1613] 2. The system according to claim 1, further comprising means for searching a database for a similar person profile based on the input person attribute information, and generating related question items.

[1614] (Claim 3)

[1615] 2. The system according to claim 1, further comprising means for adjusting the content of the question in association with the person attribute information and emotion data. [Explanation of symbols]

[1616] 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 inputting specific persona information; A means for inputting the content of a question; a means for inputting the number of questionnaires to be generated; A means for automatically generating a questionnaire using a generative AI model based on input information; and means for outputting the generated questionnaire; A system including:

2. The system according to claim 1, further comprising means for searching a database for a similar persona based on the input persona information and generating related questionnaire items.

3. The system of claim 1 , further comprising means for adjusting question content in relation to a persona.

Images