system

Abstract

We provide the system. [Solution] A means for automatically generating market research questions based on user-provided input information, A means to detect and optimize duplicate and redundant questions in the generated questions, A means of distributing questions to target respondents through multiple platforms, A means of analyzing and visualizing response data collected in real time, Based on the analysis results obtained, a means to propose solutions and support decision-making, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In market research, many companies lack the expertise and time to conduct effective questionnaire design. As a result, the questions may be redundant or important perspectives may be missing. Also, it is difficult to quickly and accurately analyze the response data and obtain insights for business use. These problems may cause delays in decision-making during the market research process.

Means for Solving the Problems

[0005] This invention provides a means for automatically generating and optimizing market research questionnaires. Based on user input, AI generates appropriate questions and eliminates duplication and redundancy. The generated questionnaires are distributed through various platforms, and response data is collected in real time. The obtained data is analyzed and visualized by AI to provide insights to the user. Furthermore, the system uses natural language processing to resolve disagreements and support rapid decision-making.

[0006] A "user" is an entity that utilizes a system for designing, distributing, and analyzing market research questionnaires, and typically refers to a company or marketing professional.

[0007] "Input information" refers to information that users provide to the system regarding the purpose and target audience of the market research, and forms the basis for the design of the questionnaire.

[0008] "Market research" refers to surveys conducted to understand consumer needs and market trends, and involves activities that collect opinions and data using questionnaires.

[0009] "Automatic question generation" is a process that uses AI technology to automatically create appropriate survey questions based on the user's specified objectives and conditions.

[0010] "Optimization" refers to improving the structure of questions and questionnaires to make them more effective and efficient for data collection.

[0011] "Detection of duplication and redundancy" is the process by which AI automatically identifies and eliminates elements with the same meaning or unnecessary expressions in the content of a question.

[0012] "Distribution" refers to the process of sending a created survey to the target audience via email, social media, or mobile apps.

[0013] "Response data" refers to the response information provided by the target audience to a survey, and is the subject of analysis.

[0014] "Real-time data collection" means that as soon as survey responses are received, they are immediately recorded in the database and processing begins without any waiting time.

[0015] "Analysis" is the process of analyzing collected data using AI technology and other methods to derive trends and patterns.

[0016] "Visualization" refers to displaying analyzed data in the form of graphs, charts, and other formats to make it easy for users to understand.

[0017] "Presenting solutions" means showing users options or recommended action plans based on the results of data analysis.

[0018] "Supporting decision-making" means providing users with the information and tools they need to make decisions about their business strategies and marketing policies.

[0019] "Natural language processing" is a technology that enables computers to understand and analyze human language, and is used to appropriately process question content and answers. [Brief explanation of the drawing]

[0020] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5]It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0021] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described according to the accompanying drawings.

[0022] First, the language used in the following description will be explained.

[0023] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0024] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0025] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0026] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0027] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0028] [First Embodiment]

[0029] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0030] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0031] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0032] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0033] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0034] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0035] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0036] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] As shown in Figure 2, in the data processing device 12, specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0038] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0039] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0040] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0041] This invention relates to a system characterized by the automated design, distribution, and analysis of market research questionnaires using AI technology. The system can be used by the user providing the server with the objectives and conditions of the market research.

[0042] The server uses AI algorithms to automatically generate market research questionnaire questions based on information entered by the user. The AI ​​references similar past surveys from an accessible database to select the most appropriate questions. This allows users to quickly obtain effective and comprehensive questionnaires.

[0043] After the survey is designed, the server detects duplicate and redundant questions and optimizes them using natural language processing techniques. This optimization improves the quality of the survey and reduces the burden on respondents. The finalized survey data is then sent to the terminal.

[0044] The device selects the appropriate distribution channel and sends the survey to the identified target audience. This process is automated and carried out efficiently using various methods such as email, social media, and apps. After the survey is distributed and responses are collected, the device sends the collected data to the server.

[0045] The server analyzes data in real time, using AI to identify trends and patterns. This allows users to instantly gain market insights. The analysis results are visualized as graphs and charts and provided to the user via their device.

[0046] As a concrete example, a user planning to launch a new product can use this system to design a survey targeting their desired customer base. After confirming that the questions automatically generated by the server align with the user's objectives, the survey is distributed. The collected responses are immediately analyzed by the server, providing the user with insights into the new product's market potential and areas for improvement. Based on these analysis results, the user can quickly and efficiently formulate a new product launch strategy.

[0047] Thus, the present invention helps users conduct advanced market research and make rapid business decisions without requiring them to possess special statistical knowledge or analytical skills.

[0048] The following describes the processing flow.

[0049] Step 1:

[0050] To initiate market research, users submit input information, such as the research objectives and target audience, to the server. Users provide this information through the system's interface.

[0051] Step 2:

[0052] The server uses an AI algorithm to automatically generate survey questions based on the user's input information. The AI ​​consults an internal database and designs the optimal questions, taking into account similar past surveys and current market trends.

[0053] Step 3:

[0054] The server uses natural language processing techniques to detect duplication and redundancy in the generated questions and makes corrections as needed, thereby improving the effectiveness of the survey.

[0055] Step 4:

[0056] The finalized questionnaire is sent to the device, which then distributes it to the target audience via the most appropriate channel. These channels include email, social media, and mobile apps.

[0057] Step 5:

[0058] After distribution, the device collects the received survey responses in real time and sends the data to the server. The data is transmitted using a secure protocol.

[0059] Step 6:

[0060] The server uses AI technology to analyze the collected response data and derive insights such as trends and anomalies. The analysis is processed quickly.

[0061] Step 7:

[0062] The server visualizes the analysis results and generates graphs and charts, allowing users to intuitively gain insights from the data.

[0063] Step 8:

[0064] Users view visualized analysis results through their devices and make decisions based on the insights gained. The server may also provide additional solutions or recommendations.

[0065] Step 9:

[0066] Users make decisions and, if necessary, adjust strategies based on research findings, thereby contributing to business activities.

[0067] (Example 1)

[0068] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0069] Traditionally, market research often involved manual processes such as question design, response collection, and data analysis. This not only resulted in time-consuming and costly work, but also led to inconsistencies in question quality and response analysis. Furthermore, redundant or redundant questions increased the burden on respondents and reduced the reliability of the data obtained. In addition, there was a need to efficiently analyze the obtained data and make rapid business decisions.

[0070] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0071] In this invention, the server includes means for automatically generating market research questions based on input information provided by the user, means for detecting and optimizing the duplicates and redundancies of the generated questions using natural language processing technology, and means for distributing the questions to target respondents through multiple communication means. This enables the automation of market research, allowing for rapid and effective market research and data analysis.

[0072] "User-provided input information" refers to information such as the purpose, conditions, and target audience that users input into the system for market research purposes.

[0073] "Methods for automatically generating questions" refers to a function that uses AI technology to automatically construct the most suitable questions for market research based on input information provided by the user.

[0074] "Methods for detecting and optimizing duplication and redundancy" refers to a function that uses natural language processing technology to identify redundant content and unnecessarily complex expressions within the generated questions, and then simplifies the content to make it clearer and more concise.

[0075] "Means of distributing questions to respondents through multiple communication methods" refers to a function that sends questions to respondents targeted for the survey using various communication methods such as email, social media, and mobile apps.

[0076] "Collected response information" refers to the survey data returned by respondents, which will be used for subsequent data analysis.

[0077] "Means of analysis and visualization" refers to a function that statistically analyzes collected response information using AI technology and visually displays the results in graphs, charts, etc.

[0078] "Means of proposing countermeasures and supporting decision-making" refers to a function that supports users' business decision-making by proposing market strategies and product improvements based on insights gained from analysis results.

[0079] "A means of selecting questions by referring to past survey data and improving the completeness of the survey" refers to a function that improves the quality of the survey by referring to data from similar surveys conducted in the past and selecting more comprehensive and useful questions based on that data.

[0080] This invention relates to market research using AI technology. First, the user provides the server with the purpose and conditions of the market research. Based on this information, the server automatically generates market research questionnaire questions using a generative AI model. The AI ​​refers to past research data and selects the most suitable questions, thereby quickly providing an effective questionnaire.

[0081] The designed survey questions are optimized on the server using natural language processing technology. This process removes redundancy and repetition from the questions, making them less burdensome and easier to understand for respondents. The optimized questions are sent to terminals and then distributed to the target respondents.

[0082] The device selects the most suitable distribution method depending on the target audience. Options include email, social media, and mobile apps. This distribution process is automated, allowing for efficient delivery of questionnaires to multiple target groups.

[0083] The collected response information is transmitted to the server in real time, where AI is used for data analysis. This analysis extracts and visualizes trends and patterns. As a result, users can gain insights into the market, which can be used to formulate business strategies and improve products.

[0084] As a concrete example, a user planning to launch a new service can use this system to distribute a survey to their target market. After confirming that the questions generated by the server align with the user's business objectives, the survey is distributed. The collected responses are immediately analyzed by the server, revealing market expectations and challenges for the new service. Based on this, the user can quickly and accurately formulate a strategy.

[0085] Example prompt: "Automatically generate a market research questionnaire regarding new service B and distribute it to the target audience."

[0086] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0087] Step 1:

[0088] The user inputs the objectives and conditions of the market research and sends them to the server. This input includes the target customer base, research objectives, and expected results. This allows the server to obtain the basic data needed to create a questionnaire that meets the user's requirements.

[0089] Step 2:

[0090] The server automatically generates questions from the input information received using a generative AI model. The AI ​​constructs optimal questions by referring to past survey data, detecting and optimizing for redundancy and duplication using natural language processing techniques. This process improves the quality of the questions and provides them to the user. The server then proceeds to the next process with the generated questions.

[0091] Step 3:

[0092] The server sends optimized questions to the device. The device evaluates the criteria for identifying target respondents and selects the appropriate delivery channel. Possible delivery channels include email, social media, and mobile apps, and the AI ​​recommends which method is best. The device then prepares to send the questions via the selected channel.

[0093] Step 4:

[0094] The device sends questions to the target audience using the selected distribution channel. The survey is efficiently delivered to each respondent at the most appropriate time and in the most suitable manner. After delivery, the device monitors the arrival of responses and appropriately collects the data.

[0095] Step 5:

[0096] The device sends the collected response data to the server. The server receives the data and analyzes it in real time using AI. In particular, it identifies trends and patterns and generates visualized results. This prepares the system to provide users with easily understandable insights.

[0097] Step 6:

[0098] The server visualizes the analysis results as graphs and charts and sends the data to the terminal. The user receives these results through the terminal and, if necessary, uses them as foundational data for further analysis or to formulate new strategies. This enables users to make quick decisions.

[0099] (Application Example 1)

[0100] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0101] Modern market research demands the rapid and accurate understanding of diverse consumer preferences and purchasing history. However, the process is complex, and traditional methods struggle to respond to real-time, ever-changing market needs. Furthermore, designing research projects requires advanced expertise, making it difficult to easily obtain market insights.

[0102] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0103] In this invention, the server includes the functions of creating market research questions based on user input information obtained through information provision media, identifying and optimizing the duplicates and redundancies of the created questions, and providing the questions to target respondents via various platforms. This enables the automatic generation of research designs that take into account consumers' purchase and browsing history information, allowing for rapid and effective market research.

[0104] "Information provision medium" refers to the technical means used to obtain input information from users, and includes the internet and mobile devices.

[0105] The "question generation function" is a technical means of automatically generating appropriate questions based on the objectives of market research.

[0106] The "duplicate and redundancy identification function" is a technology that detects duplicate content and unnecessary parts in the generated questions and optimizes them.

[0107] "Functions provided through diverse platforms" refers to means of presenting questions to respondents via multiple platforms such as email and social media.

[0108] "Purchase and browsing history information" refers to historical data on products that consumers have purchased and content they have viewed in the past, and is data that indicates the preferences of individual consumers.

[0109] "Automated survey generation" is a function that uses AI to generate market research that takes into account past consumer data, without human intervention.

[0110] To carry out the present invention, a system having the following configuration is used.

[0111] The system uses servers and terminals to automatically generate, optimize, and distribute market research questions. The server first obtains input information from users through information provision media. Based on this input information, it uses an AI algorithm to create appropriate questions and utilizes a generation AI model. The generated questions are optimized using natural language processing (NLP) techniques to identify duplication and redundancy. Python and Django are preferred software for this system.

[0112] Optimized questions are delivered to target respondents via various platforms such as email and social media. After delivery, the devices send the collected response data to the server in real time. The server analyzes and visualizes this data. Based on the analysis results, users can obtain recommended solutions that take into account their purchasing behavior and browsing history. The analysis results are displayed in graphs and charts and provided to users in real time.

[0113] As a concrete example, when a company launches a new product into the market, it uses this system to create questions for its target customer base. The questions generated through the AI ​​model are automatically sent via social media or email. The collected responses are immediately analyzed, allowing the company to quickly understand consumers' purchasing intent and evaluation of the new product.

[0114] Example of a prompt:

[0115] Customer segment: Women aged 20 to 30

[0116] Product Category: Casual Wear

[0117] Survey topic: Feedback on new products

[0118] Desired analysis content: Color acceptance, price tolerance

[0119] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0120] Step 1:

[0121] The server collects input information from users, such as the purpose and conditions of the market research, through information provision media. This is done using prompts from questionnaires filled out by the user. The entered information is stored in a database and used to generate questions in the next step.

[0122] Step 2:

[0123] The server uses a generative AI model to create market research questions based on stored input information. It determines the content of the questions by referring to past research data. The generated questions are temporarily stored in memory to check for compliance and duplicates.

[0124] Step 3:

[0125] The server performs natural language processing (NLP) to identify duplication and redundancy in the generated questions. This optimizes the questions, reducing the burden on respondents. The optimized questions are then saved to the database.

[0126] Step 4:

[0127] The device delivers optimized questions to target respondents through various platforms selected by the user (email, social networking services, etc.). Data is transmitted in real time and delivered in a format individually adapted to each platform.

[0128] Step 5:

[0129] The terminal collects response data from the subjects and sends it to the server. The collected data is formatted so that it arrives at the server in a format that allows for immediate analysis.

[0130] Step 6:

[0131] The server analyzes the collected response data and generates trends and insights in real time. This analysis uses data mining techniques and also takes into account the user's purchase and browsing history. The analysis results are displayed to the user in a visualized format.

[0132] Step 7:

[0133] Users receive analysis results and make decisions based on the visualized data. This allows users to quickly grasp market trends and make strategic adjustments regarding new products and services.

[0134] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0135] This invention is a market research questionnaire system that combines an emotion engine, and is characterized by designing an effective and appropriate questionnaire based on input information provided by the user, and performing analysis while taking the user's emotions into consideration.

[0136] First, when a user begins market research, they provide the server with the research objectives and target audience information. Based on this information, the server automatically generates questions using an AI algorithm. It forms the optimal set of questions by referring to past data.

[0137] After the survey is designed, the server uses natural language processing techniques to eliminate duplicate and redundant questions. Furthermore, it utilizes an emotion engine to dynamically adjust questions based on the user's emotional state. This process improves the targeting accuracy of the survey.

[0138] Once the design is complete, the questionnaire will be sent to the target audience via multiple distribution channels (email, social media, apps, etc.) through their devices. Simultaneously with distribution, the device will monitor the user's emotional changes using an emotion engine and adjust the content of the distribution as needed.

[0139] Once responses are collected, the device sends the data to the server. The server analyzes the response data in real time, gaining insights that include emotional changes captured by the emotion engine. This provides deeper, emotion-based insights that go beyond typical data analysis.

[0140] As a concrete example, when formulating a marketing strategy for a new product, users can use this system to conduct research that takes into account the emotional state of the target audience. A survey is conducted using questions generated by the server, and the collected emotional data becomes valuable information for predicting sales of the new product and inferring potential customer responses.

[0141] In this system, users can obtain sophisticated information that takes emotions into account, enabling them to efficiently optimize product development and marketing strategies. The data obtained by the emotion engine adds the necessary dimensions for business decision-making, supporting more competitive market strategies.

[0142] The following describes the processing flow.

[0143] Step 1:

[0144] The user initiates market research and provides input information, such as the research target and objectives, to the server. The user enters this information through a web interface or application.

[0145] Step 2:

[0146] The server uses AI algorithms to automatically generate survey questions based on information provided by the user. It selects the most relevant questions for the target audience, taking into account past similar surveys and current market trends.

[0147] Step 3:

[0148] The server optimizes the generated questions using natural language processing techniques. It improves the quality of the survey by detecting and removing or correcting duplicate or redundant expressions in the questions.

[0149] Step 4:

[0150] The server uses an emotion engine to adjust the content of questions to match the user's emotional state. This provides appropriate stimuli to the respondent's emotions, allowing for the collection of more accurate data.

[0151] Step 5:

[0152] The optimized survey is sent to the device, which then distributes it to the target audience. The distribution method can be email, social media, or app, selected according to the target audience.

[0153] Step 6:

[0154] The device uses an emotion engine during the broadcast to monitor changes in the respondents' emotions. If necessary, it dynamically adjusts the broadcast content and provides follow-up at the appropriate time.

[0155] Step 7:

[0156] Once survey responses are collected, the device sends the data to the server. Data transfer occurs in real time, enabling high-speed analysis.

[0157] Step 8:

[0158] The server analyzes the received response data using AI technology, combines it with emotional information obtained from the emotion engine, and gains comprehensive insights. It analyzes trends and the influence of emotions and presents them to the user visually.

[0159] Step 9:

[0160] Users review the analysis results through their devices and make decisions based on insights, including sentiment data. The server provides additional solutions and points of interest to support the user's decision-making.

[0161] (Example 2)

[0162] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0163] In market research, there are challenges in achieving accurate market analysis and making effective decisions due to insufficient optimization of research content, improvement of targeting accuracy, and real-time adjustments that take into account changes in user sentiment.

[0164] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0165] In this invention, the server includes means for dynamically adjusting tasks generated in accordance with the user's emotional state, means for monitoring emotional changes in real time and adjusting the content delivered as needed, and means for improving the quality of the research by referring to past research information. As a result, the user can make adjustments in real time that take emotional changes into account, enabling highly accurate market analysis and decision-making.

[0166] A "user" is an entity that uses the system to input information about the survey content and target individuals, and makes decisions based on the analysis results.

[0167] "Research" is the process of collecting and analyzing information based on a specific purpose.

[0168] A "task" is a set of questions or problems presented to the survey participants.

[0169] "Automatic generation" refers to the process of mechanically creating tasks using an AI model based on information provided by the user.

[0170] "Optimization" means eliminating duplication and redundancy in the generated tasks and making them the most suitable form for the purpose of the investigation.

[0171] "Communication methods" refer to media used to deliver information to survey participants, such as email, social networking services (SNS), and applications.

[0172] "Analysis" is the process of analyzing collected data and extracting information.

[0173] "Visualization" refers to representing analysis results in the form of graphs, charts, and other formats to make them easier to understand.

[0174] "Countermeasures" refer to action plans or solutions proposed based on the analysis results obtained.

[0175] "Emotional state" refers to the psychological and emotional responses that a user exhibits.

[0176] "Real-time" is a term that indicates that information is processed and analyzed immediately.

[0177] "Adjustment" refers to modifying content based on specific conditions of the user or target audience.

[0178] This invention relates to a specific embodiment of a market research questionnaire system that incorporates an emotion engine. This system consists of a user, a server, and a terminal.

[0179] The user first inputs information about the purpose and target audience of their market research. The server receives this information and automatically generates the most suitable challenges using a generative AI model. The AI ​​model refers to a database of past research information and performs keyword extraction and prompt generation to select the most effective challenges.

[0180] The generated tasks are processed using natural language processing technology on the server to remove duplication and redundancy. The server also uses an emotion engine to dynamically adjust the task content based on the user's emotional state. This improves the targeting accuracy of the survey.

[0181] Next, the completed questionnaire is sent to the survey participants via multiple communication methods such as email, social media, and applications through the device. The device monitors the recipient's emotional changes during delivery using an emotion engine and adjusts the delivery timing and message content in real time as needed.

[0182] Finally, the device collects the responses and sends them to the server. The server analyzes this data to gain insights, including changes in sentiment. The information obtained in this process is visualized to support the user's decision-making and presented as effective countermeasures.

[0183] As a concrete example, when evaluating the brand image of a new product, a survey can be conducted using the prompt, "What was your first impression when you saw this product for the first time?" In this way, users can obtain sophisticated information that reflects their emotional changes, which can contribute to the optimization of product development and marketing strategies.

[0184] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0185] Step 1:

[0186] The user inputs information into the server regarding the purpose and target audience for initiating the market research. Specifically, this includes research items, expected outcomes, and demographic information of the target audience. This information is used for initial processing of the AI ​​algorithm.

[0187] Step 2:

[0188] The server automatically generates research questions using a generative AI model based on the information it receives. It analyzes the input data, extracts highly relevant keywords by referring to past market databases, and constructs questions based on those keywords. The output is a set of questions tailored to the user's information.

[0189] Step 3:

[0190] The server uses natural language processing (NLP) to eliminate duplication and redundancy from the generated questions. It receives a set of generated questions as input, performs text analysis, and obtains an optimized list of questions as output.

[0191] Step 4:

[0192] The server uses an emotion engine to analyze the user's emotional state and dynamically adjusts the questions as needed. The input includes a list of optimized questions and the user's emotional state, and the output provides questions customized to match the emotion.

[0193] Step 5:

[0194] The device delivers customized questions to survey participants via communication methods such as email, social media, and apps. Input includes customized questions and distribution channel settings, while output is a questionnaire delivered to the survey participants.

[0195] Step 6:

[0196] The device monitors the recipient's emotional changes during delivery. It uses an emotion engine to analyze the received data and adjust the delivery timing and message content in real time as needed. The output is the adjusted delivery content.

[0197] Step 7:

[0198] The terminal collects responses from survey participants and sends them to the server. The server receives the collected data and performs analysis, including changes in sentiment. The output is a detailed analysis result for the user.

[0199] Step 8:

[0200] The server visualizes the obtained analysis results and presents them to support the user's decision-making. The input is detailed analysis results, and the output is provided to the user as visualized insights and suggestions.

[0201] (Application Example 2)

[0202] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0203] In today's advertising market, accurately capturing viewers' emotions and effectively optimizing advertising content is essential. However, traditional advertising systems struggle to detect viewers' emotions in real time and dynamically adjust advertisements accordingly. This results in limited advertising effectiveness to target audiences and makes it difficult to maximize the effectiveness of advertising strategies.

[0204] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0205] In this invention, the server includes means for automatically generating market research questions based on user-provided input information, means for detecting and optimizing duplicate or redundant generated questions, and means for detecting emotions and dynamically adjusting advertising content. This makes it possible to optimize advertisements according to the emotional state of the viewer.

[0206] A "user" is an entity that provides input information to the system and generates questions for market research.

[0207] "Input information" refers to information provided by the user regarding the purpose and target audience of the market research, and this information serves as the basic data from which questions are generated.

[0208] An "automatic question generation method" is a function that mechanically generates questions for market research based on input information provided by the user.

[0209] "Question optimization means" refers to a function that detects duplication and redundancy in generated questions and transforms them into an efficient and clear question structure.

[0210] "Means for detecting emotions and dynamically adjusting advertising content" refers to a function that senses the viewer's emotional state in real time and effectively changes the content of advertisements accordingly.

[0211] "Information and communication means" refers to communication functions for distributing questions to target respondents through multiple platforms.

[0212] "Methods for analyzing and visualizing response data" refers to a function that analyzes response data collected in real time and visually represents the results.

[0213] "Means for presenting problem-solving methods based on analysis results" refers to a function that, based on the obtained analysis results, proposes specific problem-solving solutions to support the user's decision-making.

[0214] The system implementing this invention is configured in which a server, a terminal, and a user cooperate to operate. The server first receives input information provided by the user and automatically generates questions for market research based on this information. The questions are generated using an AI algorithm, specifically a generative AI model, while referring to past data. The generated questions are optimized using natural language processing technology to detect redundancy and repetition.

[0215] Next, the device uses an emotion engine to detect the user's emotions in real time and dynamically adjusts the ad content based on this. After the ad is optimized, it is delivered to the target respondents across multiple platforms via information and communication means. The delivered ad and response data to the questions are sent to a server via the device and analyzed. At that time, the server also analyzes and visualizes the emotional information contained in the response data.

[0216] Based on the analysis results obtained, the server provides the user with specific suggestions for problem solving. These suggestions enable the user to make optimal decisions based on market research findings.

[0217] For example, if a user visits a shopping mall through smart glasses and shows interest in a particular product, the emotion engine will detect that interest and display relevant advertisements on the user's smartphone. By providing the right information at the right time in this way, a higher advertising effect can be expected.

[0218] An example of a prompt is: "Generate optimal ad content based on the user's current emotional state and suggest ads that support the user's decision-making." The ad content generated based on this prompt is adjusted according to the viewer's interests and emotions, more effectively meeting the viewer's needs.

[0219] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0220] Step 1:

[0221] The server receives input information from the user. This input information includes data about the purpose of the market research and the target audience. Based on the received information, the server builds the foundational data to generate the optimal set of questions.

[0222] Step 2:

[0223] The server utilizes a generative AI model to automatically generate market research questions from input information. It performs data calculations to design the most effective questions by comparing them with historical data, and outputs an optimized list of questions.

[0224] Step 3:

[0225] The server detects redundancy and duplication in the generated questions and optimizes them using natural language processing. Specifically, it removes unnecessary phrases and transforms them into concise and clear expressions. It then outputs the optimized set of questions.

[0226] Step 4:

[0227] The device uses an emotion engine to detect the user's emotions in real time. It takes data about the emotional state as input and generates optimal ad content according to the user's current state. It outputs how the emotional information influenced changes to the ad content.

[0228] Step 5:

[0229] The device delivers questions and advertisements optimized for the target respondents via information and communication means. Specifically, it sends data to email and social media platforms, reaching the target through various channels.

[0230] Step 6:

[0231] The terminal sends the response data collected from the target respondents and the sentiment information detected in real time to the server. Based on the input data, the server starts the analysis and outputs detailed insights that take sentiment into account.

[0232] Step 7:

[0233] The server proposes solutions to the user based on the analysis results. These proposals reflect market insights obtained by integrating collected data and sentiment information. Based on this, the user can make optimal decisions.

[0234] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0235] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0236] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0237] [Second Embodiment]

[0238] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0239] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0240] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0241] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0242] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0243] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0244] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0245] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0246] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0247] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0248] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0249] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0250] This invention relates to a system characterized by the automated design, distribution, and analysis of market research questionnaires using AI technology. The system can be used by the user providing the server with the objectives and conditions of the market research.

[0251] The server uses AI algorithms to automatically generate market research questionnaire questions based on information entered by the user. The AI ​​references similar past surveys from an accessible database to select the most appropriate questions. This allows users to quickly obtain effective and comprehensive questionnaires.

[0252] After the survey is designed, the server detects duplicate and redundant questions and optimizes them using natural language processing techniques. This optimization improves the quality of the survey and reduces the burden on respondents. The finalized survey data is then sent to the terminal.

[0253] The device selects the appropriate distribution channel and sends the survey to the identified target audience. This process is automated and carried out efficiently using various methods such as email, social media, and apps. After the survey is distributed and responses are collected, the device sends the collected data to the server.

[0254] The server analyzes data in real time, using AI to identify trends and patterns. This allows users to instantly gain market insights. The analysis results are visualized as graphs and charts and provided to the user via their device.

[0255] As a concrete example, a user planning to launch a new product can use this system to design a survey targeting their desired customer base. After confirming that the questions automatically generated by the server align with the user's objectives, the survey is distributed. The collected responses are immediately analyzed by the server, providing the user with insights into the new product's market potential and areas for improvement. Based on these analysis results, the user can quickly and efficiently formulate a new product launch strategy.

[0256] Thus, the present invention helps users conduct advanced market research and make rapid business decisions without requiring them to possess special statistical knowledge or analytical skills.

[0257] The following describes the processing flow.

[0258] Step 1:

[0259] To initiate market research, users submit input information, such as the research objectives and target audience, to the server. Users provide this information through the system's interface.

[0260] Step 2:

[0261] The server uses an AI algorithm to automatically generate survey questions based on the user's input information. The AI ​​consults an internal database and designs the optimal questions, taking into account similar past surveys and current market trends.

[0262] Step 3:

[0263] The server uses natural language processing techniques to detect duplication and redundancy in the generated questions and makes corrections as needed, thereby improving the effectiveness of the survey.

[0264] Step 4:

[0265] The finalized questionnaire is sent to the device, which then distributes it to the target audience via the most appropriate channel. These channels include email, social media, and mobile apps.

[0266] Step 5:

[0267] After distribution, the device collects the received survey responses in real time and sends the data to the server. The data is transmitted using a secure protocol.

[0268] Step 6:

[0269] The server uses AI technology to analyze the collected response data and derive insights such as trends and anomalies. The analysis is processed quickly.

[0270] Step 7:

[0271] The server visualizes the analysis results and generates graphs and charts, allowing users to intuitively gain insights from the data.

[0272] Step 8:

[0273] Users view visualized analysis results through their devices and make decisions based on the insights gained. The server may also provide additional solutions or recommendations.

[0274] Step 9:

[0275] Users make decisions and, if necessary, adjust strategies based on research findings, thereby contributing to business activities.

[0276] (Example 1)

[0277] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0278] Traditionally, market research often involved manual processes such as question design, response collection, and data analysis. This not only resulted in time-consuming and costly work, but also led to inconsistencies in question quality and response analysis. Furthermore, redundant or redundant questions increased the burden on respondents and reduced the reliability of the data obtained. In addition, there was a need to efficiently analyze the obtained data and make rapid business decisions.

[0279] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0280] In this invention, the server includes means for automatically generating questions for market research based on input information provided by the user, means for detecting and optimizing the duplication and redundancy of the generated questions using natural language processing technology, and means for distributing the questions to the target respondents through multiple communication means. Thereby, the automation of market research is realized, enabling rapid and effective market research and data analysis.

[0281] The "input information provided by the user" refers to information such as the purpose, conditions, and targets that the user inputs into the system for market research.

[0282] The "means for automatically generating questions" refers to the function of automatically constructing optimal questions in market research using AI technology based on the input information provided by the user.

[0283] The "means for detecting and optimizing duplication and redundancy" refers to the function of identifying duplicate content and unnecessarily complex expressions in the generated questions using natural language processing technology and making the content clear and concise.

[0284] The "means for distributing questions to respondents through multiple communication means" refers to the function of sending questions to the target respondents of the survey using various communication means such as email, SNS, and mobile apps.

[0285] The "collected response information" refers to the questionnaire data returned by the respondents and is used for subsequent data analysis.

[0286] The "means for analyzing and visualizing" refers to the function of statistically analyzing the collected response information using AI technology and visually displaying the results in graphs, charts, etc.

[0287] The "means for presenting countermeasures and supporting decision-making" refers to the function of proposing market strategies and product improvements based on the findings obtained from the analysis results and supporting the user's decision-making in business.

[0288] "A means of selecting questions by referring to past survey data and improving the completeness of the survey" refers to a function that improves the quality of the survey by referring to data from similar surveys conducted in the past and selecting more comprehensive and useful questions based on that data.

[0289] This invention relates to market research using AI technology. First, the user provides the server with the purpose and conditions of the market research. Based on this information, the server automatically generates market research questionnaire questions using a generative AI model. The AI ​​refers to past research data and selects the most suitable questions, thereby quickly providing an effective questionnaire.

[0290] The designed survey questions are optimized on the server using natural language processing technology. This process removes redundancy and repetition from the questions, making them less burdensome and easier to understand for respondents. The optimized questions are sent to terminals and then distributed to the target respondents.

[0291] The device selects the most suitable distribution method depending on the target audience. Options include email, social media, and mobile apps. This distribution process is automated, allowing for efficient delivery of questionnaires to multiple target groups.

[0292] The collected response information is transmitted to the server in real time, where AI is used for data analysis. This analysis extracts and visualizes trends and patterns. As a result, users can gain insights into the market, which can be used to formulate business strategies and improve products.

[0293] As a concrete example, a user planning to launch a new service can use this system to distribute a survey to their target market. After confirming that the questions generated by the server align with the user's business objectives, the survey is distributed. The collected responses are immediately analyzed by the server, revealing market expectations and challenges for the new service. Based on this, the user can quickly and accurately formulate a strategy.

[0294] Example prompt: "Automatically generate a market research questionnaire regarding new service B and distribute it to the target audience."

[0295] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0296] Step 1:

[0297] The user inputs the objectives and conditions of the market research and sends them to the server. This input includes the target customer base, research objectives, and expected results. This allows the server to obtain the basic data needed to create a questionnaire that meets the user's requirements.

[0298] Step 2:

[0299] The server automatically generates questions from the input information received using a generative AI model. The AI ​​constructs optimal questions by referring to past survey data, detecting and optimizing for redundancy and duplication using natural language processing techniques. This process improves the quality of the questions and provides them to the user. The server then proceeds to the next process with the generated questions.

[0300] Step 3:

[0301] The server sends optimized questions to the device. The device evaluates the criteria for identifying target respondents and selects the appropriate delivery channel. Possible delivery channels include email, social media, and mobile apps, and the AI ​​recommends which method is best. The device then prepares to send the questions via the selected channel.

[0302] Step 4:

[0303] The device sends questions to the target audience using the selected distribution channel. The survey is efficiently delivered to each respondent at the most appropriate time and in the most suitable manner. After delivery, the device monitors the arrival of responses and appropriately collects the data.

[0304] Step 5:

[0305] The terminal transmits the response data collected to the server. The server receives it and analyzes the response data in real time using AI. In particular, trends and patterns are identified and visualized results are generated. This prepares to provide user-friendly insights to the user.

[0306] Step 6:

[0307] The server visualizes the analysis results as graphs or charts and transmits the data to the terminal. The user receives this result through the terminal and, if necessary, conducts further analysis or uses it as a reference for formulating new strategies. This enables the user to make quick decisions.

[0308] (Application Example 1)

[0309] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0310] In modern market research, it is required to quickly and accurately grasp consumers' diverse preferences and purchase histories, but the process is complicated, and there is a problem that it is difficult to respond to changing market needs in real time with conventional methods. Also, when the user himself / herself conducts survey design, high-level expertise is required, and there is a problem that market insights cannot be easily obtained.

[0311] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0312] In this invention, the server includes the functions of creating market research questions based on user input information obtained through information provision media, identifying and optimizing the duplicates and redundancies of the created questions, and providing the questions to target respondents via various platforms. This enables the automatic generation of research designs that take into account consumers' purchase and browsing history information, allowing for rapid and effective market research.

[0313] "Information provision medium" refers to the technical means used to obtain input information from users, and includes the internet and mobile devices.

[0314] The "question generation function" is a technical means of automatically generating appropriate questions based on the objectives of market research.

[0315] The "duplicate and redundancy identification function" is a technology that detects duplicate content and unnecessary parts in the generated questions and optimizes them.

[0316] "Functions provided through diverse platforms" refers to means of presenting questions to respondents via multiple platforms such as email and social media.

[0317] "Purchase and browsing history information" refers to historical data on products that consumers have purchased and content they have viewed in the past, and is data that indicates the preferences of individual consumers.

[0318] "Automated survey generation" is a function that uses AI to generate market research that takes into account past consumer data, without human intervention.

[0319] To carry out the present invention, a system having the following configuration is used.

[0320] The system uses servers and terminals to automatically generate, optimize, and distribute market research questions. The server first obtains input information from users through information provision media. Based on this input information, it uses an AI algorithm to create appropriate questions and utilizes a generation AI model. The generated questions are optimized using natural language processing (NLP) techniques to identify duplication and redundancy. Python and Django are preferred software for this system.

[0321] Optimized questions are delivered to target respondents via various platforms such as email and social media. After delivery, the devices send the collected response data to the server in real time. The server analyzes and visualizes this data. Based on the analysis results, users can obtain recommended solutions that take into account their purchasing behavior and browsing history. The analysis results are displayed in graphs and charts and provided to users in real time.

[0322] As a concrete example, when a company launches a new product into the market, it uses this system to create questions for its target customer base. The questions generated through the AI ​​model are automatically sent via social media or email. The collected responses are immediately analyzed, allowing the company to quickly understand consumers' purchasing intent and evaluation of the new product.

[0323] Example of a prompt:

[0324] Customer segment: Women aged 20 to 30

[0325] Product Category: Casual Wear

[0326] Survey topic: Feedback on new products

[0327] Desired analysis content: Color acceptance, price tolerance

[0328] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0329] Step 1:

[0330] The server collects input information from users, such as the purpose and conditions of the market research, through information provision media. This is done using prompts from questionnaires filled out by the user. The entered information is stored in a database and used to generate questions in the next step.

[0331] Step 2:

[0332] The server uses a generative AI model to create market research questions based on stored input information. It determines the content of the questions by referring to past research data. The generated questions are temporarily stored in memory to check for compliance and duplicates.

[0333] Step 3:

[0334] The server performs natural language processing (NLP) to identify duplication and redundancy in the generated questions. This optimizes the questions, reducing the burden on respondents. The optimized questions are then saved to the database.

[0335] Step 4:

[0336] The device delivers optimized questions to target respondents through various platforms selected by the user (email, social networking services, etc.). Data is transmitted in real time and delivered in a format individually adapted to each platform.

[0337] Step 5:

[0338] The terminal collects response data from the subjects and sends it to the server. The collected data is formatted so that it arrives at the server in a format that allows for immediate analysis.

[0339] Step 6:

[0340] The server analyzes the collected response data and generates trends and insights in real time. This analysis uses data mining techniques and also takes into account the user's purchase and browsing history. The analysis results are displayed to the user in a visualized format.

[0341] Step 7:

[0342] Users receive analysis results and make decisions based on the visualized data. This allows users to quickly grasp market trends and make strategic adjustments regarding new products and services.

[0343] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0344] This invention is a market research questionnaire system that combines an emotion engine, and is characterized by designing an effective and appropriate questionnaire based on input information provided by the user, and performing analysis while taking the user's emotions into consideration.

[0345] First, when a user begins market research, they provide the server with information about the research objectives and target audience. Based on this information, the server automatically generates questions using an AI algorithm. It then forms an optimal set of questions by referring to past data.

[0346] After the survey is designed, the server uses natural language processing techniques to eliminate duplicate and redundant questions. Furthermore, it utilizes an emotion engine to dynamically adjust questions based on the user's emotional state. This process improves the targeting accuracy of the survey.

[0347] Once the design is complete, the questionnaire will be sent to the target audience via multiple distribution channels (email, social media, apps, etc.) through their devices. Simultaneously with distribution, the device will monitor the user's emotional changes using an emotion engine and adjust the content of the distribution as needed.

[0348] Once responses are collected, the device sends the data to the server. The server analyzes the response data in real time, gaining insights that include emotional changes captured by the emotion engine. This provides deeper, emotion-based insights that go beyond typical data analysis.

[0349] As a concrete example, when formulating a marketing strategy for a new product, users can use this system to conduct research that takes into account the emotional state of the target audience. A survey is conducted using questions generated by the server, and the collected emotional data becomes valuable information for predicting sales of the new product and inferring potential customer responses.

[0350] In this system, users can obtain sophisticated information that takes emotions into account, enabling them to efficiently optimize product development and marketing strategies. The data obtained by the emotion engine adds the necessary dimensions for business decision-making, supporting more competitive market strategies.

[0351] The following describes the processing flow.

[0352] Step 1:

[0353] The user initiates market research and provides input information, such as the research target and objectives, to the server. The user enters this information through a web interface or application.

[0354] Step 2:

[0355] The server uses AI algorithms to automatically generate survey questions based on information provided by the user. It selects the most relevant questions for the target audience, taking into account past similar surveys and current market trends.

[0356] Step 3:

[0357] The server optimizes the generated questions using natural language processing techniques. It improves the quality of the survey by detecting and removing or correcting duplicate or redundant expressions in the questions.

[0358] Step 4:

[0359] The server uses an emotion engine to adjust the content of questions to match the user's emotional state. This provides appropriate stimuli to the respondent's emotions, allowing for the collection of more accurate data.

[0360] Step 5:

[0361] The optimized survey is sent to the device, which then distributes it to the target audience. The distribution method can be email, social media, or app, selected according to the target audience.

[0362] Step 6:

[0363] The device uses an emotion engine during the broadcast to monitor changes in the respondents' emotions. If necessary, it dynamically adjusts the broadcast content and provides follow-up at the appropriate time.

[0364] Step 7:

[0365] Once survey responses are collected, the device sends the data to the server. Data transfer occurs in real time, enabling high-speed analysis.

[0366] Step 8:

[0367] The server analyzes the received response data using AI technology, combines it with emotional information obtained from the emotion engine, and gains comprehensive insights. It analyzes trends and the influence of emotions and presents them to the user visually.

[0368] Step 9:

[0369] Users review the analysis results through their devices and make decisions based on insights, including sentiment data. The server provides additional solutions and points of interest to support the user's decision-making.

[0370] (Example 2)

[0371] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0372] In market research, there are challenges in achieving accurate market analysis and making effective decisions due to insufficient optimization of research content, improvement of targeting accuracy, and real-time adjustments that take into account changes in user sentiment.

[0373] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0374] In this invention, the server includes means for dynamically adjusting tasks generated in accordance with the user's emotional state, means for monitoring emotional changes in real time and adjusting the content delivered as needed, and means for improving the quality of the research by referring to past research information. As a result, the user can make adjustments in real time that take emotional changes into account, enabling highly accurate market analysis and decision-making.

[0375] A "user" is an entity that uses the system to input information about the survey content and target individuals, and makes decisions based on the analysis results.

[0376] "Research" is the process of collecting and analyzing information based on a specific purpose.

[0377] A "task" is a set of questions or problems presented to the survey participants.

[0378] "Automatic generation" refers to the process of mechanically creating tasks using an AI model based on information provided by the user.

[0379] "Optimization" means eliminating duplication and redundancy in the generated tasks and making them the most suitable form for the purpose of the investigation.

[0380] "Communication methods" refer to media used to deliver information to survey participants, such as email, social networking services (SNS), and applications.

[0381] "Analysis" is the process of analyzing collected data and extracting information.

[0382] "Visualization" refers to representing analysis results in the form of graphs, charts, and other formats to make them easier to understand.

[0383] "Countermeasures" refer to action plans or solutions proposed based on the analysis results obtained.

[0384] "Emotional state" refers to the psychological and emotional responses that a user exhibits.

[0385] "Real-time" is a term that indicates that information is processed and analyzed immediately.

[0386] "Adjustment" refers to modifying content based on specific conditions of the user or target audience.

[0387] This invention relates to a specific embodiment of a market research questionnaire system that incorporates an emotion engine. This system consists of a user, a server, and a terminal.

[0388] The user first inputs information about the purpose and target audience of their market research. The server receives this information and automatically generates the most suitable challenges using a generative AI model. The AI ​​model refers to a database of past research information and performs keyword extraction and prompt generation to select the most effective challenges.

[0389] The generated tasks are processed using natural language processing technology on the server to remove duplication and redundancy. The server also uses an emotion engine to dynamically adjust the task content based on the user's emotional state. This improves the targeting accuracy of the survey.

[0390] Next, the completed questionnaire is sent to the survey participants via multiple communication methods such as email, social media, and applications through the device. The device monitors the recipient's emotional changes during delivery using an emotion engine and adjusts the delivery timing and message content in real time as needed.

[0391] Finally, the device collects the responses and sends them to the server. The server analyzes this data to gain insights, including changes in sentiment. The information obtained in this process is visualized to support the user's decision-making and presented as effective countermeasures.

[0392] As a concrete example, when evaluating the brand image of a new product, a survey can be conducted using the prompt, "What was your first impression when you saw this product for the first time?" In this way, users can obtain sophisticated information that reflects their emotional changes, which can contribute to the optimization of product development and marketing strategies.

[0393] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0394] Step 1:

[0395] The user inputs information into the server regarding the purpose and target audience for initiating the market research. Specifically, this includes research items, expected outcomes, and demographic information of the target audience. This information is used for initial processing of the AI ​​algorithm.

[0396] Step 2:

[0397] The server automatically generates research questions using a generative AI model based on the information it receives. It analyzes the input data, extracts highly relevant keywords by referring to past market databases, and constructs questions based on those keywords. The output is a set of questions tailored to the user's information.

[0398] Step 3:

[0399] The server uses natural language processing (NLP) to eliminate duplication and redundancy from the generated questions. It receives a set of generated questions as input, performs text analysis, and obtains an optimized list of questions as output.

[0400] Step 4:

[0401] The server uses an emotion engine to analyze the user's emotional state and dynamically adjusts the questions as needed. The input includes a list of optimized questions and the user's emotional state, and the output provides questions customized to match the emotion.

[0402] Step 5:

[0403] The device delivers customized questions to survey participants via communication methods such as email, social media, and apps. Input includes customized questions and distribution channel settings, while output is a questionnaire delivered to the survey participants.

[0404] Step 6:

[0405] The device monitors the recipient's emotional changes during delivery. It uses an emotion engine to analyze the received data and adjust the delivery timing and message content in real time as needed. The output is the adjusted delivery content.

[0406] Step 7:

[0407] The terminal collects responses from survey participants and sends them to the server. The server receives the collected data and performs analysis, including changes in sentiment. The output is a detailed analysis result for the user.

[0408] Step 8:

[0409] The server visualizes the obtained analysis results and presents them to support the user's decision-making. The input is detailed analysis results, and the output is provided to the user as visualized insights and suggestions.

[0410] (Application Example 2)

[0411] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0412] In today's advertising market, accurately capturing viewers' emotions and effectively optimizing advertising content is essential. However, traditional advertising systems struggle to detect viewers' emotions in real time and dynamically adjust advertisements accordingly. This results in limited advertising effectiveness to target audiences and makes it difficult to maximize the effectiveness of advertising strategies.

[0413] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0414] In this invention, the server includes means for automatically generating market research questions based on user-provided input information, means for detecting and optimizing duplicate or redundant generated questions, and means for detecting emotions and dynamically adjusting advertising content. This makes it possible to optimize advertisements according to the emotional state of the viewer.

[0415] A "user" is an entity that provides input information to the system and generates questions for market research.

[0416] "Input information" refers to information provided by the user regarding the purpose and target audience of the market research, and this information serves as the basic data from which questions are generated.

[0417] An "automatic question generation method" is a function that mechanically generates questions for market research based on input information provided by the user.

[0418] "Question optimization means" refers to a function that detects duplication and redundancy in generated questions and transforms them into an efficient and clear question structure.

[0419] "Means for detecting emotions and dynamically adjusting advertising content" refers to a function that senses the viewer's emotional state in real time and effectively changes the content of advertisements accordingly.

[0420] "Information and communication means" refers to communication functions for distributing questions to target respondents through multiple platforms.

[0421] "Methods for analyzing and visualizing response data" refers to a function that analyzes response data collected in real time and visually represents the results.

[0422] "Means for presenting problem-solving methods based on analysis results" refers to a function that, based on the obtained analysis results, proposes specific problem-solving solutions to support the user's decision-making.

[0423] The system implementing this invention is configured in which a server, a terminal, and a user cooperate to operate. The server first receives input information provided by the user and automatically generates questions for market research based on this information. The questions are generated using an AI algorithm, specifically a generative AI model, while referring to past data. The generated questions are optimized using natural language processing technology to detect redundancy and repetition.

[0424] Next, the device uses an emotion engine to detect the user's emotions in real time and dynamically adjusts the ad content based on this. After the ad is optimized, it is delivered to the target respondents across multiple platforms via information and communication means. The delivered ad and response data to the questions are sent to a server via the device and analyzed. At that time, the server also analyzes and visualizes the emotional information contained in the response data.

[0425] Based on the analysis results obtained, the server provides the user with specific suggestions for problem solving. These suggestions enable the user to make optimal decisions based on market research findings.

[0426] For example, if a user visits a shopping mall through smart glasses and shows interest in a particular product, the emotion engine will detect that interest and display relevant advertisements on the user's smartphone. By providing the right information at the right time in this way, a higher advertising effect can be expected.

[0427] An example of a prompt is: "Generate optimal ad content based on the user's current emotional state and suggest ads that support the user's decision-making." The ad content generated based on this prompt is adjusted according to the viewer's interests and emotions, more effectively meeting the viewer's needs.

[0428] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0429] Step 1:

[0430] The server receives input information from the user. This input information includes data about the purpose of the market research and the target audience. Based on the received information, the server builds the foundational data to generate the optimal set of questions.

[0431] Step 2:

[0432] The server utilizes a generative AI model to automatically generate market research questions from input information. It performs data calculations to design the most effective questions by comparing them with historical data, and outputs an optimized list of questions.

[0433] Step 3:

[0434] The server detects redundancy and duplication in the generated questions and optimizes them using natural language processing. Specifically, it removes unnecessary phrases and transforms them into concise and clear expressions. It then outputs the optimized set of questions.

[0435] Step 4:

[0436] The device uses an emotion engine to detect the user's emotions in real time. It takes data about the emotional state as input and generates optimal ad content according to the user's current state. It outputs how the emotional information influenced changes to the ad content.

[0437] Step 5:

[0438] The device delivers questions and advertisements optimized for the target respondents via information and communication means. Specifically, it sends data to email and social media platforms, reaching the target through various channels.

[0439] Step 6:

[0440] The terminal sends the response data collected from the target respondents and the sentiment information detected in real time to the server. Based on the input data, the server starts the analysis and outputs detailed insights that take sentiment into account.

[0441] Step 7:

[0442] The server proposes solutions to the user based on the analysis results. These proposals reflect market insights obtained by integrating collected data and sentiment information. Based on this, the user can make optimal decisions.

[0443] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0444] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0445] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0446] [Third Embodiment]

[0447] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0448] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0449] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0450] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0451] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0452] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0453] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0454] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0455] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0456] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0457] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0458] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0459] This invention relates to a system characterized by the automated design, distribution, and analysis of market research questionnaires using AI technology. The system can be used by the user providing the server with the objectives and conditions of the market research.

[0460] The server uses AI algorithms to automatically generate market research questionnaire questions based on information entered by the user. The AI ​​references similar past surveys from an accessible database to select the most appropriate questions. This allows users to quickly obtain effective and comprehensive questionnaires.

[0461] After the survey is designed, the server detects duplicate and redundant questions and optimizes them using natural language processing techniques. This optimization improves the quality of the survey and reduces the burden on respondents. The finalized survey data is then sent to the terminal.

[0462] The device selects the appropriate distribution channel and sends the survey to the identified target audience. This process is automated and carried out efficiently using various methods such as email, social media, and apps. After the survey is distributed and responses are collected, the device sends the collected data to the server.

[0463] The server analyzes data in real time, using AI to identify trends and patterns. This allows users to instantly gain market insights. The analysis results are visualized as graphs and charts and provided to the user via their device.

[0464] As a concrete example, a user planning to launch a new product can use this system to design a survey targeting their desired customer base. After confirming that the questions automatically generated by the server align with the user's objectives, the survey is distributed. The collected responses are immediately analyzed by the server, providing the user with insights into the new product's market potential and areas for improvement. Based on these analysis results, the user can quickly and efficiently formulate a new product launch strategy.

[0465] Thus, the present invention helps users conduct advanced market research and make rapid business decisions without requiring them to possess special statistical knowledge or analytical skills.

[0466] The following describes the processing flow.

[0467] Step 1:

[0468] To initiate market research, users submit input information, such as the research objectives and target audience, to the server. Users provide this information through the system's interface.

[0469] Step 2:

[0470] The server uses an AI algorithm to automatically generate survey questions based on the user's input information. The AI ​​consults an internal database and designs the optimal questions, taking into account similar past surveys and current market trends.

[0471] Step 3:

[0472] The server uses natural language processing techniques to detect duplication and redundancy in the generated questions and makes corrections as needed, thereby improving the effectiveness of the survey.

[0473] Step 4:

[0474] The finalized questionnaire is sent to the device, which then distributes it to the target audience via the most appropriate channel. These channels include email, social media, and mobile apps.

[0475] Step 5:

[0476] After distribution, the device collects the received survey responses in real time and sends the data to the server. The data is transmitted using a secure protocol.

[0477] Step 6:

[0478] The server uses AI technology to analyze the collected response data and derive insights such as trends and anomalies. The analysis is processed quickly.

[0479] Step 7:

[0480] The server visualizes the analysis results and generates graphs and charts, allowing users to intuitively gain insights from the data.

[0481] Step 8:

[0482] Users view visualized analysis results through their devices and make decisions based on the insights gained. The server may also provide additional solutions or recommendations.

[0483] Step 9:

[0484] Users make decisions and, if necessary, adjust strategies based on research findings, thereby contributing to business activities.

[0485] (Example 1)

[0486] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0487] Traditionally, market research often involved manual processes such as question design, response collection, and data analysis. This not only resulted in time-consuming and costly work, but also led to inconsistencies in question quality and response analysis. Furthermore, redundant or redundant questions increased the burden on respondents and reduced the reliability of the data obtained. In addition, there was a need to efficiently analyze the obtained data and make rapid business decisions.

[0488] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0489] In this invention, the server includes means for automatically generating market research questions based on input information provided by the user, means for detecting and optimizing the duplicates and redundancies of the generated questions using natural language processing technology, and means for distributing the questions to target respondents through multiple communication means. This enables the automation of market research, allowing for rapid and effective market research and data analysis.

[0490] "User-provided input information" refers to information such as the purpose, conditions, and target audience that users input into the system for market research purposes.

[0491] "Methods for automatically generating questions" refers to a function that uses AI technology to automatically construct the most suitable questions for market research based on input information provided by the user.

[0492] "Methods for detecting and optimizing duplication and redundancy" refers to a function that uses natural language processing technology to identify redundant content and unnecessarily complex expressions within the generated questions, and then simplifies the content to make it clearer and more concise.

[0493] "Means of distributing questions to respondents through multiple communication methods" refers to a function that sends questions to respondents targeted for the survey using various communication methods such as email, social media, and mobile apps.

[0494] "Collected response information" refers to the survey data returned by respondents, which will be used for subsequent data analysis.

[0495] "Means of analysis and visualization" refers to a function that statistically analyzes collected response information using AI technology and visually displays the results in graphs, charts, etc.

[0496] "Means of proposing countermeasures and supporting decision-making" refers to a function that supports users' business decision-making by proposing market strategies and product improvements based on insights gained from analysis results.

[0497] "A means of selecting questions by referring to past survey data and improving the completeness of the survey" refers to a function that improves the quality of the survey by referring to data from similar surveys conducted in the past and selecting more comprehensive and useful questions based on that data.

[0498] This invention relates to market research using AI technology. First, the user provides the server with the purpose and conditions of the market research. Based on this information, the server automatically generates market research questionnaire questions using a generative AI model. The AI ​​refers to past research data and selects the most suitable questions, thereby quickly providing an effective questionnaire.

[0499] The designed survey questions are optimized on the server using natural language processing technology. This process removes redundancy and repetition from the questions, making them less burdensome and easier to understand for respondents. The optimized questions are sent to terminals and then distributed to the target respondents.

[0500] The device selects the most suitable distribution method depending on the target audience. Options include email, social media, and mobile apps. This distribution process is automated, allowing for efficient delivery of questionnaires to multiple target groups.

[0501] The collected response information is transmitted to the server in real time, where AI is used for data analysis. This analysis extracts and visualizes trends and patterns. As a result, users can gain insights into the market, which can be used to formulate business strategies and improve products.

[0502] As a concrete example, a user planning to launch a new service can use this system to distribute a survey to their target market. After confirming that the questions generated by the server align with the user's business objectives, the survey is distributed. The collected responses are immediately analyzed by the server, revealing market expectations and challenges for the new service. Based on this, the user can quickly and accurately formulate a strategy.

[0503] Example prompt: "Automatically generate a market research questionnaire regarding new service B and distribute it to the target audience."

[0504] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0505] Step 1:

[0506] The user inputs the objectives and conditions of the market research and sends them to the server. This input includes the target customer base, research objectives, and expected results. This allows the server to obtain the basic data needed to create a questionnaire that meets the user's requirements.

[0507] Step 2:

[0508] The server automatically generates questions from the input information received using a generative AI model. The AI ​​constructs optimal questions by referring to past survey data, detecting and optimizing for redundancy and duplication using natural language processing techniques. This process improves the quality of the questions and provides them to the user. The server then proceeds to the next process with the generated questions.

[0509] Step 3:

[0510] The server sends optimized questions to the device. The device evaluates the criteria for identifying target respondents and selects the appropriate delivery channel. Possible delivery channels include email, social media, and mobile apps, and the AI ​​recommends which method is best. The device then prepares to send the questions via the selected channel.

[0511] Step 4:

[0512] The device sends questions to the target audience using the selected distribution channel. The survey is efficiently delivered to each respondent at the most appropriate time and in the most suitable manner. After delivery, the device monitors the arrival of responses and appropriately collects the data.

[0513] Step 5:

[0514] The device sends the collected response data to the server. The server receives the data and analyzes it in real time using AI. In particular, it identifies trends and patterns and generates visualized results. This prepares the system to provide users with easily understandable insights.

[0515] Step 6:

[0516] The server visualizes the analysis results as graphs and charts and sends the data to the terminal. The user receives these results through the terminal and, if necessary, uses them as foundational data for further analysis or to formulate new strategies. This enables users to make quick decisions.

[0517] (Application Example 1)

[0518] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0519] Modern market research demands the rapid and accurate understanding of diverse consumer preferences and purchasing history. However, the process is complex, and traditional methods struggle to respond to real-time, ever-changing market needs. Furthermore, designing research projects requires advanced expertise, making it difficult to easily obtain market insights.

[0520] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0521] In this invention, the server includes the functions of creating market research questions based on user input information obtained through information provision media, identifying and optimizing the duplicates and redundancies of the created questions, and providing the questions to target respondents via various platforms. This enables the automatic generation of research designs that take into account consumers' purchase and browsing history information, allowing for rapid and effective market research.

[0522] "Information provision medium" refers to the technical means used to obtain input information from users, and includes the internet and mobile devices.

[0523] The "question generation function" is a technical means of automatically generating appropriate questions based on the objectives of market research.

[0524] The "duplicate and redundancy identification function" is a technology that detects duplicate content and unnecessary parts in the generated questions and optimizes them.

[0525] "Functions provided through diverse platforms" refers to means of presenting questions to respondents via multiple platforms such as email and social media.

[0526] "Purchase and browsing history information" refers to historical data on products that consumers have purchased and content they have viewed in the past, and is data that indicates the preferences of individual consumers.

[0527] "Automated survey generation" is a function that uses AI to generate market research that takes into account past consumer data, without human intervention.

[0528] To carry out the present invention, a system having the following configuration is used.

[0529] The system uses servers and terminals to automatically generate, optimize, and distribute market research questions. The server first obtains input information from users through information provision media. Based on this input information, it uses an AI algorithm to create appropriate questions and utilizes a generation AI model. The generated questions are optimized using natural language processing (NLP) techniques to identify duplication and redundancy. Python and Django are preferred software for this system.

[0530] Optimized questions are delivered to target respondents via various platforms such as email and social media. After delivery, the devices send the collected response data to the server in real time. The server analyzes and visualizes this data. Based on the analysis results, users can obtain recommended solutions that take into account their purchasing behavior and browsing history. The analysis results are displayed in graphs and charts and provided to users in real time.

[0531] As a concrete example, when a company launches a new product into the market, it uses this system to create questions for its target customer base. The questions generated through the AI ​​model are automatically sent via social media or email. The collected responses are immediately analyzed, allowing the company to quickly understand consumers' purchasing intent and evaluation of the new product.

[0532] Example of a prompt:

[0533] Customer segment: Women aged 20 to 30

[0534] Product Category: Casual Wear

[0535] Survey topic: Feedback on new products

[0536] Desired analysis content: Color acceptance, price tolerance

[0537] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0538] Step 1:

[0539] The server collects input information from users, such as the purpose and conditions of the market research, through information provision media. This is done using prompts from questionnaires filled out by the user. The entered information is stored in a database and used to generate questions in the next step.

[0540] Step 2:

[0541] The server uses a generative AI model to create market research questions based on stored input information. It determines the content of the questions by referring to past research data. The generated questions are temporarily stored in memory to check for compliance and duplicates.

[0542] Step 3:

[0543] The server performs natural language processing (NLP) to identify duplication and redundancy in the generated questions. This optimizes the questions, reducing the burden on respondents. The optimized questions are then saved to the database.

[0544] Step 4:

[0545] The device delivers optimized questions to target respondents through various platforms selected by the user (email, social networking services, etc.). Data is transmitted in real time and delivered in a format individually adapted to each platform.

[0546] Step 5:

[0547] The terminal collects response data from the subjects and sends it to the server. The collected data is formatted so that it arrives at the server in a format that allows for immediate analysis.

[0548] Step 6:

[0549] The server analyzes the collected response data and generates trends and insights in real time. This analysis uses data mining techniques and also takes into account the user's purchase and browsing history. The analysis results are displayed to the user in a visualized format.

[0550] Step 7:

[0551] Users receive analysis results and make decisions based on the visualized data. This allows users to quickly grasp market trends and make strategic adjustments regarding new products and services.

[0552] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0553] This invention is a market research questionnaire system that combines an emotion engine, and is characterized by designing an effective and appropriate questionnaire based on input information provided by the user, and performing analysis while taking the user's emotions into consideration.

[0554] First, when a user begins market research, they provide the server with the research objectives and target audience information. Based on this information, the server automatically generates questions using an AI algorithm. It forms the optimal set of questions by referring to past data.

[0555] After the survey is designed, the server uses natural language processing techniques to eliminate duplicate and redundant questions. Furthermore, it utilizes an emotion engine to dynamically adjust questions based on the user's emotional state. This process improves the targeting accuracy of the survey.

[0556] Once the design is complete, the questionnaire will be sent to the target audience via multiple distribution channels (email, social media, apps, etc.) through their devices. Simultaneously with distribution, the device will monitor the user's emotional changes using an emotion engine and adjust the content of the distribution as needed.

[0557] Once responses are collected, the device sends the data to the server. The server analyzes the response data in real time, gaining insights that include emotional changes captured by the emotion engine. This provides deeper, emotion-based insights that go beyond typical data analysis.

[0558] As a concrete example, when formulating a marketing strategy for a new product, users can use this system to conduct research that takes into account the emotional state of the target audience. A survey is conducted using questions generated by the server, and the collected emotional data becomes valuable information for predicting sales of the new product and inferring potential customer responses.

[0559] In this system, users can obtain sophisticated information that takes emotions into account, enabling them to efficiently optimize product development and marketing strategies. The data obtained by the emotion engine adds the necessary dimensions for business decision-making, supporting more competitive market strategies.

[0560] The following describes the processing flow.

[0561] Step 1:

[0562] The user initiates market research and provides input information, such as the research target and objectives, to the server. The user enters this information through a web interface or application.

[0563] Step 2:

[0564] The server uses AI algorithms to automatically generate survey questions based on information provided by the user. It selects the most relevant questions for the target audience, taking into account past similar surveys and current market trends.

[0565] Step 3:

[0566] The server optimizes the generated questions using natural language processing techniques. It improves the quality of the survey by detecting and removing or correcting duplicate or redundant expressions in the questions.

[0567] Step 4:

[0568] The server uses an emotion engine to adjust the content of questions to match the user's emotional state. This provides appropriate stimuli to the respondent's emotions, allowing for the collection of more accurate data.

[0569] Step 5:

[0570] The optimized survey is sent to the device, which then distributes it to the target audience. The distribution method can be email, social media, or app, selected according to the target audience.

[0571] Step 6:

[0572] The device uses an emotion engine during the broadcast to monitor changes in the respondents' emotions. If necessary, it dynamically adjusts the broadcast content and provides follow-up at the appropriate time.

[0573] Step 7:

[0574] Once survey responses are collected, the device sends the data to the server. Data transfer occurs in real time, enabling high-speed analysis.

[0575] Step 8:

[0576] The server analyzes the received response data using AI technology, combines it with emotional information obtained from the emotion engine, and gains comprehensive insights. It analyzes trends and the influence of emotions and presents them to the user visually.

[0577] Step 9:

[0578] Users review the analysis results through their devices and make decisions based on insights, including sentiment data. The server provides additional solutions and points of interest to support the user's decision-making.

[0579] (Example 2)

[0580] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0581] In market research, there are challenges in achieving accurate market analysis and making effective decisions due to insufficient optimization of research content, improvement of targeting accuracy, and real-time adjustments that take into account changes in user sentiment.

[0582] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0583] In this invention, the server includes means for dynamically adjusting tasks generated in accordance with the user's emotional state, means for monitoring emotional changes in real time and adjusting the content delivered as needed, and means for improving the quality of the research by referring to past research information. As a result, the user can make adjustments in real time that take emotional changes into account, enabling highly accurate market analysis and decision-making.

[0584] A "user" is an entity that uses the system to input information about the survey content and target individuals, and makes decisions based on the analysis results.

[0585] "Research" is the process of collecting and analyzing information based on a specific purpose.

[0586] A "task" is a set of questions or problems presented to the survey participants.

[0587] "Automatic generation" refers to the process of mechanically creating tasks using an AI model based on information provided by the user.

[0588] "Optimization" means eliminating duplication and redundancy in the generated tasks and making them the most suitable form for the purpose of the investigation.

[0589] "Communication methods" refer to media used to deliver information to survey participants, such as email, social networking services (SNS), and applications.

[0590] "Analysis" is the process of analyzing collected data and extracting information.

[0591] "Visualization" refers to representing analysis results in the form of graphs, charts, and other formats to make them easier to understand.

[0592] "Countermeasures" refer to action plans or solutions proposed based on the analysis results obtained.

[0593] "Emotional state" refers to the psychological and emotional responses that a user exhibits.

[0594] "Real-time" is a term that indicates that information is processed and analyzed immediately.

[0595] "Adjustment" refers to modifying content based on specific conditions of the user or target audience.

[0596] This invention relates to a specific embodiment of a market research questionnaire system that incorporates an emotion engine. This system consists of a user, a server, and a terminal.

[0597] The user first inputs information about the purpose and target audience of their market research. The server receives this information and automatically generates the most suitable challenges using a generative AI model. The AI ​​model refers to a database of past research information and performs keyword extraction and prompt generation to select the most effective challenges.

[0598] The generated tasks are processed using natural language processing technology on the server to remove duplication and redundancy. The server also uses an emotion engine to dynamically adjust the task content based on the user's emotional state. This improves the targeting accuracy of the survey.

[0599] Next, the completed questionnaire is sent to the survey participants via multiple communication methods such as email, social media, and applications through the device. The device monitors the recipient's emotional changes during delivery using an emotion engine and adjusts the delivery timing and message content in real time as needed.

[0600] Finally, the device collects the responses and sends them to the server. The server analyzes this data to gain insights, including changes in sentiment. The information obtained in this process is visualized to support the user's decision-making and presented as effective countermeasures.

[0601] As a concrete example, when evaluating the brand image of a new product, a survey can be conducted using the prompt, "What was your first impression when you saw this product for the first time?" In this way, users can obtain sophisticated information that reflects their emotional changes, which can contribute to the optimization of product development and marketing strategies.

[0602] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0603] Step 1:

[0604] The user inputs information into the server regarding the purpose and target audience for initiating the market research. Specifically, this includes research items, expected outcomes, and demographic information of the target audience. This information is used for initial processing of the AI ​​algorithm.

[0605] Step 2:

[0606] The server automatically generates research questions using a generative AI model based on the information it receives. It analyzes the input data, extracts highly relevant keywords by referring to past market databases, and constructs questions based on those keywords. The output is a set of questions tailored to the user's information.

[0607] Step 3:

[0608] The server uses natural language processing (NLP) to eliminate duplication and redundancy from the generated questions. It receives a set of generated questions as input, performs text analysis, and obtains an optimized list of questions as output.

[0609] Step 4:

[0610] The server uses an emotion engine to analyze the user's emotional state and dynamically adjusts the questions as needed. The input includes a list of optimized questions and the user's emotional state, and the output provides questions customized to match the emotion.

[0611] Step 5:

[0612] The device delivers customized questions to survey participants via communication methods such as email, social media, and apps. Input includes customized questions and distribution channel settings, while output is a questionnaire delivered to the survey participants.

[0613] Step 6:

[0614] The device monitors the recipient's emotional changes during delivery. It uses an emotion engine to analyze the received data and adjust the delivery timing and message content in real time as needed. The output is the adjusted delivery content.

[0615] Step 7:

[0616] The terminal collects responses from survey participants and sends them to the server. The server receives the collected data and performs analysis, including changes in sentiment. The output is a detailed analysis result for the user.

[0617] Step 8:

[0618] The server visualizes the obtained analysis results and presents them to support the user's decision-making. The input is detailed analysis results, and the output is provided to the user as visualized insights and suggestions.

[0619] (Application Example 2)

[0620] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0621] In today's advertising market, accurately capturing viewers' emotions and effectively optimizing advertising content is essential. However, traditional advertising systems struggle to detect viewers' emotions in real time and dynamically adjust advertisements accordingly. This results in limited advertising effectiveness to target audiences and makes it difficult to maximize the effectiveness of advertising strategies.

[0622] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0623] In this invention, the server includes means for automatically generating market research questions based on user-provided input information, means for detecting and optimizing duplicate or redundant generated questions, and means for detecting emotions and dynamically adjusting advertising content. This makes it possible to optimize advertisements according to the emotional state of the viewer.

[0624] A "user" is an entity that provides input information to the system and generates questions for market research.

[0625] "Input information" refers to information provided by the user regarding the purpose and target audience of the market research, and this information serves as the basic data from which questions are generated.

[0626] An "automatic question generation method" is a function that mechanically generates questions for market research based on input information provided by the user.

[0627] "Question optimization means" refers to a function that detects duplication and redundancy in generated questions and transforms them into an efficient and clear question structure.

[0628] "Means for detecting emotions and dynamically adjusting advertising content" refers to a function that senses the viewer's emotional state in real time and effectively changes the content of advertisements accordingly.

[0629] "Information and communication means" refers to communication functions for distributing questions to target respondents through multiple platforms.

[0630] "Methods for analyzing and visualizing response data" refers to a function that analyzes response data collected in real time and visually represents the results.

[0631] "Means for presenting problem-solving methods based on analysis results" refers to a function that, based on the obtained analysis results, proposes specific problem-solving solutions to support the user's decision-making.

[0632] The system implementing this invention is configured in which a server, a terminal, and a user cooperate to operate. The server first receives input information provided by the user and automatically generates questions for market research based on this information. The questions are generated using an AI algorithm, specifically a generative AI model, while referring to past data. The generated questions are optimized using natural language processing technology to detect redundancy and repetition.

[0633] Next, the device uses an emotion engine to detect the user's emotions in real time and dynamically adjusts the ad content based on this. After the ad is optimized, it is delivered to the target respondents across multiple platforms via information and communication means. The delivered ad and response data to the questions are sent to a server via the device and analyzed. At that time, the server also analyzes and visualizes the emotional information contained in the response data.

[0634] Based on the analysis results obtained, the server provides the user with specific suggestions for problem solving. These suggestions enable the user to make optimal decisions based on market research findings.

[0635] For example, if a user visits a shopping mall through smart glasses and shows interest in a particular product, the emotion engine will detect that interest and display relevant advertisements on the user's smartphone. By providing the right information at the right time in this way, a higher advertising effect can be expected.

[0636] An example of a prompt is: "Generate optimal ad content based on the user's current emotional state and suggest ads that support the user's decision-making." The ad content generated based on this prompt is adjusted according to the viewer's interests and emotions, more effectively meeting the viewer's needs.

[0637] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0638] Step 1:

[0639] The server receives input information from the user. This input information includes data about the purpose of the market research and the target audience. Based on the received information, the server builds the foundational data to generate the optimal set of questions.

[0640] Step 2:

[0641] The server utilizes a generative AI model to automatically generate market research questions from input information. It performs data calculations to design the most effective questions by comparing them with historical data, and outputs an optimized list of questions.

[0642] Step 3:

[0643] The server detects redundancy and duplication in the generated questions and optimizes them using natural language processing. Specifically, it removes unnecessary phrases and transforms them into concise and clear expressions. It then outputs the optimized set of questions.

[0644] Step 4:

[0645] The device uses an emotion engine to detect the user's emotions in real time. It takes data about the emotional state as input and generates optimal ad content according to the user's current state. It outputs how the emotional information influenced changes to the ad content.

[0646] Step 5:

[0647] The device delivers questions and advertisements optimized for the target respondents via information and communication means. Specifically, it sends data to email and social media platforms, reaching the target through various channels.

[0648] Step 6:

[0649] The terminal sends the response data collected from the target respondents and the sentiment information detected in real time to the server. Based on the input data, the server starts the analysis and outputs detailed insights that take sentiment into account.

[0650] Step 7:

[0651] The server proposes solutions to the user based on the analysis results. These proposals reflect market insights obtained by integrating collected data and sentiment information. Based on this, the user can make optimal decisions.

[0652] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0653] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0654] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0655] [Fourth Embodiment]

[0656] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0657] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0658] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0659] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0660] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0661] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0662] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0663] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0664] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0665] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0666] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0667] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0668] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0669] This invention relates to a system characterized by the automated design, distribution, and analysis of market research questionnaires using AI technology. The system can be used by the user providing the server with the objectives and conditions of the market research.

[0670] The server uses AI algorithms to automatically generate market research questionnaire questions based on information entered by the user. The AI ​​references similar past surveys from an accessible database to select the most appropriate questions. This allows users to quickly obtain effective and comprehensive questionnaires.

[0671] After the survey is designed, the server detects duplicate and redundant questions and optimizes them using natural language processing techniques. This optimization improves the quality of the survey and reduces the burden on respondents. The finalized survey data is then sent to the terminal.

[0672] The device selects the appropriate distribution channel and sends the survey to the identified target audience. This process is automated and carried out efficiently using various methods such as email, social media, and apps. After the survey is distributed and responses are collected, the device sends the collected data to the server.

[0673] The server analyzes data in real time, using AI to identify trends and patterns. This allows users to instantly gain market insights. The analysis results are visualized as graphs and charts and provided to the user via their device.

[0674] As a concrete example, a user planning to launch a new product can use this system to design a survey targeting their desired customer base. After confirming that the questions automatically generated by the server align with the user's objectives, the survey is distributed. The collected responses are immediately analyzed by the server, providing the user with insights into the new product's market potential and areas for improvement. Based on these analysis results, the user can quickly and efficiently formulate a new product launch strategy.

[0675] Thus, the present invention helps users conduct advanced market research and make rapid business decisions without requiring them to possess special statistical knowledge or analytical skills.

[0676] The following describes the processing flow.

[0677] Step 1:

[0678] To initiate market research, users submit input information, such as the research objectives and target audience, to the server. Users provide this information through the system's interface.

[0679] Step 2:

[0680] The server uses an AI algorithm to automatically generate survey questions based on the user's input information. The AI ​​consults an internal database and designs the optimal questions, taking into account similar past surveys and current market trends.

[0681] Step 3:

[0682] The server uses natural language processing techniques to detect duplication and redundancy in the generated questions and makes corrections as needed, thereby improving the effectiveness of the survey.

[0683] Step 4:

[0684] The finalized questionnaire is sent to the device, which then distributes it to the target audience via the most appropriate channel. These channels include email, social media, and mobile apps.

[0685] Step 5:

[0686] After distribution, the device collects the received survey responses in real time and sends the data to the server. The data is transmitted using a secure protocol.

[0687] Step 6:

[0688] The server uses AI technology to analyze the collected response data and derive insights such as trends and anomalies. The analysis is processed quickly.

[0689] Step 7:

[0690] The server visualizes the analysis results and generates graphs and charts, allowing users to intuitively gain insights from the data.

[0691] Step 8:

[0692] Users view visualized analysis results through their devices and make decisions based on the insights gained. The server may also provide additional solutions or recommendations.

[0693] Step 9:

[0694] Users make decisions and, if necessary, adjust strategies based on research findings, thereby contributing to business activities.

[0695] (Example 1)

[0696] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0697] Traditionally, market research often involved manual processes such as question design, response collection, and data analysis. This not only resulted in time-consuming and costly work, but also led to inconsistencies in question quality and response analysis. Furthermore, redundant or redundant questions increased the burden on respondents and reduced the reliability of the data obtained. In addition, there was a need to efficiently analyze the obtained data and make rapid business decisions.

[0698] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0699] In this invention, the server includes means for automatically generating market research questions based on input information provided by the user, means for detecting and optimizing the duplicates and redundancies of the generated questions using natural language processing technology, and means for distributing the questions to target respondents through multiple communication means. This enables the automation of market research, allowing for rapid and effective market research and data analysis.

[0700] "User-provided input information" refers to information such as the purpose, conditions, and target audience that users input into the system for market research purposes.

[0701] "Methods for automatically generating questions" refers to a function that uses AI technology to automatically construct the most suitable questions for market research based on input information provided by the user.

[0702] "Methods for detecting and optimizing duplication and redundancy" refers to a function that uses natural language processing technology to identify redundant content and unnecessarily complex expressions within the generated questions, and then simplifies the content to make it clearer and more concise.

[0703] "Means of distributing questions to respondents through multiple communication methods" refers to a function that sends questions to respondents targeted for the survey using various communication methods such as email, social media, and mobile apps.

[0704] "Collected response information" refers to the survey data returned by respondents, which will be used for subsequent data analysis.

[0705] "Means of analysis and visualization" refers to a function that statistically analyzes collected response information using AI technology and visually displays the results in graphs, charts, etc.

[0706] "Means of proposing countermeasures and supporting decision-making" refers to a function that supports users' business decision-making by proposing market strategies and product improvements based on insights gained from analysis results.

[0707] "A means of selecting questions by referring to past survey data and improving the completeness of the survey" refers to a function that improves the quality of the survey by referring to data from similar surveys conducted in the past and selecting more comprehensive and useful questions based on that data.

[0708] This invention relates to market research using AI technology. First, the user provides the server with the purpose and conditions of the market research. Based on this information, the server automatically generates market research questionnaire questions using a generative AI model. The AI ​​refers to past research data and selects the most suitable questions, thereby quickly providing an effective questionnaire.

[0709] The designed survey questions are optimized on the server using natural language processing technology. This process removes redundancy and repetition from the questions, making them less burdensome and easier to understand for respondents. The optimized questions are sent to terminals and then distributed to the target respondents.

[0710] The device selects the most suitable distribution method depending on the target audience. Options include email, social media, and mobile apps. This distribution process is automated, allowing for efficient delivery of questionnaires to multiple target groups.

[0711] The collected response information is transmitted to the server in real time, where AI is used for data analysis. This analysis extracts and visualizes trends and patterns. As a result, users can gain insights into the market, which can be used to formulate business strategies and improve products.

[0712] As a concrete example, a user planning to launch a new service can use this system to distribute a survey to their target market. After confirming that the questions generated by the server align with the user's business objectives, the survey is distributed. The collected responses are immediately analyzed by the server, revealing market expectations and challenges for the new service. Based on this, the user can quickly and accurately formulate a strategy.

[0713] Example prompt: "Automatically generate a market research questionnaire regarding new service B and distribute it to the target audience."

[0714] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0715] Step 1:

[0716] The user inputs the objectives and conditions of the market research and sends them to the server. This input includes the target customer base, research objectives, and expected results. This allows the server to obtain the basic data needed to create a questionnaire that meets the user's requirements.

[0717] Step 2:

[0718] The server automatically generates questions from the input information received using a generative AI model. The AI ​​constructs optimal questions by referring to past survey data, detecting and optimizing for redundancy and duplication using natural language processing techniques. This process improves the quality of the questions and provides them to the user. The server then proceeds to the next process with the generated questions.

[0719] Step 3:

[0720] The server sends optimized questions to the device. The device evaluates the criteria for identifying target respondents and selects the appropriate delivery channel. Possible delivery channels include email, social media, and mobile apps, and the AI ​​recommends which method is best. The device then prepares to send the questions via the selected channel.

[0721] Step 4:

[0722] The device sends questions to the target audience using the selected distribution channel. The survey is efficiently delivered to each respondent at the most appropriate time and in the most suitable manner. After delivery, the device monitors the arrival of responses and appropriately collects the data.

[0723] Step 5:

[0724] The device sends the collected response data to the server. The server receives the data and analyzes it in real time using AI. In particular, it identifies trends and patterns and generates visualized results. This prepares the system to provide users with easily understandable insights.

[0725] Step 6:

[0726] The server visualizes the analysis results as graphs and charts and sends the data to the terminal. The user receives these results through the terminal and, if necessary, uses them as foundational data for further analysis or to formulate new strategies. This enables users to make quick decisions.

[0727] (Application Example 1)

[0728] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0729] Modern market research demands the rapid and accurate understanding of diverse consumer preferences and purchasing history. However, the process is complex, and traditional methods struggle to respond to real-time, ever-changing market needs. Furthermore, designing research projects requires advanced expertise, making it difficult to easily obtain market insights.

[0730] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0731] In this invention, the server includes the functions of creating market research questions based on user input information obtained through information provision media, identifying and optimizing the duplicates and redundancies of the created questions, and providing the questions to target respondents via various platforms. This enables the automatic generation of research designs that take into account consumers' purchase and browsing history information, allowing for rapid and effective market research.

[0732] "Information provision medium" refers to the technical means used to obtain input information from users, and includes the internet and mobile devices.

[0733] The "question generation function" is a technical means of automatically generating appropriate questions based on the objectives of market research.

[0734] The "duplicate and redundancy identification function" is a technology that detects duplicate content and unnecessary parts in the generated questions and optimizes them.

[0735] "Functions provided through diverse platforms" refers to means of presenting questions to respondents via multiple platforms such as email and social media.

[0736] "Purchase and browsing history information" refers to historical data on products that consumers have purchased and content they have viewed in the past, and is data that indicates the preferences of individual consumers.

[0737] "Automated survey generation" is a function that uses AI to generate market research that takes into account past consumer data, without human intervention.

[0738] To carry out the present invention, a system having the following configuration is used.

[0739] The system uses servers and terminals to automatically generate, optimize, and distribute market research questions. The server first obtains input information from users through information provision media. Based on this input information, it uses an AI algorithm to create appropriate questions and utilizes a generation AI model. The generated questions are optimized using natural language processing (NLP) techniques to identify duplication and redundancy. Python and Django are preferred software for this system.

[0740] Optimized questions are delivered to target respondents via various platforms such as email and social media. After delivery, the devices send the collected response data to the server in real time. The server analyzes and visualizes this data. Based on the analysis results, users can obtain recommended solutions that take into account their purchasing behavior and browsing history. The analysis results are displayed in graphs and charts and provided to users in real time.

[0741] As a concrete example, when a company launches a new product into the market, it uses this system to create questions for its target customer base. The questions generated through the AI ​​model are automatically sent via social media or email. The collected responses are immediately analyzed, allowing the company to quickly understand consumers' purchasing intent and evaluation of the new product.

[0742] Example of a prompt:

[0743] Customer segment: Women aged 20 to 30

[0744] Product Category: Casual Wear

[0745] Survey topic: Feedback on new products

[0746] Desired analysis content: Color acceptance, price tolerance

[0747] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0748] Step 1:

[0749] The server collects input information from users, such as the purpose and conditions of the market research, through information provision media. This is done using prompts from questionnaires filled out by the user. The entered information is stored in a database and used to generate questions in the next step.

[0750] Step 2:

[0751] The server uses a generative AI model to create market research questions based on stored input information. It determines the content of the questions by referring to past research data. The generated questions are temporarily stored in memory to check for compliance and duplicates.

[0752] Step 3:

[0753] The server performs natural language processing (NLP) to identify duplication and redundancy in the generated questions. This optimizes the questions, reducing the burden on respondents. The optimized questions are then saved to the database.

[0754] Step 4:

[0755] The device delivers optimized questions to target respondents through various platforms selected by the user (email, social networking services, etc.). Data is transmitted in real time and delivered in a format individually adapted to each platform.

[0756] Step 5:

[0757] The terminal collects response data from the subjects and sends it to the server. The collected data is formatted so that it arrives at the server in a format that allows for immediate analysis.

[0758] Step 6:

[0759] The server analyzes the collected response data and generates trends and insights in real time. This analysis uses data mining techniques and also takes into account the user's purchase and browsing history. The analysis results are displayed to the user in a visualized format.

[0760] Step 7:

[0761] Users receive analysis results and make decisions based on the visualized data. This allows users to quickly grasp market trends and make strategic adjustments regarding new products and services.

[0762] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0763] This invention is a market research questionnaire system that combines an emotion engine, and is characterized by designing an effective and appropriate questionnaire based on input information provided by the user, and performing analysis while taking the user's emotions into consideration.

[0764] First, when a user begins market research, they provide the server with the research objectives and target audience information. Based on this information, the server automatically generates questions using an AI algorithm. It forms the optimal set of questions by referring to past data.

[0765] After the survey is designed, the server uses natural language processing techniques to eliminate duplicate and redundant questions. Furthermore, it utilizes an emotion engine to dynamically adjust questions based on the user's emotional state. This process improves the targeting accuracy of the survey.

[0766] Once the design is complete, the questionnaire will be sent to the target audience via multiple distribution channels (email, social media, apps, etc.) through their devices. Simultaneously with distribution, the device will monitor the user's emotional changes using an emotion engine and adjust the content of the distribution as needed.

[0767] Once responses are collected, the device sends the data to the server. The server analyzes the response data in real time, gaining insights that include emotional changes captured by the emotion engine. This provides deeper, emotion-based insights that go beyond typical data analysis.

[0768] As a concrete example, when formulating a marketing strategy for a new product, users can use this system to conduct research that takes into account the emotional state of the target audience. A survey is conducted using questions generated by the server, and the collected emotional data becomes valuable information for predicting sales of the new product and inferring potential customer responses.

[0769] In this system, users can obtain sophisticated information that takes emotions into account, enabling them to efficiently optimize product development and marketing strategies. The data obtained by the emotion engine adds the necessary dimensions for business decision-making, supporting more competitive market strategies.

[0770] The following describes the processing flow.

[0771] Step 1:

[0772] The user initiates market research and provides input information, such as the research target and objectives, to the server. The user enters this information through a web interface or application.

[0773] Step 2:

[0774] The server uses AI algorithms to automatically generate survey questions based on information provided by the user. It selects the most relevant questions for the target audience, taking into account past similar surveys and current market trends.

[0775] Step 3:

[0776] The server optimizes the generated questions using natural language processing techniques. It improves the quality of the survey by detecting and removing or correcting duplicate or redundant expressions in the questions.

[0777] Step 4:

[0778] The server uses an emotion engine to adjust the content of questions to match the user's emotional state. This provides appropriate stimuli to the respondent's emotions, allowing for the collection of more accurate data.

[0779] Step 5:

[0780] The optimized survey is sent to the device, which then distributes it to the target audience. The distribution method can be email, social media, or app, selected according to the target audience.

[0781] Step 6:

[0782] The device uses an emotion engine during the broadcast to monitor changes in the respondents' emotions. If necessary, it dynamically adjusts the broadcast content and provides follow-up at the appropriate time.

[0783] Step 7:

[0784] Once survey responses are collected, the device sends the data to the server. Data transfer occurs in real time, enabling high-speed analysis.

[0785] Step 8:

[0786] The server analyzes the received response data using AI technology, combines it with emotional information obtained from the emotion engine, and gains comprehensive insights. It analyzes trends and the influence of emotions and presents them to the user visually.

[0787] Step 9:

[0788] Users review the analysis results through their devices and make decisions based on insights, including sentiment data. The server provides additional solutions and points of interest to support the user's decision-making.

[0789] (Example 2)

[0790] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0791] In market research, there are challenges in achieving accurate market analysis and making effective decisions due to insufficient optimization of research content, improvement of targeting accuracy, and real-time adjustments that take into account changes in user sentiment.

[0792] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0793] In this invention, the server includes means for dynamically adjusting tasks generated in accordance with the user's emotional state, means for monitoring emotional changes in real time and adjusting the content delivered as needed, and means for improving the quality of the research by referring to past research information. As a result, the user can make adjustments in real time that take emotional changes into account, enabling highly accurate market analysis and decision-making.

[0794] A "user" is an entity that uses the system to input information about the survey content and target individuals, and makes decisions based on the analysis results.

[0795] "Research" is the process of collecting and analyzing information based on a specific purpose.

[0796] A "task" is a set of questions or problems presented to the survey participants.

[0797] "Automatic generation" refers to the process of mechanically creating tasks using an AI model based on information provided by the user.

[0798] "Optimization" means eliminating duplication and redundancy in the generated tasks and making them the most suitable form for the purpose of the investigation.

[0799] "Communication methods" refer to media used to deliver information to survey participants, such as email, social networking services (SNS), and applications.

[0800] "Analysis" is the process of analyzing collected data and extracting information.

[0801] "Visualization" refers to representing analysis results in the form of graphs, charts, and other formats to make them easier to understand.

[0802] "Countermeasures" refer to action plans or solutions proposed based on the analysis results obtained.

[0803] "Emotional state" refers to the psychological and emotional responses that a user exhibits.

[0804] "Real-time" is a term that indicates that information is processed and analyzed immediately.

[0805] "Adjustment" refers to modifying content based on specific conditions of the user or target audience.

[0806] This invention relates to a specific embodiment of a market research questionnaire system that incorporates an emotion engine. This system consists of a user, a server, and a terminal.

[0807] The user first inputs information about the purpose and target audience of their market research. The server receives this information and automatically generates the most suitable challenges using a generative AI model. The AI ​​model refers to a database of past research information and performs keyword extraction and prompt generation to select the most effective challenges.

[0808] The generated tasks are processed using natural language processing technology on the server to remove duplication and redundancy. The server also uses an emotion engine to dynamically adjust the task content based on the user's emotional state. This improves the targeting accuracy of the survey.

[0809] Next, the completed questionnaire is sent to the survey participants via multiple communication methods such as email, social media, and applications through the device. The device monitors the recipient's emotional changes during delivery using an emotion engine and adjusts the delivery timing and message content in real time as needed.

[0810] Finally, the device collects the responses and sends them to the server. The server analyzes this data to gain insights, including changes in sentiment. The information obtained in this process is visualized to support the user's decision-making and presented as effective countermeasures.

[0811] As a concrete example, when evaluating the brand image of a new product, a survey can be conducted using the prompt, "What was your first impression when you saw this product for the first time?" In this way, users can obtain sophisticated information that reflects their emotional changes, which can contribute to the optimization of product development and marketing strategies.

[0812] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0813] Step 1:

[0814] The user inputs information into the server regarding the purpose and target audience for initiating the market research. Specifically, this includes research items, expected outcomes, and demographic information of the target audience. This information is used for initial processing of the AI ​​algorithm.

[0815] Step 2:

[0816] The server automatically generates research questions using a generative AI model based on the information it receives. It analyzes the input data, extracts highly relevant keywords by referring to past market databases, and constructs questions based on those keywords. The output is a set of questions tailored to the user's information.

[0817] Step 3:

[0818] The server uses natural language processing (NLP) to eliminate duplication and redundancy from the generated questions. It receives a set of generated questions as input, performs text analysis, and obtains an optimized list of questions as output.

[0819] Step 4:

[0820] The server uses an emotion engine to analyze the user's emotional state and dynamically adjusts the questions as needed. The input includes a list of optimized questions and the user's emotional state, and the output provides questions customized to match the emotion.

[0821] Step 5:

[0822] The device delivers customized questions to survey participants via communication methods such as email, social media, and apps. Input includes customized questions and distribution channel settings, while output is a questionnaire delivered to the survey participants.

[0823] Step 6:

[0824] The device monitors the recipient's emotional changes during delivery. It uses an emotion engine to analyze the received data and adjust the delivery timing and message content in real time as needed. The output is the adjusted delivery content.

[0825] Step 7:

[0826] The terminal collects responses from survey participants and sends them to the server. The server receives the collected data and performs analysis, including changes in sentiment. The output is a detailed analysis result for the user.

[0827] Step 8:

[0828] The server visualizes the obtained analysis results and presents them to support the user's decision-making. The input is detailed analysis results, and the output is provided to the user as visualized insights and suggestions.

[0829] (Application Example 2)

[0830] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0831] In today's advertising market, accurately capturing viewers' emotions and effectively optimizing advertising content is essential. However, traditional advertising systems struggle to detect viewers' emotions in real time and dynamically adjust advertisements accordingly. This results in limited advertising effectiveness to target audiences and makes it difficult to maximize the effectiveness of advertising strategies.

[0832] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0833] In this invention, the server includes means for automatically generating market research questions based on user-provided input information, means for detecting and optimizing duplicate or redundant generated questions, and means for detecting emotions and dynamically adjusting advertising content. This makes it possible to optimize advertisements according to the emotional state of the viewer.

[0834] A "user" is an entity that provides input information to the system and generates questions for market research.

[0835] "Input information" refers to information provided by the user regarding the purpose and target audience of the market research, and this information serves as the basic data from which questions are generated.

[0836] An "automatic question generation method" is a function that mechanically generates questions for market research based on input information provided by the user.

[0837] "Question optimization means" refers to a function that detects duplication and redundancy in generated questions and transforms them into an efficient and clear question structure.

[0838] "Means for detecting emotions and dynamically adjusting advertising content" refers to a function that senses the viewer's emotional state in real time and effectively changes the content of advertisements accordingly.

[0839] "Information and communication means" refers to communication functions for distributing questions to target respondents through multiple platforms.

[0840] "Methods for analyzing and visualizing response data" refers to a function that analyzes response data collected in real time and visually represents the results.

[0841] "Means for presenting problem-solving methods based on analysis results" refers to a function that, based on the obtained analysis results, proposes specific problem-solving solutions to support the user's decision-making.

[0842] The system implementing this invention is configured in which a server, a terminal, and a user cooperate to operate. The server first receives input information provided by the user and automatically generates questions for market research based on this information. The questions are generated using an AI algorithm, specifically a generative AI model, while referring to past data. The generated questions are optimized using natural language processing technology to detect redundancy and repetition.

[0843] Next, the device uses an emotion engine to detect the user's emotions in real time and dynamically adjusts the ad content based on this. After the ad is optimized, it is delivered to the target respondents across multiple platforms via information and communication means. The delivered ad and response data to the questions are sent to a server via the device and analyzed. At that time, the server also analyzes and visualizes the emotional information contained in the response data.

[0844] Based on the analysis results obtained, the server provides the user with specific suggestions for problem solving. These suggestions enable the user to make optimal decisions based on market research findings.

[0845] For example, if a user visits a shopping mall through smart glasses and shows interest in a particular product, the emotion engine will detect that interest and display relevant advertisements on the user's smartphone. By providing the right information at the right time in this way, a higher advertising effect can be expected.

[0846] An example of a prompt is: "Generate optimal ad content based on the user's current emotional state and suggest ads that support the user's decision-making." The ad content generated based on this prompt is adjusted according to the viewer's interests and emotions, more effectively meeting the viewer's needs.

[0847] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0848] Step 1:

[0849] The server receives input information from the user. This input information includes data about the purpose of the market research and the target audience. Based on the received information, the server builds the foundational data to generate the optimal set of questions.

[0850] Step 2:

[0851] The server utilizes a generative AI model to automatically generate market research questions from input information. It performs data calculations to design the most effective questions by comparing them with historical data, and outputs an optimized list of questions.

[0852] Step 3:

[0853] The server detects redundancy and duplication in the generated questions and optimizes them using natural language processing. Specifically, it removes unnecessary phrases and transforms them into concise and clear expressions. It then outputs the optimized set of questions.

[0854] Step 4:

[0855] The device uses an emotion engine to detect the user's emotions in real time. It takes data about the emotional state as input and generates optimal ad content according to the user's current state. It outputs how the emotional information influenced changes to the ad content.

[0856] Step 5:

[0857] The device delivers questions and advertisements optimized for the target respondents via information and communication means. Specifically, it sends data to email and social media platforms, reaching the target through various channels.

[0858] Step 6:

[0859] The terminal sends the response data collected from the target respondents and the sentiment information detected in real time to the server. Based on the input data, the server starts the analysis and outputs detailed insights that take sentiment into account.

[0860] Step 7:

[0861] The server proposes solutions to the user based on the analysis results. These proposals reflect market insights obtained by integrating collected data and sentiment information. Based on this, the user can make optimal decisions.

[0862] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0863] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0864] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0865] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0866] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0867] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0868] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0869] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0870] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0871] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0872] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0873] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0874] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0875] 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.

[0876] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0877] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0878] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0879] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0880] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0881] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0882] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0883] The following is further disclosed regarding the embodiments described above.

[0884] (Claim 1)

[0885] A means for automatically generating market research questions based on user-provided input information,

[0886] A means to detect and optimize duplicate and redundant questions in the generated questions,

[0887] A means of distributing questions to target respondents through multiple platforms,

[0888] A means of analyzing and visualizing response data collected in real time,

[0889] Based on the analysis results obtained, a means to propose solutions and support decision-making,

[0890] A system that includes this.

[0891] (Claim 2)

[0892] The system according to claim 1, comprising means for performing natural language processing in real time, analyzing differences of opinion, and providing solutions.

[0893] (Claim 3)

[0894] The system according to claim 1, comprising means for improving the quality of the survey by referring to past survey data when selecting questions.

[0895] "Example 1"

[0896] (Claim 1)

[0897] A means for automatically generating market research questions based on user-provided input information,

[0898] A method for detecting and optimizing duplicate and redundant generated questions using natural language processing techniques,

[0899] A means of distributing questions to target respondents through multiple communication methods,

[0900] A means of analyzing and visualizing response information collected in real time,

[0901] Based on the analysis results obtained, countermeasures are proposed and means of supporting decision-making,

[0902] By selecting questions based on past survey data, we can improve the integrity of the survey.

[0903] A system that includes this.

[0904] (Claim 2)

[0905] The system according to claim 1, comprising means for performing natural language processing in real time, analyzing disagreements, and providing solutions.

[0906] (Claim 3)

[0907] The system according to claim 1, comprising means for using artificial intelligence to analyze trends and patterns using collected response information.

[0908] "Application Example 1"

[0909] (Claim 1)

[0910] A function to create market research questions based on user input information obtained through information provision media,

[0911] A function to identify and optimize duplicate and redundant questions in the created questions,

[0912] A function that provides questions to target respondents through various platforms,

[0913] It has the ability to analyze and visualize response data collected in real time,

[0914] Based on the acquired analysis results, it presents recommended solutions and has a function to support decision-making.

[0915] A function that automatically generates surveys considering the user's purchase and browsing history information,

[0916] A system that includes this.

[0917] (Claim 2)

[0918] The system according to claim 1, which performs natural language processing in real time, analyzes differences of opinion, and provides proposed solutions.

[0919] (Claim 3)

[0920] The system according to claim 1, which improves the density of survey content by referring to past survey records when selecting questions.

[0921] "Example 2 of combining an emotion engine"

[0922] (Claim 1)

[0923] A means for automatically generating research tasks based on user-provided input information,

[0924] A means to detect and optimize duplicate and redundant issues in the generated tasks,

[0925] A means of delivering tasks to the dialogue partner through multiple communication methods,

[0926] A means of analyzing and visualizing information collected in real time,

[0927] A means to propose countermeasures based on the obtained analysis results and support decision-making,

[0928] A means of dynamically adjusting tasks generated according to the user's emotional state,

[0929] A means to monitor emotional changes in real time and adjust the content of the broadcast as needed,

[0930] A system that includes this.

[0931] (Claim 2)

[0932] The system according to claim 1, comprising means for performing natural language processing in real time, analyzing differences of opinion, and providing solutions.

[0933] (Claim 3)

[0934] The system according to claim 1, comprising means for improving the quality of the survey by referring to past survey information when selecting questions.

[0935] "Application example 2 when combining with an emotional engine"

[0936] (Claim 1)

[0937] A means for automatically generating market research questions based on user-provided input information,

[0938] A means to detect and optimize duplicate and redundant questions in the generated questions,

[0939] A means of detecting emotions and dynamically adjusting ad content,

[0940] A means of distributing questions to target respondents through multiple information and communication means,

[0941] A means of analyzing and visualizing response data collected in real time,

[0942] Based on the analysis results obtained, we will present problem-solving methods and provide means to support decision-making.

[0943] A system that includes this.

[0944] (Claim 2)

[0945] The system according to claim 1, comprising means for performing natural language processing in real time, analyzing disagreements, and providing solutions.

[0946] (Claim 3)

[0947] The system according to claim 1, comprising means for improving the quality of the survey by referring to past survey data when selecting questions. [Explanation of Symbols]

[0948] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for automatically generating market research questions based on user-provided input information, A means to detect and optimize duplicate and redundant questions in the generated questions, A means of distributing questions to target respondents through multiple platforms, A means of analyzing and visualizing response data collected in real time, Based on the analysis results obtained, a means to propose solutions and support decision-making, A system that includes this.

2. The system according to claim 1, comprising means for performing natural language processing in real time, analyzing differences of opinion, and providing solutions.

3. The system according to claim 1, comprising means for improving the quality of the survey by referring to past survey data when selecting questions.

Images