system

Abstract

We provide the system. [Solution] A method for extracting keywords based on the research theme using natural language processing, A means of automatically generating survey items based on keywords extracted by an artificial intelligence agent, A method for optimizing survey items generated using statistical models, A means for analyzing user feedback and generating information to recommend personalized content, A means of distributing the generated questionnaires and content to the target audience and collecting responses and feedback, A means for analyzing collected responses and feedback data and aggregating the results, 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, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In conventional market research methods, excessive time and costs are involved, and human errors are likely to occur in questionnaire design and result analysis, thus compromising the accuracy of survey results. As a result, it has been difficult to efficiently and accurately grasp market needs.

Means for Solving the Problems

[0005] This invention solves the problems of conventional survey methods by using natural language processing to extract keywords based on the survey theme and automatically generating questionnaire items using an artificial intelligence agent. Furthermore, optimization using statistical models eliminates duplicate and redundant questions, enabling efficient survey implementation. In addition, by analyzing feedback from respondents in real time and dynamically modifying the results, it is possible to accurately grasp market needs.

[0006] "Natural language processing" is a technology that enables computers to understand, interpret, and generate human language.

[0007] An "artificial intelligence agent" is software that has the ability to autonomously perform specific tasks.

[0008] "Survey items" are questions designed based on the purpose of the survey.

[0009] A "statistical model" is a mathematical method used to analyze data and find specific patterns or regularities.

[0010] "Optimization" refers to the process of adjusting resources to maximize the performance of a system or process.

[0011] "Feedback" refers to information and opinions obtained from users, and is data used to improve and adjust the system.

[0012] "Real-time" refers to processing and responses occurring with virtually no delay. [Brief explanation of the drawing]

[0013] [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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0019] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and an antenna and the like. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0020] 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."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0031] 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.

[0032] 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.

[0033] 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".

[0034] The system according to the present invention includes, as its main functions, keyword extraction using natural language processing, survey item generation by an artificial intelligence agent, optimization using a statistical model, and real-time feedback analysis.

[0035] The server first receives a survey topic from the user and extracts keywords related to that topic using natural language processing technology. This allows for the formulation of appropriate questions that are relevant to the topic, thereby improving the accuracy of the survey.

[0036] Next, the server activates an artificial intelligence agent that automatically generates survey questions based on the extracted keywords. This enables efficient survey creation and significantly reduces the time required for survey preparation.

[0037] The generated survey questions are analyzed by a statistical model maintained by the server, eliminating unnecessary duplication and redundant questions. This improves the quality of the questions and reduces the burden on respondents.

[0038] Next, the server delivers an optimized survey to the terminal. The terminal displays the received survey to the user and collects the user's responses. Once the user completes the survey, the terminal immediately sends the data to the server, which analyzes the feedback in real time.

[0039] Based on this feedback, the server aggregates the results and generates a report. Finally, the user can review this report and gain insights to help with their next investigation.

[0040] As a concrete example, consider a case where a company uses this system to conduct market research for a new product. The server sets "health foods" as the theme and extracts related keywords. Based on these, questionnaire items are generated and distributed to terminals for customer interviews at stores. The terminals send customer responses to the server, which analyzes the data in real time and aggregates the results. Through this series of processes, companies can quickly grasp market demand and formulate product strategies.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The server receives research topics from users and extracts keywords based on those topics using natural language processing technology. This allows for the identification of specific keywords suitable for the research.

[0044] Step 2:

[0045] The server uses the extracted keywords to activate artificial intelligence agents, which automatically generate survey questions. At this stage, each agent designs questions from diverse perspectives based on the keywords.

[0046] Step 3:

[0047] The server analyzes the generated survey items using a statistical model, and an optimization engine automatically removes duplicate and redundant questions. This completes the statistically optimized set of questions.

[0048] Step 4:

[0049] The server delivers an optimized survey to the terminal. The terminal receives it and prepares to display the survey to the user using an appropriate interface.

[0050] Step 5:

[0051] The user operates the device and enters their answers to the displayed survey. The device sends the completed answers to the server in real time.

[0052] Step 6:

[0053] The server analyzes the response data sent from the terminals in real time and immediately processes it for aggregation and feedback. Here, it detects overall trends and outliers in the survey and generates analysis results.

[0054] Step 7:

[0055] The server generates a report based on the aggregated analysis results and presents it to the user. The user uses this report to review the survey results and adjust the strategy for the next survey as needed.

[0056] (Example 1)

[0057] 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."

[0058] Traditional survey systems require significant time and effort for extracting theme-based information, creating, optimizing, distributing, and collecting and analyzing responses, highlighting the need for efficient and rapid data processing. Solving this challenge necessitates a new method that seamlessly integrates information extraction and result aggregation.

[0059] 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.

[0060] In this invention, the server includes means for extracting information based on the research theme using natural language processing, means for automatically generating questions based on the extracted information using artificial intelligence, and means for optimizing the generated questions using mathematical models. This makes it possible to conduct research more quickly and efficiently than with conventional methods, and to analyze the opinions obtained immediately.

[0061] "Natural language processing" is a technology that enables computers to understand, analyze, and generate human language.

[0062] A "research theme" is the central subject or topic of a particular survey or study.

[0063] "Information extraction" is the process of extracting necessary or useful information from a specific dataset.

[0064] Artificial intelligence is a technology in which computer systems mimic human intellectual activity and automatically make decisions and solve problems.

[0065] "Automatic question generation" is the process of automatically creating questions for humans to answer using algorithms and models.

[0066] A "mathematical model" is a formalization of real-world phenomena or processes using mathematical expressions.

[0067] "Optimization" is the process of adjusting and improving each element in order to obtain the best results for a specific purpose.

[0068] "Collecting responses" is the process of gathering and recording users' answers to questions.

[0069] "Aggregating results" is the process of analyzing collected data and summarizing it in an easy-to-understand format.

[0070] This invention constructs an efficient research system by combining natural language processing, artificial intelligence, and mathematical models. Specific embodiments of this system are described below.

[0071] The server processes the survey themes received from the user. The server extracts information related to the survey themes using natural language processing. This process utilizes common libraries and models (e.g., open-source natural language processing libraries) as natural language processing techniques. The extracted information is then converted into questions by artificial intelligence. The software used includes common deep learning models and AI frameworks (e.g., widely used generative AI models). These generate questions based on the provided information, and each question is tailored to the user's needs.

[0072] Subsequently, the server optimizes the questions using mathematical models. This optimization process eliminates redundant or redundant questions, ensuring an efficient and effective survey. Common software tools (e.g., computational libraries used for data analysis and optimization) are utilized to perform mathematical calculations and optimization algorithms.

[0073] As a concrete example, consider a case where a company conducts market research for a new product. The server first sets "health foods" as the theme and extracts relevant information. Based on this information, questions such as "reasons for purchasing organic foods" are generated. In this process, the server can use a prompt such as "Generate market research questions on the theme of health foods."

[0074] Optimized questions are delivered to the device, which then presents the questions to the user and sends the collected responses to the server. This allows for real-time analysis and aggregation of results, enabling rapid feedback. Users can also use these results to gain insights that will be useful for future research.

[0075] This configuration provides an efficient and highly accurate research system, enabling rapid market analysis and decision-making support.

[0076] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0077] Step 1:

[0078] The user enters the research topic into the server. For example, if the user wants to conduct market research on "health foods," they would send "health foods" as the topic name to the server. The server receives this input and prepares to proceed to the next process.

[0079] Step 2:

[0080] The server uses natural language processing to extract relevant information from the research topic. Based on the input topic "health foods," it identifies relevant keywords and phrases. This process uses a natural language processing library to analyze text data. The output is a list of keywords such as "organic," "nutrition," and "diet."

[0081] Step 3:

[0082] The server uses a generative AI model to automatically generate questions based on extracted keywords. The server inputs these keywords as prompts into the AI ​​model to generate questions. For example, a question such as "Is organic food an important factor in purchasing decisions?" might be generated. The output is a list of the set of questions used in the survey.

[0083] Step 4:

[0084] The server optimizes the generated questions using mathematical models. This process involves analysis to eliminate duplicate questions and redundant expressions. The input is the initial list of generated questions, and the output is the optimized list of questions. Statistical analysis tools are used in this process.

[0085] Step 5:

[0086] The server delivers optimized questions to the terminal. The terminal prepares to present these questions to the user through its interface. The input is an optimized list of questions, and the output is data in question format displayed on the terminal.

[0087] Step 6:

[0088] The user answers questions via a terminal. Each time the user provides input data for a question, that data is recorded on the terminal. The output is the answer data. The terminal aggregates this data and prepares it for transmission to the server.

[0089] Step 7:

[0090] The terminal sends the collected response data to the server. The input is the user's response data, and the output is in a format that is sent to the server. The server receives this data immediately.

[0091] Step 8:

[0092] The server analyzes the received response data in real time and aggregates the results. Using data analysis tools, it derives trends and patterns from the collected data. The output is a report summarizing the survey results. Users can analyze this report and use the information to guide their next actions.

[0093] (Application Example 1)

[0094] 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."

[0095] Current survey systems and content distribution services struggle to grasp user interests and feedback in real time, and to generate appropriate survey questions or suggest individually optimized content based on that information. As a result, there is a lack of timely information delivery that is tailored to user interests, and an improvement in the user experience is needed.

[0096] 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.

[0097] In this invention, the server includes means for extracting keywords based on a survey theme using natural language processing, means for automatically generating survey items based on the extracted keywords using an artificial intelligence agent, and means for analyzing user feedback and generating information for recommending personalized content. This enables the provision of personalized surveys and content to users in real time.

[0098] "Natural language processing" is the technology that enables computers to understand and generate human language.

[0099] An "artificial intelligence agent" is a system that autonomously performs tasks using machine learning algorithms.

[0100] A "statistical model" is a mathematical model used in data analysis to extract patterns and make predictions.

[0101] "Feedback" refers to opinions and reactions from users, and is information used to improve the system.

[0102] "Personalized content" refers to information and services that are customized based on the individual user's characteristics and preferences.

[0103] "Target audience" refers to individuals or groups who receive surveys or content distribution.

[0104] The system realizing this invention combines multiple functions to perform highly accurate and efficient information gathering and content distribution. The server first uses the OpenAI® natural language processing library API to extract keywords related to user feedback and themes. Based on the keywords extracted in this process, an artificial intelligence agent generates optimal survey items and content. The server then utilizes a constructed statistical model to further optimize the generated items and content.

[0105] The device provides users with optimized surveys and content, and collects feedback in real time. User feedback is immediately sent to a server for analysis. The server uses the collected data to analyze the content and aggregate the results to provide valuable information to the user. For example, in a content distribution service, if a user shows a strong interest in action movies, the data can be analyzed in real time, and movies that match the user's preferences can be recommended.

[0106] In this way, the server dynamically updates content and surveys based on the collected feedback data. This process enables the system to provide services that accurately respond to the user's interests and preferences. For example, by entering the following prompt message, "Extract keywords that will pique interest from the feedback below: The user is interested in action movies featuring strong female characters," the system can accurately extract the target keywords.

[0107] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0108] Step 1:

[0109] The server receives research topics and feedback from users. Using OpenAI's natural language processing API, it extracts relevant keywords from this input text data. This process outputs the input data as a list of keywords based on important topics.

[0110] Step 2:

[0111] The server uses an artificial intelligence agent to generate appropriate survey questions and content recommendation information based on the extracted keywords. In this process, a data model is built based on the keywords, and this is output as survey questions and content profiles.

[0112] Step 3:

[0113] The server applies statistical models to optimize the generated surveys and content. This involves data calculations such as duplicate removal and content prioritization. The input consists of survey items and content profiles, which are then output in an optimized form.

[0114] Step 4:

[0115] The device delivers optimized survey questions and content to the user, displaying them in a visually effective format on the user's device screen. The user answers the survey and consumes the content. The device records this behavior and responses as data.

[0116] Step 5:

[0117] The terminal sends feedback data collected from the user to the server. This data becomes input, and the server begins analysis in real time. Through the analysis, user interests and trends are identified, and the results are output in a visualized report format.

[0118] Step 6:

[0119] Based on the analysis results, the server dynamically modifies its content and survey strategies, updating the system to provide more suitable content and surveys in future deliveries. This process ensures that information is provided that meets the needs of the target users.

[0120] 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.

[0121] This invention is a system that combines natural language processing and artificial intelligence, and by incorporating an emotion engine, it includes a function to analyze user emotions in surveys. In addition to generating, optimizing, distributing, and aggregating typical survey items, this system grasps the user's emotional state in real time, improving the accuracy of survey content and feedback.

[0122] The server receives survey themes from users and extracts relevant keywords using natural language processing. This, combined with user sentiment data detected by the sentiment engine, enables the design of more accurate questions.

[0123] The artificial intelligence agent generates survey questions based on extracted keywords and user sentiment data. At this point, the sentiment engine analyzes the user's emotions and helps select appropriate question formats and content. This feature proactively adjusts questions that might potentially evoke emotional responses from the user.

[0124] The terminal displays the questionnaire sent from the server to the user, and an emotion engine analyzes the user's facial expressions and voice tone while they are answering the questionnaire. This data is sent back to the server and used to adjust the questionnaire questions in real time.

[0125] Based on user sentiment data, the server adds emotional insights to the survey results and generates an improved report. This report also includes an analysis of the emotions users were experiencing, providing a new perspective on interpreting the survey results.

[0126] For example, in market research for a new product, when conducting a survey on product features that are likely to cause dissatisfaction, this system can be used to detect and adjust questions that users find unpleasant in real time. In this way, the present invention provides new value by utilizing sentiment analysis to improve the accuracy of surveys and user satisfaction.

[0127] The following describes the processing flow.

[0128] Step 1:

[0129] The server receives survey themes from users and extracts keywords related to those themes using natural language processing techniques. These extracted keywords are later used to generate survey questions.

[0130] Step 2:

[0131] The server activates an emotion engine and analyzes the emotional nuances associated with the extracted keywords. Based on this analysis, an artificial intelligence agent generates survey questions. Emotionally sensitive question design takes place at this stage.

[0132] Step 3:

[0133] The server optimizes the generated survey questions using statistical models, eliminating duplicates and questions that might burden the user.

[0134] Step 4:

[0135] The server delivers an optimized survey to the terminal. The terminal receives it and prepares an interface to display the survey to the user.

[0136] Step 5:

[0137] When users answer surveys via their devices, the emotion engine analyzes their facial expressions and voice in real time. This allows the system to understand the user's emotional state.

[0138] Step 6:

[0139] The device sends the analyzed user sentiment data to the server. Based on this sentiment data, the server adjusts the content of the survey questions in real time.

[0140] Step 7:

[0141] The server analyzes the collected response data, combining it with user sentiment data, and aggregates the results. This generates a research report that includes deeper insights.

[0142] Step 8:

[0143] Users can review survey results reports sent from the server and use them to inform their decision-making by gaining emotion-based insights along with the survey findings.

[0144] (Example 2)

[0145] 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 will be referred to as the "terminal."

[0146] Traditional survey methods struggle to analyze respondents' emotions in real time, resulting in survey results lacking crucial emotional insights. Furthermore, the inability to adjust questions in real time to reflect respondents' feelings carries the risk of inappropriate or offensive questions. To address these challenges, a more emotionally sensitive and responsive survey system is needed.

[0147] 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.

[0148] In this invention, the server includes means for extracting keywords based on the survey theme using natural language processing, means for automatically generating questionnaire items based on the extracted keywords and sentiment analysis data using an artificial intelligence agent, and means for collecting user sentiment data in real time using a sentiment analysis engine and reflecting it in the questionnaire items. As a result, the questionnaire is dynamically adjusted according to the emotions of the respondents, enabling the provision of highly accurate survey results that include emotional insights.

[0149] "Natural language processing" is a technology that enables computers to understand, analyze, and generate human language, and it is a method for extracting keywords and interpreting text.

[0150] An "artificial intelligence agent" is a program that automatically performs specific tasks based on input information, and is a technology that plays a role in generating survey questions.

[0151] An "emotion analysis engine" is a technology that analyzes a user's emotional data from their voice tone and facial expressions, and uses the results as feedback.

[0152] "Information display device" refers to any device that presents questionnaires to subjects and allows for user interaction, including mobile devices and computer screens.

[0153] "Response information" refers to all data, including facial expressions, tone of voice, and text responses, that respondents exhibit while answering questionnaires.

[0154] "Emotional insight" refers to the knowledge gained from collected emotional data, and is information used to evaluate the potential emotions and attitudes of the subjects.

[0155] This invention is a survey system that utilizes natural language processing technology and artificial intelligence, and has the function of analyzing the user's emotions in real time by combining it with an emotion analysis engine. The invention includes the following specific configurations in order to carry it out.

[0156] The server receives survey themes entered by the user. It then uses a natural language processing library to extract relevant keywords. Specifically, NLTK and BERT models are expected to be used as natural language libraries. Next, a sentiment analysis engine is utilized to analyze the user's past feedback and real-time response data. Based on this, an artificial intelligence agent automatically generates survey questions using a generative AI model. For example, the GPT series would likely be used as this generative AI model.

[0157] The terminal provides an interface that displays the questionnaire sent from the server to the user. Here, the camera and microphone are used to analyze the user's facial expressions and voice tone in real time, collecting user emotion data. The collected data is then returned to the server and used to dynamically adjust the questionnaire content.

[0158] As a concrete example, when conducting market research for a new product, if the questions include product features that are likely to cause dissatisfaction, the system can instantly revise the questions if it detects negative user sentiment. For instance, the question "What are the drawbacks of this product?" could be changed to "What improvements would you like to see in this product?"

[0159] An example of a prompt might be, "Please show me how to generate survey questions based on user sentiment data and adjust them in real time." This prompt is expected to prompt the generation AI model to provide specific survey design and adjustment methods.

[0160] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0161] Step 1:

[0162] The server receives research themes entered by users. Based on the entered research themes, it extracts relevant keywords using natural language processing libraries. Specifically, it performs text analysis using Python's NLTK and BERT models and outputs important words and phrases related to the theme as a list.

[0163] Step 2:

[0164] The server retrieves relevant sentiment data through its sentiment analysis engine. During this process, it analyzes the user's past feedback and real-time text input to determine their emotions. It estimates the user's emotional state from the input data and outputs it as an emotion value. This emotion value is then used to generate subsequent questions.

[0165] Step 3:

[0166] The artificial intelligence agent receives keywords and sentiment values ​​extracted by the server as input. Using a generative AI model (e.g., the GPT series), it automatically generates survey questions based on this data. The survey questions are generated with sentiment values ​​in mind and output in a user-friendly format.

[0167] Step 4:

[0168] The device displays the generated questionnaire to the user. While the questionnaire is displayed, it records the user's response process and uses the camera and microphone to analyze the user's facial expressions and voice tone in real time. The data obtained from this analysis is sent to an emotion analysis engine, which outputs the user's emotional response as an analysis result.

[0169] Step 5:

[0170] The server receives the sentiment data sent from the device and dynamically adjusts the survey questions. If the user's sentiment shifts to negative, the server uses this information to change or rearrange the questions and outputs the revised survey content back to the device.

[0171] Step 6:

[0172] The server ultimately analyzes the survey results based on all collected user data (response information and sentiment data) and generates a detailed report. This report includes extensive analysis results, including sentiment insights, and is provided as the final output.

[0173] (Application Example 2)

[0174] 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".

[0175] User feedback on online platforms and services is crucial for improving products and services. However, traditional survey systems often use fixed questions that don't consider user emotions, which can compromise user satisfaction and the accuracy of feedback. In particular, the reliability of feedback decreases when users cannot accurately reflect their emotions. Against this backdrop, there is a need for methods that can identify users' emotional states in real time and optimize questions based on that information to obtain more accurate and useful feedback.

[0176] 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.

[0177] In this invention, the server includes means for extracting keywords based on the research theme using natural language processing, means for automatically generating question items based on the extracted keywords using an artificial intelligence agent, means for analyzing the emotional state of the subject in real time, and means for dynamically adjusting the question items based on the emotional state. This makes it possible to optimize the question items while taking into account the user's real-time emotions, thereby improving the accuracy of feedback and user satisfaction.

[0178] "Natural language processing" is a technology that uses computers to analyze, understand, and generate human language.

[0179] An "artificial intelligence agent" is a program or system that operates autonomously and makes decisions based on information from its environment.

[0180] A "statistical model" is a mathematical model created to analyze the characteristics of data and to make predictions or inferences.

[0181] "Target audience" refers to the people who answer questions in a survey or questionnaire.

[0182] "Emotional state" refers to data that indicates a user's subjective mood and feelings, and is primarily measured through facial expressions and voice tone.

[0183] "Dynamic adjustment" refers to changing the content in real time according to data and circumstances.

[0184] "Questionnaire items" refer to the specific questions presented to respondents in a survey or questionnaire.

[0185] "Feedback" is a general term for the responses, opinions, and experiences obtained from the target audience, and is used to improve products and services.

[0186] The system that realizes the present invention mainly consists of a server, a terminal, and a user interface.

[0187] When a research topic is given, the server uses natural language processing algorithms to extract relevant keywords. The server can utilize Google's Natural Language API and IBM Watson's NLP tools for this process. Furthermore, an artificial intelligence agent automatically generates survey questions based on the extracted keywords, using generative AI models such as OpenAI's GPT series. These questions are optimized using statistical models to provide the most appropriate content for each participant.

[0188] The device displays generated questions to the user and receives the user's responses. During this process, the device analyzes the user's emotional state in real time and sends captured facial expression data and voice tone to a server in the cloud. Emotion analysis uses facial recognition by Amazon Rekognition and voice analysis by Google Cloud Speech-to-Text.

[0189] Users answer questions using smartphones or tablets. The system takes the user's emotional state into consideration and dynamically adjusts the questions as needed. For example, if the system detects that the user is stressed, it can replace the question with an easier one.

[0190] Ultimately, the server aggregates and analyzes all response and sentiment data. This allows for a more accurate understanding of feedback on products and services, which is then output as a report. This report includes sentiment insights that can be used to improve product development and marketing strategies.

[0191] For example, by generating prompts such as, "What are your feelings about this product? Please tell us specifically what you would like to see improved," it becomes possible to ask questions that delve deeper into the user's subjective opinions.

[0192] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0193] Step 1:

[0194] The server receives a research topic. Given the research topic as input, it analyzes it using a natural language processing tool and extracts relevant keywords. It then uses Google's Natural Language API to break down the text and identify the main topics. The output is a set of keywords used in the next step.

[0195] Step 2:

[0196] The server processes keywords as input using an artificial intelligence agent and automatically generates question items. It utilizes OpenAI's generative AI model to form grammatically correct question sentences. This process transforms the input keywords into context-appropriate question sentences. The output is the generated question items.

[0197] Step 3:

[0198] The server optimizes the questionnaire using a statistical model. It takes the generated questionnaire as input and evaluates it using a model built from past survey data and user behavior. It predicts the effectiveness of the questions and adjusts the content to maximize user engagement. The output is the optimized questionnaire.

[0199] Step 4:

[0200] The device displays optimized questionnaire items to the user. This constitutes the actual survey. The user answers the questions and sends the input data to the device. The output is the user's response data.

[0201] Step 5:

[0202] The device measures the user's emotional state in real time during the response process. It uses a camera and microphone to perform facial recognition and voice tone analysis, and sends the data to the cloud. The input is the user's video and audio, and the output is the analyzed emotional data.

[0203] Step 6:

[0204] The server uses real-time sentiment data as input and dynamically adjusts questions as needed. If excessive stress or discomfort is detected, the difficulty and format of the questions are gently modified. The output is the modified questions.

[0205] Step 7:

[0206] The server aggregates and analyzes all response and sentiment data. The aggregation process takes individual user data as input and applies statistical analysis methods to grasp overall trends. The output is a report generated based on the analysis results. This report also includes insights gained using prompt messages.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] [Second Embodiment]

[0211] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0212] 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.

[0213] 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).

[0214] 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.

[0215] 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.

[0216] 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).

[0217] 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.

[0218] 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.

[0219] 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.

[0220] 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.

[0221] 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.

[0222] 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".

[0223] The system according to the present invention includes, as its main functions, keyword extraction using natural language processing, survey item generation by an artificial intelligence agent, optimization using a statistical model, and real-time feedback analysis.

[0224] The server first receives a survey topic from the user and extracts keywords related to that topic using natural language processing technology. This allows for the formulation of appropriate questions that are relevant to the topic, thereby improving the accuracy of the survey.

[0225] Next, the server activates an artificial intelligence agent that automatically generates survey questions based on the extracted keywords. This enables efficient survey creation and significantly reduces the time required for survey preparation.

[0226] The generated survey questions are analyzed by a statistical model maintained by the server, eliminating unnecessary duplication and redundant questions. This improves the quality of the questions and reduces the burden on respondents.

[0227] Next, the server delivers an optimized survey to the terminal. The terminal displays the received survey to the user and collects the user's responses. Once the user completes the survey, the terminal immediately sends the data to the server, which analyzes the feedback in real time.

[0228] Based on this feedback, the server aggregates the results and generates a report. Finally, the user can review this report and gain insights to help with their next investigation.

[0229] As a concrete example, consider a case where a company uses this system to conduct market research for a new product. The server sets "health foods" as the theme and extracts related keywords. Based on these, questionnaire items are generated and distributed to terminals for customer interviews at stores. The terminals send customer responses to the server, which analyzes the data in real time and aggregates the results. Through this series of processes, companies can quickly grasp market demand and formulate product strategies.

[0230] The following describes the processing flow.

[0231] Step 1:

[0232] The server receives research topics from users and extracts keywords based on those topics using natural language processing technology. This allows for the identification of specific keywords suitable for the research.

[0233] Step 2:

[0234] The server uses the extracted keywords to activate artificial intelligence agents, which automatically generate survey questions. At this stage, each agent designs questions from diverse perspectives based on the keywords.

[0235] Step 3:

[0236] The server analyzes the generated survey items using a statistical model, and an optimization engine automatically removes duplicate and redundant questions. This completes the statistically optimized set of questions.

[0237] Step 4:

[0238] The server delivers an optimized survey to the terminal. The terminal receives it and prepares to display the survey to the user using an appropriate interface.

[0239] Step 5:

[0240] The user operates the device and enters their answers to the displayed survey. The device sends the completed answers to the server in real time.

[0241] Step 6:

[0242] The server analyzes the response data sent from the terminals in real time and immediately processes it for aggregation and feedback. Here, it detects overall trends and outliers in the survey and generates analysis results.

[0243] Step 7:

[0244] The server generates a report based on the aggregated analysis results and presents it to the user. The user uses this report to review the survey results and adjust the strategy for the next survey as needed.

[0245] (Example 1)

[0246] 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."

[0247] Traditional survey systems require significant time and effort for extracting theme-based information, creating, optimizing, distributing, and collecting and analyzing responses, highlighting the need for efficient and rapid data processing. Solving this challenge necessitates a new method that seamlessly integrates information extraction and result aggregation.

[0248] 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.

[0249] In this invention, the server includes means for extracting information based on the research theme using natural language processing, means for automatically generating questions based on the extracted information using artificial intelligence, and means for optimizing the generated questions using mathematical models. This makes it possible to conduct research more quickly and efficiently than with conventional methods, and to analyze the opinions obtained immediately.

[0250] "Natural language processing" is a technology that enables computers to understand, analyze, and generate human language.

[0251] A "research theme" is the central subject or topic of a particular survey or study.

[0252] "Information extraction" is the process of extracting necessary or useful information from a specific dataset.

[0253] Artificial intelligence is a technology in which computer systems mimic human intellectual activity and automatically make decisions and solve problems.

[0254] "Automatic question generation" is the process of automatically creating questions for humans to answer using algorithms and models.

[0255] A "mathematical model" is a formalization of real-world phenomena or processes using mathematical expressions.

[0256] "Optimization" is the process of adjusting and improving each element in order to obtain the best results for a specific purpose.

[0257] "Collecting responses" is the process of gathering and recording users' answers to questions.

[0258] "Aggregating results" is the process of analyzing collected data and summarizing it in an easy-to-understand format.

[0259] This invention constructs an efficient research system by combining natural language processing, artificial intelligence, and mathematical models. Specific embodiments of this system are described below.

[0260] The server processes the survey themes received from the user. The server extracts information related to the survey themes using natural language processing. This process utilizes common libraries and models (e.g., open-source natural language processing libraries) as natural language processing techniques. The extracted information is then converted into questions by artificial intelligence. The software used includes common deep learning models and AI frameworks (e.g., widely used generative AI models). These generate questions based on the provided information, and each question is tailored to the user's needs.

[0261] Subsequently, the server optimizes the questions using mathematical models. This optimization process eliminates redundant or redundant questions, ensuring an efficient and effective survey. Common software tools (e.g., computational libraries used for data analysis and optimization) are utilized to perform mathematical calculations and optimization algorithms.

[0262] As a concrete example, consider a case where a company conducts market research for a new product. The server first sets "health foods" as the theme and extracts relevant information. Based on this information, questions such as "reasons for purchasing organic foods" are generated. In this process, the server can use a prompt such as "Generate market research questions on the theme of health foods."

[0263] Optimized questions are delivered to the device, which then presents the questions to the user and sends the collected responses to the server. This allows for real-time analysis and aggregation of results, enabling rapid feedback. Users can also use these results to gain insights that will be useful for future research.

[0264] This configuration provides an efficient and highly accurate research system, enabling rapid market analysis and decision-making support.

[0265] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0266] Step 1:

[0267] The user enters the research topic into the server. For example, if the user wants to conduct market research on "health foods," they would send "health foods" as the topic name to the server. The server receives this input and prepares to proceed to the next process.

[0268] Step 2:

[0269] The server uses natural language processing to extract relevant information from the research topic. Based on the input topic "health foods," it identifies relevant keywords and phrases. This process uses a natural language processing library to analyze text data. The output is a list of keywords such as "organic," "nutrition," and "diet."

[0270] Step 3:

[0271] The server uses a generative AI model to automatically generate questions based on extracted keywords. The server inputs these keywords as prompts into the AI ​​model to generate questions. For example, a question such as "Is organic food an important factor in purchasing decisions?" might be generated. The output is a list of the set of questions used in the survey.

[0272] Step 4:

[0273] The server optimizes the generated questions using mathematical models. This process involves analysis to eliminate duplicate questions and redundant expressions. The input is the initial list of generated questions, and the output is the optimized list of questions. Statistical analysis tools are used in this process.

[0274] Step 5:

[0275] The server delivers optimized questions to the terminal. The terminal prepares to present these questions to the user through its interface. The input is an optimized list of questions, and the output is data in question format displayed on the terminal.

[0276] Step 6:

[0277] The user answers questions via a terminal. Each time the user provides input data for a question, that data is recorded on the terminal. The output is the answer data. The terminal aggregates this data and prepares it for transmission to the server.

[0278] Step 7:

[0279] The terminal sends the collected response data to the server. The input is the user's response data, and the output is in a format that is sent to the server. The server receives this data immediately.

[0280] Step 8:

[0281] The server analyzes the received response data in real time and aggregates the results. Using data analysis tools, trends and patterns are derived from the collected data. The output is a report summarizing the survey results. Users can analyze this report and use it to inform their next actions.

[0282] (Application Example 1)

[0283] 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".

[0284] In current questionnaire systems and content delivery services, it is difficult to grasp users' interests and feedback in real time and, based on that, generate appropriate questionnaire items or propose individually optimized content. As a result, there is a lack of rapid information provision that meets users' interests, and an improvement in the experience is required.

[0285] 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.

[0286] In this invention, the server includes means for extracting keywords based on a survey theme using natural language processing, means for automatically generating questionnaire items based on the keywords extracted by an artificial intelligence agent, and means for analyzing feedback from users and generating information for recommending personalized content. As a result, it becomes possible to provide individualized questionnaires and content to users in real time.

[0287] "Natural language processing" is a technology by which a computer understands and generates human language.

[0288] "Artificial intelligence agent" is a system that autonomously performs tasks using machine learning algorithms.

[0289] A "statistical model" is a mathematical model used in data analysis to extract patterns and make predictions.

[0290] "Feedback" refers to opinions and reactions from users, and is information used to improve the system.

[0291] "Personalized content" refers to information and services that are customized based on the individual user's characteristics and preferences.

[0292] "Target audience" refers to individuals or groups who receive surveys or content distribution.

[0293] The system realizing this invention combines multiple functions to perform highly accurate and efficient information gathering and content distribution. The server first uses the OpenAI API, a natural language processing library, to extract keywords related to user feedback and themes. Based on the keywords extracted in this process, an artificial intelligence agent generates optimal survey items and content. The server then utilizes a constructed statistical model to further optimize the generated items and content.

[0294] The device provides users with optimized surveys and content, and collects feedback in real time. User feedback is immediately sent to a server for analysis. The server uses the collected data to analyze the content and aggregate the results to provide valuable information to the user. For example, in a content distribution service, if a user shows a strong interest in action movies, the data can be analyzed in real time, and movies that match the user's preferences can be recommended.

[0295] In this way, the server dynamically updates content and surveys based on the collected feedback data. This process enables the system to provide services that accurately respond to the user's interests and preferences. For example, by entering the following prompt message, "Extract keywords that will pique interest from the feedback below: The user is interested in action movies featuring strong female characters," the system can accurately extract the target keywords.

[0296] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0297] Step 1:

[0298] The server receives research topics and feedback from users. Using OpenAI's natural language processing API, it extracts relevant keywords from this input text data. This process outputs the input data as a list of keywords based on important topics.

[0299] Step 2:

[0300] The server uses an artificial intelligence agent to generate appropriate survey questions and content recommendation information based on the extracted keywords. In this process, a data model is built based on the keywords, and this is output as survey questions and content profiles.

[0301] Step 3:

[0302] The server applies statistical models to optimize the generated surveys and content. This involves data calculations such as duplicate removal and content prioritization. The input consists of survey items and content profiles, which are then output in an optimized form.

[0303] Step 4:

[0304] The terminal distributes optimized questionnaire items and content to the user. At this time, it is displayed in a visually effective form on the user's terminal screen. The user answers the questionnaire and consumes the content. The terminal records the user's actions and answers as data.

[0305] Step 5:

[0306] The terminal sends the feedback data collected from the user to the server. This data serves as input, and the server starts analyzing it in real time. Through the analysis, the user's interests and trends are identified, and the results are output in the form of a visualized report.

[0307] Step 6:

[0308] Based on the analysis results, the server dynamically modifies further content and questionnaire strategies, and updates the system so that more suitable content can be provided in the next content provision and questionnaire distribution. This process ensures the provision of information adapted to the targeted user needs.

[0309] Furthermore, an emotion engine for estimating the user's emotions may be combined. That is, the specific processing unit 290 may estimate the user's emotions using the emotion identification model 59 and perform specific processing using the user's emotions.

[0310] The present invention is a system that integrates natural language processing and artificial intelligence, and includes a function of analyzing the user's emotions in a questionnaire survey by combining an emotion engine. This system, in addition to the generation, optimization, distribution, and aggregation of normal questionnaire items, grasps the user's emotional state in real time and improves the accuracy of the questionnaire content and feedback.

[0311] The server receives the survey theme from the user and extracts relevant keywords using natural language processing. By combining this with the user's emotion data detected by the emotion engine, more accurate question design becomes possible.

[0312] The artificial intelligence agent generates survey questions based on extracted keywords and user sentiment data. At this point, the sentiment engine analyzes the user's emotions and helps select appropriate question formats and content. This feature proactively adjusts questions that might potentially evoke emotional responses from the user.

[0313] The terminal displays the questionnaire sent from the server to the user, and an emotion engine analyzes the user's facial expressions and voice tone while they are answering the questionnaire. This data is sent back to the server and used to adjust the questionnaire questions in real time.

[0314] Based on user sentiment data, the server adds emotional insights to the survey results and generates an improved report. This report also includes an analysis of the emotions users were experiencing, providing a new perspective on interpreting the survey results.

[0315] For example, in market research for a new product, when conducting a survey on product features that are likely to cause dissatisfaction, this system can be used to detect and adjust questions that users find unpleasant in real time. In this way, the present invention provides new value by utilizing sentiment analysis to improve the accuracy of surveys and user satisfaction.

[0316] The following describes the processing flow.

[0317] Step 1:

[0318] The server receives survey themes from users and extracts keywords related to those themes using natural language processing techniques. These extracted keywords are later used to generate survey questions.

[0319] Step 2:

[0320] The server activates an emotion engine and analyzes the emotional nuances associated with the extracted keywords. Based on this analysis, an artificial intelligence agent generates survey questions. Emotionally sensitive question design takes place at this stage.

[0321] Step 3:

[0322] The server optimizes the generated survey questions using statistical models, eliminating duplicates and questions that might burden the user.

[0323] Step 4:

[0324] The server delivers an optimized survey to the terminal. The terminal receives it and prepares an interface to display the survey to the user.

[0325] Step 5:

[0326] When users answer surveys via their devices, the emotion engine analyzes their facial expressions and voice in real time. This allows the system to understand the user's emotional state.

[0327] Step 6:

[0328] The device sends the analyzed user sentiment data to the server. Based on this sentiment data, the server adjusts the content of the survey questions in real time.

[0329] Step 7:

[0330] The server analyzes the collected response data, combining it with user sentiment data, and aggregates the results. This generates a research report that includes deeper insights.

[0331] Step 8:

[0332] Users can review survey results reports sent from the server and use them to inform their decision-making by gaining emotion-based insights along with the survey findings.

[0333] (Example 2)

[0334] 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".

[0335] Traditional survey methods struggle to analyze respondents' emotions in real time, resulting in survey results lacking crucial emotional insights. Furthermore, the inability to adjust questions in real time to reflect respondents' feelings carries the risk of inappropriate or offensive questions. To address these challenges, a more emotionally sensitive and responsive survey system is needed.

[0336] 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.

[0337] In this invention, the server includes means for extracting keywords based on the survey theme using natural language processing, means for automatically generating questionnaire items based on the extracted keywords and sentiment analysis data using an artificial intelligence agent, and means for collecting user sentiment data in real time using a sentiment analysis engine and reflecting it in the questionnaire items. As a result, the questionnaire is dynamically adjusted according to the emotions of the respondents, enabling the provision of highly accurate survey results that include emotional insights.

[0338] "Natural language processing" is a technology that enables computers to understand, analyze, and generate human language, and it is a method for extracting keywords and interpreting text.

[0339] An "artificial intelligence agent" is a program that automatically performs specific tasks based on input information, and is a technology that plays a role in generating survey questions.

[0340] An "emotion analysis engine" is a technology that analyzes a user's emotional data from their voice tone and facial expressions, and uses the results as feedback.

[0341] "Information display device" refers to any device that presents questionnaires to subjects and allows for user interaction, including mobile devices and computer screens.

[0342] "Response information" refers to all data, including facial expressions, tone of voice, and text responses, that respondents exhibit while answering questionnaires.

[0343] "Emotional insight" refers to the knowledge gained from collected emotional data, and is information used to evaluate the potential emotions and attitudes of the subjects.

[0344] This invention is a survey system that utilizes natural language processing technology and artificial intelligence, and has the function of analyzing the user's emotions in real time by combining it with an emotion analysis engine. The invention includes the following specific configurations in order to carry it out.

[0345] The server receives survey themes entered by the user. It then uses a natural language processing library to extract relevant keywords. Specifically, NLTK and BERT models are expected to be used as natural language libraries. Next, a sentiment analysis engine is utilized to analyze the user's past feedback and real-time response data. Based on this, an artificial intelligence agent automatically generates survey questions using a generative AI model. For example, the GPT series would likely be used as this generative AI model.

[0346] The terminal provides an interface that displays the questionnaire sent from the server to the user. Here, the camera and microphone are used to analyze the user's facial expressions and voice tone in real time, collecting user emotion data. The collected data is then returned to the server and used to dynamically adjust the questionnaire content.

[0347] As a concrete example, when conducting market research for a new product, if the questions include product features that are likely to cause dissatisfaction, the system can instantly revise the questions if it detects negative user sentiment. For instance, the question "What are the drawbacks of this product?" could be changed to "What improvements would you like to see in this product?"

[0348] An example of a prompt might be, "Please show me how to generate survey questions based on user sentiment data and adjust them in real time." This prompt is expected to prompt the generation AI model to provide specific survey design and adjustment methods.

[0349] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0350] Step 1:

[0351] The server receives research themes entered by users. Based on the entered research themes, it extracts relevant keywords using natural language processing libraries. Specifically, it performs text analysis using Python's NLTK and BERT models and outputs important words and phrases related to the theme as a list.

[0352] Step 2:

[0353] The server retrieves relevant sentiment data through its sentiment analysis engine. During this process, it analyzes the user's past feedback and real-time text input to determine their emotions. It estimates the user's emotional state from the input data and outputs it as an emotion value. This emotion value is then used to generate subsequent questions.

[0354] Step 3:

[0355] The artificial intelligence agent receives keywords and sentiment values ​​extracted by the server as input. Using a generative AI model (e.g., the GPT series), it automatically generates survey questions based on this data. The survey questions are generated with sentiment values ​​in mind and output in a user-friendly format.

[0356] Step 4:

[0357] The device displays the generated questionnaire to the user. While the questionnaire is displayed, it records the user's response process and uses the camera and microphone to analyze the user's facial expressions and voice tone in real time. The data obtained from this analysis is sent to an emotion analysis engine, which outputs the user's emotional response as an analysis result.

[0358] Step 5:

[0359] The server receives the sentiment data sent from the device and dynamically adjusts the survey questions. If the user's sentiment shifts to negative, the server uses this information to change or rearrange the questions and outputs the revised survey content back to the device.

[0360] Step 6:

[0361] The server ultimately analyzes the survey results based on all collected user data (response information and sentiment data) and generates a detailed report. This report includes extensive analysis results, including sentiment insights, and is provided as the final output.

[0362] (Application Example 2)

[0363] 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 as the "terminal".

[0364] User feedback on online platforms and services is crucial for improving products and services. However, traditional survey systems often use fixed questions that don't consider user emotions, which can compromise user satisfaction and the accuracy of feedback. In particular, the reliability of feedback decreases when users cannot accurately reflect their emotions. Against this backdrop, there is a need for methods that can identify users' emotional states in real time and optimize questions based on that information to obtain more accurate and useful feedback.

[0365] 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.

[0366] In this invention, the server includes means for extracting keywords based on the research theme using natural language processing, means for automatically generating question items based on the extracted keywords using an artificial intelligence agent, means for analyzing the emotional state of the subject in real time, and means for dynamically adjusting the question items based on the emotional state. This makes it possible to optimize the question items while taking into account the user's real-time emotions, thereby improving the accuracy of feedback and user satisfaction.

[0367] "Natural language processing" is a technology that uses computers to analyze, understand, and generate human language.

[0368] An "artificial intelligence agent" is a program or system that operates autonomously and makes decisions based on information from its environment.

[0369] A "statistical model" is a mathematical model created to analyze the characteristics of data and to make predictions or inferences.

[0370] "Target audience" refers to the people who answer questions in a survey or questionnaire.

[0371] "Emotional state" refers to data that indicates a user's subjective mood and feelings, and is primarily measured through facial expressions and voice tone.

[0372] "Dynamic adjustment" refers to changing the content in real time according to data and circumstances.

[0373] "Questionnaire items" refer to the specific questions presented to respondents in a survey or questionnaire.

[0374] "Feedback" is a general term for the responses, opinions, and experiences obtained from the target audience, and is used to improve products and services.

[0375] The system that realizes the present invention mainly consists of a server, a terminal, and a user interface.

[0376] When a research topic is given, the server extracts relevant keywords using natural language processing algorithms. The server can utilize Google's Natural Language API and IBM Watson's NLP tools for this process. Furthermore, an artificial intelligence agent automatically generates survey questions based on the extracted keywords, using generative AI models such as OpenAI's GPT series. These questions are optimized using statistical models to provide the most appropriate content for each participant.

[0377] The device displays generated questions to the user and receives the user's responses. During this process, the device analyzes the user's emotional state in real time and sends captured facial expression data and voice tone to a server in the cloud. Emotion analysis uses facial recognition by Amazon Rekognition and voice analysis by Google Cloud Speech-to-Text.

[0378] Users answer questions using smartphones or tablets. The system takes the user's emotional state into consideration and dynamically adjusts the questions as needed. For example, if the system detects that the user is stressed, it can replace the question with an easier one.

[0379] Ultimately, the server aggregates and analyzes all response and sentiment data. This allows for a more accurate understanding of feedback on products and services, which is then output as a report. This report includes sentiment insights that can be used to improve product development and marketing strategies.

[0380] For example, by generating prompts such as, "What are your feelings about this product? Please tell us specifically what you would like to see improved," it becomes possible to ask questions that delve deeper into the user's subjective opinions.

[0381] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0382] Step 1:

[0383] The server receives a research topic. Given the research topic as input, it analyzes it using a natural language processing tool and extracts relevant keywords. It then uses Google's Natural Language API to break down the text and identify the main topics. The output is a set of keywords used in the next step.

[0384] Step 2:

[0385] The server processes keywords as input using an artificial intelligence agent and automatically generates question items. It utilizes OpenAI's generative AI model to form grammatically correct question sentences. This process transforms the input keywords into context-appropriate question sentences. The output is the generated question items.

[0386] Step 3:

[0387] The server optimizes the questionnaire using a statistical model. It takes the generated questionnaire as input and evaluates it using a model built from past survey data and user behavior. It predicts the effectiveness of the questions and adjusts the content to maximize user engagement. The output is the optimized questionnaire.

[0388] Step 4:

[0389] The device displays optimized questionnaire items to the user. This constitutes the actual survey. The user answers the questions and sends the input data to the device. The output is the user's response data.

[0390] Step 5:

[0391] The device measures the user's emotional state in real time during the response process. It uses a camera and microphone to perform facial recognition and voice tone analysis, and sends the data to the cloud. The input is the user's video and audio, and the output is the analyzed emotional data.

[0392] Step 6:

[0393] The server uses real-time sentiment data as input and dynamically adjusts questions as needed. If excessive stress or discomfort is detected, the difficulty and format of the questions are gently modified. The output is the modified questions.

[0394] Step 7:

[0395] The server aggregates and analyzes all response and sentiment data. The aggregation process takes individual user data as input and applies statistical analysis methods to grasp overall trends. The output is a report generated based on the analysis results. This report also includes insights gained using prompt messages.

[0396] 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.

[0397] 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.

[0398] 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.

[0399] [Third Embodiment]

[0400] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0401] 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.

[0402] 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).

[0403] 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.

[0404] 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.

[0405] 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).

[0406] 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.

[0407] 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.

[0408] 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.

[0409] 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.

[0410] 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.

[0411] 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".

[0412] The system according to the present invention includes, as its main functions, keyword extraction using natural language processing, survey item generation by an artificial intelligence agent, optimization using a statistical model, and real-time feedback analysis.

[0413] The server first receives a survey topic from the user and extracts keywords related to that topic using natural language processing technology. This allows for the formulation of appropriate questions that are relevant to the topic, thereby improving the accuracy of the survey.

[0414] Next, the server activates an artificial intelligence agent that automatically generates survey questions based on the extracted keywords. This enables efficient survey creation and significantly reduces the time required for survey preparation.

[0415] The generated survey questions are analyzed by a statistical model maintained by the server, eliminating unnecessary duplication and redundant questions. This improves the quality of the questions and reduces the burden on respondents.

[0416] Next, the server delivers an optimized survey to the terminal. The terminal displays the received survey to the user and collects the user's responses. Once the user completes the survey, the terminal immediately sends the data to the server, which analyzes the feedback in real time.

[0417] Based on this feedback, the server aggregates the results and generates a report. Finally, the user can review this report and gain insights to help with their next investigation.

[0418] As a concrete example, consider a case where a company uses this system to conduct market research for a new product. The server sets "health foods" as the theme and extracts related keywords. Based on these, questionnaire items are generated and distributed to terminals for customer interviews at stores. The terminals send customer responses to the server, which analyzes the data in real time and aggregates the results. Through this series of processes, companies can quickly grasp market demand and formulate product strategies.

[0419] The following describes the processing flow.

[0420] Step 1:

[0421] The server receives research topics from users and extracts keywords based on those topics using natural language processing technology. This allows for the identification of specific keywords suitable for the research.

[0422] Step 2:

[0423] The server uses the extracted keywords to activate artificial intelligence agents, which automatically generate survey questions. At this stage, each agent designs questions from diverse perspectives based on the keywords.

[0424] Step 3:

[0425] The server analyzes the generated survey items using a statistical model, and an optimization engine automatically removes duplicate and redundant questions. This completes the statistically optimized set of questions.

[0426] Step 4:

[0427] The server delivers an optimized survey to the terminal. The terminal receives it and prepares to display the survey to the user using an appropriate interface.

[0428] Step 5:

[0429] The user operates the device and enters their answers to the displayed survey. The device sends the completed answers to the server in real time.

[0430] Step 6:

[0431] The server analyzes the response data sent from the terminals in real time and immediately processes it for aggregation and feedback. Here, it detects overall trends and outliers in the survey and generates analysis results.

[0432] Step 7:

[0433] The server generates a report based on the aggregated analysis results and presents it to the user. The user uses this report to review the survey results and adjust the strategy for the next survey as needed.

[0434] (Example 1)

[0435] 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."

[0436] Traditional survey systems require significant time and effort for extracting theme-based information, creating, optimizing, distributing, and collecting and analyzing responses, highlighting the need for efficient and rapid data processing. Solving this challenge necessitates a new method that seamlessly integrates information extraction and result aggregation.

[0437] 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.

[0438] In this invention, the server includes means for extracting information based on the research theme using natural language processing, means for automatically generating questions based on the extracted information using artificial intelligence, and means for optimizing the generated questions using mathematical models. This makes it possible to conduct research more quickly and efficiently than with conventional methods, and to analyze the opinions obtained immediately.

[0439] "Natural language processing" is a technology that enables computers to understand, analyze, and generate human language.

[0440] A "research theme" is the central subject or topic of a particular survey or study.

[0441] "Information extraction" is the process of extracting necessary or useful information from a specific dataset.

[0442] Artificial intelligence is a technology in which computer systems mimic human intellectual activity and automatically make decisions and solve problems.

[0443] "Automatic question generation" is the process of automatically creating questions for humans to answer using algorithms and models.

[0444] A "mathematical model" is a formalization of real-world phenomena or processes using mathematical expressions.

[0445] "Optimization" is the process of adjusting and improving each element in order to obtain the best results for a specific purpose.

[0446] "Collecting responses" is the process of gathering and recording users' answers to questions.

[0447] "Aggregating results" is the process of analyzing collected data and summarizing it in an easy-to-understand format.

[0448] This invention constructs an efficient research system by combining natural language processing, artificial intelligence, and mathematical models. Specific embodiments of this system are described below.

[0449] The server processes the survey themes received from the user. The server extracts information related to the survey themes using natural language processing. This process utilizes common libraries and models (e.g., open-source natural language processing libraries) as natural language processing techniques. The extracted information is then converted into questions by artificial intelligence. The software used includes common deep learning models and AI frameworks (e.g., widely used generative AI models). These generate questions based on the provided information, and each question is tailored to the user's needs.

[0450] Subsequently, the server optimizes the questions using mathematical models. This optimization process eliminates redundant or redundant questions, ensuring an efficient and effective survey. Common software tools (e.g., computational libraries used for data analysis and optimization) are utilized to perform mathematical calculations and optimization algorithms.

[0451] As a concrete example, consider a case where a company conducts market research for a new product. The server first sets "health foods" as the theme and extracts relevant information. Based on this information, questions such as "reasons for purchasing organic foods" are generated. In this process, the server can use a prompt such as "Generate market research questions on the theme of health foods."

[0452] Optimized questions are delivered to the device, which then presents the questions to the user and sends the collected responses to the server. This allows for real-time analysis and aggregation of results, enabling rapid feedback. Users can also use these results to gain insights that will be useful for future research.

[0453] This configuration provides an efficient and highly accurate research system, enabling rapid market analysis and decision-making support.

[0454] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0455] Step 1:

[0456] The user enters the research topic into the server. For example, if the user wants to conduct market research on "health foods," they would send "health foods" as the topic name to the server. The server receives this input and prepares to proceed to the next process.

[0457] Step 2:

[0458] The server uses natural language processing to extract relevant information from the research topic. Based on the input topic "health foods," it identifies relevant keywords and phrases. This process uses a natural language processing library to analyze text data. The output is a list of keywords such as "organic," "nutrition," and "diet."

[0459] Step 3:

[0460] The server uses a generative AI model to automatically generate questions based on extracted keywords. The server inputs these keywords as prompts into the AI ​​model to generate questions. For example, a question such as "Is organic food an important factor in purchasing decisions?" might be generated. The output is a list of the set of questions used in the survey.

[0461] Step 4:

[0462] The server optimizes the generated questions using mathematical models. This process involves analysis to eliminate duplicate questions and redundant expressions. The input is the initial list of generated questions, and the output is the optimized list of questions. Statistical analysis tools are used in this process.

[0463] Step 5:

[0464] The server delivers optimized questions to the terminal. The terminal prepares to present these questions to the user through its interface. The input is an optimized list of questions, and the output is data in question format displayed on the terminal.

[0465] Step 6:

[0466] The user answers questions via a terminal. Each time the user provides input data for a question, that data is recorded on the terminal. The output is the answer data. The terminal aggregates this data and prepares it for transmission to the server.

[0467] Step 7:

[0468] The terminal sends the collected response data to the server. The input is the user's response data, and the output is in a format that is sent to the server. The server receives this data immediately.

[0469] Step 8:

[0470] The server analyzes the received response data in real time and aggregates the results. Using data analysis tools, it derives trends and patterns from the collected data. The output is a report summarizing the survey results. Users can analyze this report and use the information to guide their next actions.

[0471] (Application Example 1)

[0472] 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."

[0473] Current survey systems and content distribution services struggle to grasp user interests and feedback in real time, and to generate appropriate survey questions or suggest individually optimized content based on that information. As a result, there is a lack of timely information delivery that is tailored to user interests, and an improvement in the user experience is needed.

[0474] 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.

[0475] In this invention, the server includes means for extracting keywords based on a survey theme using natural language processing, means for automatically generating survey items based on the extracted keywords using an artificial intelligence agent, and means for analyzing user feedback and generating information for recommending personalized content. This enables the provision of personalized surveys and content to users in real time.

[0476] "Natural language processing" is the technology that enables computers to understand and generate human language.

[0477] An "artificial intelligence agent" is a system that autonomously performs tasks using machine learning algorithms.

[0478] A "statistical model" is a mathematical model used in data analysis to extract patterns and make predictions.

[0479] "Feedback" refers to opinions and reactions from users, and is information used to improve the system.

[0480] "Personalized content" refers to information and services that are customized based on the individual user's characteristics and preferences.

[0481] "Target audience" refers to individuals or groups who receive surveys or content distribution.

[0482] The system realizing this invention combines multiple functions to perform highly accurate and efficient information gathering and content distribution. The server first uses the OpenAI API, a natural language processing library, to extract keywords related to user feedback and themes. Based on the keywords extracted in this process, an artificial intelligence agent generates optimal survey items and content. The server then utilizes a constructed statistical model to further optimize the generated items and content.

[0483] The device provides users with optimized surveys and content, and collects feedback in real time. User feedback is immediately sent to a server for analysis. The server uses the collected data to analyze the content and aggregate the results to provide valuable information to the user. For example, in a content distribution service, if a user shows a strong interest in action movies, the data can be analyzed in real time, and movies that match the user's preferences can be recommended.

[0484] In this way, the server dynamically updates content and surveys based on the collected feedback data. This process enables the system to provide services that accurately respond to the user's interests and preferences. For example, by entering the following prompt message, "Extract keywords that will pique interest from the feedback below: The user is interested in action movies featuring strong female characters," the system can accurately extract the target keywords.

[0485] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0486] Step 1:

[0487] The server receives research topics and feedback from users. Using OpenAI's natural language processing API, it extracts relevant keywords from this input text data. This process outputs the input data as a list of keywords based on important topics.

[0488] Step 2:

[0489] The server uses an artificial intelligence agent to generate appropriate survey questions and content recommendation information based on the extracted keywords. In this process, a data model is built based on the keywords, and this is output as survey questions and content profiles.

[0490] Step 3:

[0491] The server applies statistical models to optimize the generated surveys and content. This involves data calculations such as duplicate removal and content prioritization. The input consists of survey items and content profiles, which are then output in an optimized form.

[0492] Step 4:

[0493] The device delivers optimized survey questions and content to the user, displaying them in a visually effective format on the user's device screen. The user answers the survey and consumes the content. The device records this behavior and responses as data.

[0494] Step 5:

[0495] The terminal sends feedback data collected from the user to the server. This data becomes input, and the server begins analysis in real time. Through the analysis, user interests and trends are identified, and the results are output in a visualized report format.

[0496] Step 6:

[0497] Based on the analysis results, the server dynamically modifies its content and survey strategies, updating the system to provide more suitable content and surveys in future deliveries. This process ensures that information is provided that meets the needs of the target users.

[0498] 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.

[0499] This invention is a system that combines natural language processing and artificial intelligence, and by incorporating an emotion engine, it includes a function to analyze user emotions in surveys. In addition to generating, optimizing, distributing, and aggregating typical survey items, this system grasps the user's emotional state in real time, improving the accuracy of survey content and feedback.

[0500] The server receives survey themes from users and extracts relevant keywords using natural language processing. This, combined with user sentiment data detected by the sentiment engine, enables the design of more accurate questions.

[0501] The artificial intelligence agent generates survey questions based on extracted keywords and user sentiment data. At this point, the sentiment engine analyzes the user's emotions and helps select appropriate question formats and content. This feature proactively adjusts questions that might potentially evoke emotional responses from the user.

[0502] The terminal displays the questionnaire sent from the server to the user, and an emotion engine analyzes the user's facial expressions and voice tone while they are answering the questionnaire. This data is sent back to the server and used to adjust the questionnaire questions in real time.

[0503] Based on user sentiment data, the server adds emotional insights to the survey results and generates an improved report. This report also includes an analysis of the emotions users were experiencing, providing a new perspective on interpreting the survey results.

[0504] For example, in market research for a new product, when conducting a survey on product features that are likely to cause dissatisfaction, this system can be used to detect and adjust questions that users find unpleasant in real time. In this way, the present invention provides new value by utilizing sentiment analysis to improve the accuracy of surveys and user satisfaction.

[0505] The following describes the processing flow.

[0506] Step 1:

[0507] The server receives survey themes from users and extracts keywords related to those themes using natural language processing techniques. These extracted keywords are later used to generate survey questions.

[0508] Step 2:

[0509] The server activates an emotion engine and analyzes the emotional nuances associated with the extracted keywords. Based on this analysis, an artificial intelligence agent generates survey questions. Emotionally sensitive question design takes place at this stage.

[0510] Step 3:

[0511] The server optimizes the generated survey questions using statistical models, eliminating duplicates and questions that might burden the user.

[0512] Step 4:

[0513] The server delivers an optimized survey to the terminal. The terminal receives it and prepares an interface to display the survey to the user.

[0514] Step 5:

[0515] When users answer surveys via their devices, the emotion engine analyzes their facial expressions and voice in real time. This allows the system to understand the user's emotional state.

[0516] Step 6:

[0517] The device sends the analyzed user sentiment data to the server. Based on this sentiment data, the server adjusts the content of the survey questions in real time.

[0518] Step 7:

[0519] The server analyzes the collected response data, combining it with user sentiment data, and aggregates the results. This generates a research report that includes deeper insights.

[0520] Step 8:

[0521] Users can review survey results reports sent from the server and use them to inform their decision-making by gaining emotion-based insights along with the survey findings.

[0522] (Example 2)

[0523] 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."

[0524] Traditional survey methods struggle to analyze respondents' emotions in real time, resulting in survey results lacking crucial emotional insights. Furthermore, the inability to adjust questions in real time to reflect respondents' feelings carries the risk of inappropriate or offensive questions. To address these challenges, a more emotionally sensitive and responsive survey system is needed.

[0525] 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.

[0526] In this invention, the server includes means for extracting keywords based on the survey theme using natural language processing, means for automatically generating questionnaire items based on the extracted keywords and sentiment analysis data using an artificial intelligence agent, and means for collecting user sentiment data in real time using a sentiment analysis engine and reflecting it in the questionnaire items. As a result, the questionnaire is dynamically adjusted according to the emotions of the respondents, enabling the provision of highly accurate survey results that include emotional insights.

[0527] "Natural language processing" is a technology that enables computers to understand, analyze, and generate human language, and it is a method for extracting keywords and interpreting text.

[0528] An "artificial intelligence agent" is a program that automatically performs specific tasks based on input information, and is a technology that plays a role in generating survey questions.

[0529] An "emotion analysis engine" is a technology that analyzes a user's emotional data from their voice tone and facial expressions, and uses the results as feedback.

[0530] "Information display device" refers to any device that presents questionnaires to subjects and allows for user interaction, including mobile devices and computer screens.

[0531] "Response information" refers to all data, including facial expressions, tone of voice, and text responses, that respondents exhibit while answering questionnaires.

[0532] "Emotional insight" refers to the knowledge gained from collected emotional data, and is information used to evaluate the potential emotions and attitudes of the subjects.

[0533] This invention is a survey system that utilizes natural language processing technology and artificial intelligence, and has the function of analyzing the user's emotions in real time by combining it with an emotion analysis engine. The invention includes the following specific configurations in order to carry it out.

[0534] The server receives survey themes entered by the user. It then uses a natural language processing library to extract relevant keywords. Specifically, NLTK and BERT models are expected to be used as natural language libraries. Next, a sentiment analysis engine is utilized to analyze the user's past feedback and real-time response data. Based on this, an artificial intelligence agent automatically generates survey questions using a generative AI model. For example, the GPT series would likely be used as this generative AI model.

[0535] The terminal provides an interface that displays the questionnaire sent from the server to the user. Here, the camera and microphone are used to analyze the user's facial expressions and voice tone in real time, collecting user emotion data. The collected data is then returned to the server and used to dynamically adjust the questionnaire content.

[0536] As a concrete example, when conducting market research for a new product, if the questions include product features that are likely to cause dissatisfaction, the system can instantly revise the questions if it detects negative user sentiment. For instance, the question "What are the drawbacks of this product?" could be changed to "What improvements would you like to see in this product?"

[0537] An example of a prompt might be, "Please show me how to generate survey questions based on user sentiment data and adjust them in real time." This prompt is expected to prompt the generation AI model to provide specific survey design and adjustment methods.

[0538] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0539] Step 1:

[0540] The server receives research themes entered by users. Based on the entered research themes, it extracts relevant keywords using natural language processing libraries. Specifically, it performs text analysis using Python's NLTK and BERT models and outputs important words and phrases related to the theme as a list.

[0541] Step 2:

[0542] The server retrieves relevant sentiment data through its sentiment analysis engine. During this process, it analyzes the user's past feedback and real-time text input to determine their emotions. It estimates the user's emotional state from the input data and outputs it as an emotion value. This emotion value is then used to generate subsequent questions.

[0543] Step 3:

[0544] The artificial intelligence agent receives keywords and sentiment values ​​extracted by the server as input. Using a generative AI model (e.g., the GPT series), it automatically generates survey questions based on this data. The survey questions are generated with sentiment values ​​in mind and output in a user-friendly format.

[0545] Step 4:

[0546] The device displays the generated questionnaire to the user. While the questionnaire is displayed, it records the user's response process and uses the camera and microphone to analyze the user's facial expressions and voice tone in real time. The data obtained from this analysis is sent to an emotion analysis engine, which outputs the user's emotional response as an analysis result.

[0547] Step 5:

[0548] The server receives the sentiment data sent from the device and dynamically adjusts the survey questions. If the user's sentiment shifts to negative, the server uses this information to change or rearrange the questions and outputs the revised survey content back to the device.

[0549] Step 6:

[0550] The server ultimately analyzes the survey results based on all collected user data (response information and sentiment data) and generates a detailed report. This report includes extensive analysis results, including sentiment insights, and is provided as the final output.

[0551] (Application Example 2)

[0552] 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."

[0553] User feedback on online platforms and services is crucial for improving products and services. However, traditional survey systems often use fixed questions that don't consider user emotions, which can compromise user satisfaction and the accuracy of feedback. In particular, the reliability of feedback decreases when users cannot accurately reflect their emotions. Against this backdrop, there is a need for methods that can identify users' emotional states in real time and optimize questions based on that information to obtain more accurate and useful feedback.

[0554] 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.

[0555] In this invention, the server includes means for extracting keywords based on the research theme using natural language processing, means for automatically generating question items based on the extracted keywords using an artificial intelligence agent, means for analyzing the emotional state of the subject in real time, and means for dynamically adjusting the question items based on the emotional state. This makes it possible to optimize the question items while taking into account the user's real-time emotions, thereby improving the accuracy of feedback and user satisfaction.

[0556] "Natural language processing" is a technology that uses computers to analyze, understand, and generate human language.

[0557] An "artificial intelligence agent" is a program or system that operates autonomously and makes decisions based on information from its environment.

[0558] A "statistical model" is a mathematical model created to analyze the characteristics of data and to make predictions or inferences.

[0559] "Target audience" refers to the people who answer questions in a survey or questionnaire.

[0560] "Emotional state" refers to data that indicates a user's subjective mood and feelings, and is primarily measured through facial expressions and voice tone.

[0561] "Dynamic adjustment" refers to changing the content in real time according to data and circumstances.

[0562] "Questionnaire items" refer to the specific questions presented to respondents in a survey or questionnaire.

[0563] "Feedback" is a general term for the responses, opinions, and experiences obtained from the target audience, and is used to improve products and services.

[0564] The system that realizes the present invention mainly consists of a server, a terminal, and a user interface.

[0565] When a research topic is given, the server extracts relevant keywords using natural language processing algorithms. The server can utilize Google's Natural Language API and IBM Watson's NLP tools for this process. Furthermore, an artificial intelligence agent automatically generates survey questions based on the extracted keywords, using generative AI models such as OpenAI's GPT series. These questions are optimized using statistical models to provide the most appropriate content for each participant.

[0566] The device displays generated questions to the user and receives the user's responses. During this process, the device analyzes the user's emotional state in real time and sends captured facial expression data and voice tone to a server in the cloud. Emotion analysis uses facial recognition by Amazon Rekognition and voice analysis by Google Cloud Speech-to-Text.

[0567] Users answer questions using smartphones or tablets. The system takes the user's emotional state into consideration and dynamically adjusts the questions as needed. For example, if the system detects that the user is stressed, it can replace the question with an easier one.

[0568] Ultimately, the server aggregates and analyzes all response and sentiment data. This allows for a more accurate understanding of feedback on products and services, which is then output as a report. This report includes sentiment insights that can be used to improve product development and marketing strategies.

[0569] For example, by generating prompts such as, "What are your feelings about this product? Please tell us specifically what you would like to see improved," it becomes possible to ask questions that delve deeper into the user's subjective opinions.

[0570] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0571] Step 1:

[0572] The server receives a research topic. Given the research topic as input, it analyzes it using a natural language processing tool and extracts relevant keywords. It then uses Google's Natural Language API to break down the text and identify the main topics. The output is a set of keywords used in the next step.

[0573] Step 2:

[0574] The server processes keywords as input using an artificial intelligence agent and automatically generates question items. It utilizes OpenAI's generative AI model to form grammatically correct question sentences. This process transforms the input keywords into context-appropriate question sentences. The output is the generated question items.

[0575] Step 3:

[0576] The server optimizes the questionnaire using a statistical model. It takes the generated questionnaire as input and evaluates it using a model built from past survey data and user behavior. It predicts the effectiveness of the questions and adjusts the content to maximize user engagement. The output is the optimized questionnaire.

[0577] Step 4:

[0578] The device displays optimized questionnaire items to the user. This constitutes the actual survey. The user answers the questions and sends the input data to the device. The output is the user's response data.

[0579] Step 5:

[0580] The device measures the user's emotional state in real time during the response process. It uses a camera and microphone to perform facial recognition and voice tone analysis, and sends the data to the cloud. The input is the user's video and audio, and the output is the analyzed emotional data.

[0581] Step 6:

[0582] The server uses real-time sentiment data as input and dynamically adjusts questions as needed. If excessive stress or discomfort is detected, the difficulty and format of the questions are gently modified. The output is the modified questions.

[0583] Step 7:

[0584] The server aggregates and analyzes all response and sentiment data. The aggregation process takes individual user data as input and applies statistical analysis methods to grasp overall trends. The output is a report generated based on the analysis results. This report also includes insights gained using prompt messages.

[0585] 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.

[0586] 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.

[0587] 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.

[0588] [Fourth Embodiment]

[0589] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0590] 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.

[0591] 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).

[0592] 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.

[0593] 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.

[0594] 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).

[0595] 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.

[0596] 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.

[0597] 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.

[0598] 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.

[0599] 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.

[0600] 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.

[0601] 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".

[0602] The system according to the present invention includes, as its main functions, keyword extraction using natural language processing, survey item generation by an artificial intelligence agent, optimization using a statistical model, and real-time feedback analysis.

[0603] The server first receives a survey topic from the user and extracts keywords related to that topic using natural language processing technology. This allows for the formulation of appropriate questions that are relevant to the topic, thereby improving the accuracy of the survey.

[0604] Next, the server activates an artificial intelligence agent that automatically generates survey questions based on the extracted keywords. This enables efficient survey creation and significantly reduces the time required for survey preparation.

[0605] The generated survey questions are analyzed by a statistical model maintained by the server, eliminating unnecessary duplication and redundant questions. This improves the quality of the questions and reduces the burden on respondents.

[0606] Next, the server delivers an optimized survey to the terminal. The terminal displays the received survey to the user and collects the user's responses. Once the user completes the survey, the terminal immediately sends the data to the server, which analyzes the feedback in real time.

[0607] Based on this feedback, the server aggregates the results and generates a report. Finally, the user can review this report and gain insights to help with their next investigation.

[0608] As a concrete example, consider a case where a company uses this system to conduct market research for a new product. The server sets "health foods" as the theme and extracts related keywords. Based on these, questionnaire items are generated and distributed to terminals for customer interviews at stores. The terminals send customer responses to the server, which analyzes the data in real time and aggregates the results. Through this series of processes, companies can quickly grasp market demand and formulate product strategies.

[0609] The following describes the processing flow.

[0610] Step 1:

[0611] The server receives research topics from users and extracts keywords based on those topics using natural language processing technology. This allows for the identification of specific keywords suitable for the research.

[0612] Step 2:

[0613] The server uses the extracted keywords to activate artificial intelligence agents, which automatically generate survey questions. At this stage, each agent designs questions from diverse perspectives based on the keywords.

[0614] Step 3:

[0615] The server analyzes the generated survey items using a statistical model, and an optimization engine automatically removes duplicate and redundant questions. This completes the statistically optimized set of questions.

[0616] Step 4:

[0617] The server delivers an optimized survey to the terminal. The terminal receives it and prepares to display the survey to the user using an appropriate interface.

[0618] Step 5:

[0619] The user operates the device and enters their answers to the displayed survey. The device sends the completed answers to the server in real time.

[0620] Step 6:

[0621] The server analyzes the response data sent from the terminals in real time and immediately processes it for aggregation and feedback. Here, it detects overall trends and outliers in the survey and generates analysis results.

[0622] Step 7:

[0623] The server generates a report based on the aggregated analysis results and presents it to the user. The user uses this report to review the survey results and adjust the strategy for the next survey as needed.

[0624] (Example 1)

[0625] 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".

[0626] Traditional survey systems require significant time and effort for extracting theme-based information, creating, optimizing, distributing, and collecting and analyzing responses, highlighting the need for efficient and rapid data processing. Solving this challenge necessitates a new method that seamlessly integrates information extraction and result aggregation.

[0627] 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.

[0628] In this invention, the server includes means for extracting information based on the research theme using natural language processing, means for automatically generating questions based on the extracted information using artificial intelligence, and means for optimizing the generated questions using mathematical models. This makes it possible to conduct research more quickly and efficiently than with conventional methods, and to analyze the opinions obtained immediately.

[0629] "Natural language processing" is a technology that enables computers to understand, analyze, and generate human language.

[0630] A "research theme" is the central subject or topic of a particular survey or study.

[0631] "Information extraction" is the process of extracting necessary or useful information from a specific dataset.

[0632] Artificial intelligence is a technology in which computer systems mimic human intellectual activity and automatically make decisions and solve problems.

[0633] "Automatic question generation" is the process of automatically creating questions for humans to answer using algorithms and models.

[0634] A "mathematical model" is a formalization of real-world phenomena or processes using mathematical expressions.

[0635] "Optimization" is the process of adjusting and improving each element in order to obtain the best results for a specific purpose.

[0636] "Collecting responses" is the process of gathering and recording users' answers to questions.

[0637] "Aggregating results" is the process of analyzing collected data and summarizing it in an easy-to-understand format.

[0638] This invention constructs an efficient research system by combining natural language processing, artificial intelligence, and mathematical models. Specific embodiments of this system are described below.

[0639] The server processes the survey themes received from the user. The server extracts information related to the survey themes using natural language processing. This process utilizes common libraries and models (e.g., open-source natural language processing libraries) as natural language processing techniques. The extracted information is then converted into questions by artificial intelligence. The software used includes common deep learning models and AI frameworks (e.g., widely used generative AI models). These generate questions based on the provided information, and each question is tailored to the user's needs.

[0640] Subsequently, the server optimizes the questions using mathematical models. This optimization process eliminates redundant or redundant questions, ensuring an efficient and effective survey. Common software tools (e.g., computational libraries used for data analysis and optimization) are utilized to perform mathematical calculations and optimization algorithms.

[0641] As a concrete example, consider a case where a company conducts market research for a new product. The server first sets "health foods" as the theme and extracts relevant information. Based on this information, questions such as "reasons for purchasing organic foods" are generated. In this process, the server can use a prompt such as "Generate market research questions on the theme of health foods."

[0642] Optimized questions are delivered to the device, which then presents the questions to the user and sends the collected responses to the server. This allows for real-time analysis and aggregation of results, enabling rapid feedback. Users can also use these results to gain insights that will be useful for future research.

[0643] This configuration provides an efficient and highly accurate research system, enabling rapid market analysis and decision-making support.

[0644] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0645] Step 1:

[0646] The user enters the research topic into the server. For example, if the user wants to conduct market research on "health foods," they would send "health foods" as the topic name to the server. The server receives this input and prepares to proceed to the next process.

[0647] Step 2:

[0648] The server uses natural language processing to extract relevant information from the research topic. Based on the input topic "health foods," it identifies relevant keywords and phrases. This process uses a natural language processing library to analyze text data. The output is a list of keywords such as "organic," "nutrition," and "diet."

[0649] Step 3:

[0650] The server uses a generative AI model to automatically generate questions based on extracted keywords. The server inputs these keywords as prompts into the AI ​​model to generate questions. For example, a question such as "Is organic food an important factor in purchasing decisions?" might be generated. The output is a list of the set of questions used in the survey.

[0651] Step 4:

[0652] The server optimizes the generated questions using mathematical models. This process involves analysis to eliminate duplicate questions and redundant expressions. The input is the initial list of generated questions, and the output is the optimized list of questions. Statistical analysis tools are used in this process.

[0653] Step 5:

[0654] The server delivers optimized questions to the terminal. The terminal prepares to present these questions to the user through its interface. The input is an optimized list of questions, and the output is data in question format displayed on the terminal.

[0655] Step 6:

[0656] The user answers questions via a terminal. Each time the user provides input data for a question, that data is recorded on the terminal. The output is the answer data. The terminal aggregates this data and prepares it for transmission to the server.

[0657] Step 7:

[0658] The terminal sends the collected response data to the server. The input is the user's response data, and the output is in a format that is sent to the server. The server receives this data immediately.

[0659] Step 8:

[0660] The server analyzes the received response data in real time and aggregates the results. Using data analysis tools, it derives trends and patterns from the collected data. The output is a report summarizing the survey results. Users can analyze this report and use the information to guide their next actions.

[0661] (Application Example 1)

[0662] 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".

[0663] Current survey systems and content distribution services struggle to grasp user interests and feedback in real time, and to generate appropriate survey questions or suggest individually optimized content based on that information. As a result, there is a lack of timely information delivery that is tailored to user interests, and an improvement in the user experience is needed.

[0664] 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.

[0665] In this invention, the server includes means for extracting keywords based on a survey theme using natural language processing, means for automatically generating survey items based on the extracted keywords using an artificial intelligence agent, and means for analyzing user feedback and generating information for recommending personalized content. This enables the provision of personalized surveys and content to users in real time.

[0666] "Natural language processing" is the technology that enables computers to understand and generate human language.

[0667] An "artificial intelligence agent" is a system that autonomously performs tasks using machine learning algorithms.

[0668] A "statistical model" is a mathematical model used in data analysis to extract patterns and make predictions.

[0669] "Feedback" refers to opinions and reactions from users, and is information used to improve the system.

[0670] "Personalized content" refers to information and services that are customized based on the individual user's characteristics and preferences.

[0671] "Target audience" refers to individuals or groups who receive surveys or content distribution.

[0672] The system realizing this invention combines multiple functions to perform highly accurate and efficient information gathering and content distribution. The server first uses the OpenAI API, a natural language processing library, to extract keywords related to user feedback and themes. Based on the keywords extracted in this process, an artificial intelligence agent generates optimal survey items and content. The server then utilizes a constructed statistical model to further optimize the generated items and content.

[0673] The device provides users with optimized surveys and content, and collects feedback in real time. User feedback is immediately sent to a server for analysis. The server uses the collected data to analyze the content and aggregate the results to provide valuable information to the user. For example, in a content distribution service, if a user shows a strong interest in action movies, the data can be analyzed in real time, and movies that match the user's preferences can be recommended.

[0674] In this way, the server dynamically updates content and surveys based on the collected feedback data. This process enables the system to provide services that accurately respond to the user's interests and preferences. For example, by entering the following prompt message, "Extract keywords that will pique interest from the feedback below: The user is interested in action movies featuring strong female characters," the system can accurately extract the target keywords.

[0675] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0676] Step 1:

[0677] The server receives research topics and feedback from users. Using OpenAI's natural language processing API, it extracts relevant keywords from this input text data. This process outputs the input data as a list of keywords based on important topics.

[0678] Step 2:

[0679] The server uses an artificial intelligence agent to generate appropriate survey questions and content recommendation information based on the extracted keywords. In this process, a data model is built based on the keywords, and this is output as survey questions and content profiles.

[0680] Step 3:

[0681] The server applies statistical models to optimize the generated surveys and content. This involves data calculations such as duplicate removal and content prioritization. The input consists of survey items and content profiles, which are then output in an optimized form.

[0682] Step 4:

[0683] The device delivers optimized survey questions and content to the user, displaying them in a visually effective format on the user's device screen. The user answers the survey and consumes the content. The device records this behavior and responses as data.

[0684] Step 5:

[0685] The terminal sends feedback data collected from the user to the server. This data becomes input, and the server begins analysis in real time. Through the analysis, user interests and trends are identified, and the results are output in a visualized report format.

[0686] Step 6:

[0687] Based on the analysis results, the server dynamically modifies its content and survey strategies, updating the system to provide more suitable content and surveys in future deliveries. This process ensures that information is provided that meets the needs of the target users.

[0688] 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.

[0689] This invention is a system that combines natural language processing and artificial intelligence, and by incorporating an emotion engine, it includes a function to analyze user emotions in surveys. In addition to generating, optimizing, distributing, and aggregating typical survey items, this system grasps the user's emotional state in real time, improving the accuracy of survey content and feedback.

[0690] The server receives survey themes from users and extracts relevant keywords using natural language processing. This, combined with user sentiment data detected by the sentiment engine, enables the design of more accurate questions.

[0691] The artificial intelligence agent generates survey questions based on extracted keywords and user sentiment data. At this point, the sentiment engine analyzes the user's emotions and helps select appropriate question formats and content. This feature proactively adjusts questions that might potentially evoke emotional responses from the user.

[0692] The terminal displays the questionnaire sent from the server to the user, and an emotion engine analyzes the user's facial expressions and voice tone while they are answering the questionnaire. This data is sent back to the server and used to adjust the questionnaire questions in real time.

[0693] Based on user sentiment data, the server adds emotional insights to the survey results and generates an improved report. This report also includes an analysis of the emotions users were experiencing, providing a new perspective on interpreting the survey results.

[0694] For example, in market research for a new product, when conducting a survey on product features that are likely to cause dissatisfaction, this system can be used to detect and adjust questions that users find unpleasant in real time. In this way, the present invention provides new value by utilizing sentiment analysis to improve the accuracy of surveys and user satisfaction.

[0695] The following describes the processing flow.

[0696] Step 1:

[0697] The server receives survey themes from users and extracts keywords related to those themes using natural language processing techniques. These extracted keywords are later used to generate survey questions.

[0698] Step 2:

[0699] The server activates an emotion engine and analyzes the emotional nuances associated with the extracted keywords. Based on this analysis, an artificial intelligence agent generates survey questions. Emotionally sensitive question design takes place at this stage.

[0700] Step 3:

[0701] The server optimizes the generated survey questions using statistical models, eliminating duplicates and questions that might burden the user.

[0702] Step 4:

[0703] The server delivers an optimized survey to the terminal. The terminal receives it and prepares an interface to display the survey to the user.

[0704] Step 5:

[0705] When users answer surveys via their devices, the emotion engine analyzes their facial expressions and voice in real time. This allows the system to understand the user's emotional state.

[0706] Step 6:

[0707] The device sends the analyzed user sentiment data to the server. Based on this sentiment data, the server adjusts the content of the survey questions in real time.

[0708] Step 7:

[0709] The server analyzes the collected response data, combining it with user sentiment data, and aggregates the results. This generates a research report that includes deeper insights.

[0710] Step 8:

[0711] Users can review survey results reports sent from the server and use them to inform their decision-making by gaining emotion-based insights along with the survey findings.

[0712] (Example 2)

[0713] 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".

[0714] Traditional survey methods struggle to analyze respondents' emotions in real time, resulting in survey results lacking crucial emotional insights. Furthermore, the inability to adjust questions in real time to reflect respondents' feelings carries the risk of inappropriate or offensive questions. To address these challenges, a more emotionally sensitive and responsive survey system is needed.

[0715] 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.

[0716] In this invention, the server includes means for extracting keywords based on the survey theme using natural language processing, means for automatically generating questionnaire items based on the extracted keywords and sentiment analysis data using an artificial intelligence agent, and means for collecting user sentiment data in real time using a sentiment analysis engine and reflecting it in the questionnaire items. As a result, the questionnaire is dynamically adjusted according to the emotions of the respondents, enabling the provision of highly accurate survey results that include emotional insights.

[0717] "Natural language processing" is a technology that enables computers to understand, analyze, and generate human language, and it is a method for extracting keywords and interpreting text.

[0718] An "artificial intelligence agent" is a program that automatically performs specific tasks based on input information, and is a technology that plays a role in generating survey questions.

[0719] An "emotion analysis engine" is a technology that analyzes a user's emotional data from their voice tone and facial expressions, and uses the results as feedback.

[0720] "Information display device" refers to any device that presents questionnaires to subjects and allows for user interaction, including mobile devices and computer screens.

[0721] "Response information" refers to all data, including facial expressions, tone of voice, and text responses, that respondents exhibit while answering questionnaires.

[0722] "Emotional insight" refers to the knowledge gained from collected emotional data, and is information used to evaluate the potential emotions and attitudes of the subjects.

[0723] This invention is a survey system that utilizes natural language processing technology and artificial intelligence, and has the function of analyzing the user's emotions in real time by combining it with an emotion analysis engine. The invention includes the following specific configurations in order to carry it out.

[0724] The server receives survey themes entered by the user. It then uses a natural language processing library to extract relevant keywords. Specifically, NLTK and BERT models are expected to be used as natural language libraries. Next, a sentiment analysis engine is utilized to analyze the user's past feedback and real-time response data. Based on this, an artificial intelligence agent automatically generates survey questions using a generative AI model. For example, the GPT series would likely be used as this generative AI model.

[0725] The terminal provides an interface that displays the questionnaire sent from the server to the user. Here, the camera and microphone are used to analyze the user's facial expressions and voice tone in real time, collecting user emotion data. The collected data is then returned to the server and used to dynamically adjust the questionnaire content.

[0726] As a concrete example, when conducting market research for a new product, if the questions include product features that are likely to cause dissatisfaction, the system can instantly revise the questions if it detects negative user sentiment. For instance, the question "What are the drawbacks of this product?" could be changed to "What improvements would you like to see in this product?"

[0727] An example of a prompt might be, "Please show me how to generate survey questions based on user sentiment data and adjust them in real time." This prompt is expected to prompt the generation AI model to provide specific survey design and adjustment methods.

[0728] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0729] Step 1:

[0730] The server receives research themes entered by users. Based on the entered research themes, it extracts relevant keywords using natural language processing libraries. Specifically, it performs text analysis using Python's NLTK and BERT models and outputs important words and phrases related to the theme as a list.

[0731] Step 2:

[0732] The server retrieves relevant sentiment data through its sentiment analysis engine. During this process, it analyzes the user's past feedback and real-time text input to determine their emotions. It estimates the user's emotional state from the input data and outputs it as an emotion value. This emotion value is then used to generate subsequent questions.

[0733] Step 3:

[0734] The artificial intelligence agent receives keywords and sentiment values ​​extracted by the server as input. Using a generative AI model (e.g., the GPT series), it automatically generates survey questions based on this data. The survey questions are generated with sentiment values ​​in mind and output in a user-friendly format.

[0735] Step 4:

[0736] The device displays the generated questionnaire to the user. While the questionnaire is displayed, it records the user's response process and uses the camera and microphone to analyze the user's facial expressions and voice tone in real time. The data obtained from this analysis is sent to an emotion analysis engine, which outputs the user's emotional response as an analysis result.

[0737] Step 5:

[0738] The server receives the sentiment data sent from the device and dynamically adjusts the survey questions. If the user's sentiment shifts to negative, the server uses this information to change or rearrange the questions and outputs the revised survey content back to the device.

[0739] Step 6:

[0740] The server ultimately analyzes the survey results based on all collected user data (response information and sentiment data) and generates a detailed report. This report includes extensive analysis results, including sentiment insights, and is provided as the final output.

[0741] (Application Example 2)

[0742] 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".

[0743] User feedback on online platforms and services is crucial for improving products and services. However, traditional survey systems often use fixed questions that don't consider user emotions, which can compromise user satisfaction and the accuracy of feedback. In particular, the reliability of feedback decreases when users cannot accurately reflect their emotions. Against this backdrop, there is a need for methods that can identify users' emotional states in real time and optimize questions based on that information to obtain more accurate and useful feedback.

[0744] 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.

[0745] In this invention, the server includes means for extracting keywords based on the research theme using natural language processing, means for automatically generating question items based on the extracted keywords using an artificial intelligence agent, means for analyzing the emotional state of the subject in real time, and means for dynamically adjusting the question items based on the emotional state. This makes it possible to optimize the question items while taking into account the user's real-time emotions, thereby improving the accuracy of feedback and user satisfaction.

[0746] "Natural language processing" is a technology that uses computers to analyze, understand, and generate human language.

[0747] An "artificial intelligence agent" is a program or system that operates autonomously and makes decisions based on information from its environment.

[0748] A "statistical model" is a mathematical model created to analyze the characteristics of data and to make predictions or inferences.

[0749] "Target audience" refers to the people who answer questions in a survey or questionnaire.

[0750] "Emotional state" refers to data that indicates a user's subjective mood and feelings, and is primarily measured through facial expressions and voice tone.

[0751] "Dynamic adjustment" refers to changing the content in real time according to data and circumstances.

[0752] "Questionnaire items" refer to the specific questions presented to respondents in a survey or questionnaire.

[0753] "Feedback" is a general term for the responses, opinions, and experiences obtained from the target audience, and is used to improve products and services.

[0754] The system that realizes the present invention mainly consists of a server, a terminal, and a user interface.

[0755] When a research topic is given, the server extracts relevant keywords using natural language processing algorithms. The server can utilize Google's Natural Language API and IBM Watson's NLP tools for this process. Furthermore, an artificial intelligence agent automatically generates survey questions based on the extracted keywords, using generative AI models such as OpenAI's GPT series. These questions are optimized using statistical models to provide the most appropriate content for each participant.

[0756] The device displays generated questions to the user and receives the user's responses. During this process, the device analyzes the user's emotional state in real time and sends captured facial expression data and voice tone to a server in the cloud. Emotion analysis uses facial recognition by Amazon Rekognition and voice analysis by Google Cloud Speech-to-Text.

[0757] Users answer questions using smartphones or tablets. The system takes the user's emotional state into consideration and dynamically adjusts the questions as needed. For example, if the system detects that the user is stressed, it can replace the question with an easier one.

[0758] Ultimately, the server aggregates and analyzes all response and sentiment data. This allows for a more accurate understanding of feedback on products and services, which is then output as a report. This report includes sentiment insights that can be used to improve product development and marketing strategies.

[0759] For example, by generating prompts such as, "What are your feelings about this product? Please tell us specifically what you would like to see improved," it becomes possible to ask questions that delve deeper into the user's subjective opinions.

[0760] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0761] Step 1:

[0762] The server receives a research topic. Given the research topic as input, it analyzes it using a natural language processing tool and extracts relevant keywords. It then uses Google's Natural Language API to break down the text and identify the main topics. The output is a set of keywords used in the next step.

[0763] Step 2:

[0764] The server processes keywords as input using an artificial intelligence agent and automatically generates question items. It utilizes OpenAI's generative AI model to form grammatically correct question sentences. This process transforms the input keywords into context-appropriate question sentences. The output is the generated question items.

[0765] Step 3:

[0766] The server optimizes the questionnaire using a statistical model. It takes the generated questionnaire as input and evaluates it using a model built from past survey data and user behavior. It predicts the effectiveness of the questions and adjusts the content to maximize user engagement. The output is the optimized questionnaire.

[0767] Step 4:

[0768] The device displays optimized questionnaire items to the user. This constitutes the actual survey. The user answers the questions and sends the input data to the device. The output is the user's response data.

[0769] Step 5:

[0770] The device measures the user's emotional state in real time during the response process. It uses a camera and microphone to perform facial recognition and voice tone analysis, and sends the data to the cloud. The input is the user's video and audio, and the output is the analyzed emotional data.

[0771] Step 6:

[0772] The server uses real-time sentiment data as input and dynamically adjusts questions as needed. If excessive stress or discomfort is detected, the difficulty and format of the questions are gently modified. The output is the modified questions.

[0773] Step 7:

[0774] The server aggregates and analyzes all response and sentiment data. The aggregation process takes individual user data as input and applies statistical analysis methods to grasp overall trends. The output is a report generated based on the analysis results. This report also includes insights gained using prompt messages.

[0775] 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.

[0776] 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.

[0777] 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.

[0778] 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.

[0779] 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.

[0780] 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.

[0781] 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.

[0782] 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.

[0783] 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."

[0784] 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.

[0785] 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.

[0786] 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.

[0787] 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.

[0788] 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.

[0789] 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.

[0790] 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.

[0791] 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.

[0792] 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.

[0793] 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.

[0794] 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.

[0795] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0796] The following is further disclosed regarding the embodiments described above.

[0797] (Claim 1)

[0798] A method for extracting keywords based on the research theme using natural language processing,

[0799] A means of automatically generating survey items based on keywords extracted by an artificial intelligence agent,

[0800] A method for optimizing survey items generated using statistical models,

[0801] A method for distributing the generated questionnaire to the target audience and collecting responses,

[0802] A means of analyzing the collected response data and aggregating the results,

[0803] A system that includes this.

[0804] (Claim 2)

[0805] The system according to claim 1, which analyzes collected response data in real time.

[0806] (Claim 3)

[0807] The system according to claim 1, which dynamically modifies questionnaire items in response to feedback from the target audience.

[0808] "Example 1"

[0809] (Claim 1)

[0810] A means of extracting information based on the research theme using natural language processing,

[0811] A means of automatically generating questions based on information extracted by artificial intelligence,

[0812] A means of optimizing questions generated using mathematical models,

[0813] A means of distributing generated questions to users and collecting their responses,

[0814] A means of analyzing the collected response information and aggregating the results,

[0815] A system that includes this.

[0816] (Claim 2)

[0817] The system according to claim 1, which immediately analyzes the collected response information.

[0818] (Claim 3)

[0819] The system according to claim 1, which dynamically modifies questions in response to user feedback.

[0820] "Application Example 1"

[0821] (Claim 1)

[0822] A method for extracting keywords based on the research theme using natural language processing,

[0823] A means of automatically generating survey items based on keywords extracted by an artificial intelligence agent,

[0824] A method for optimizing survey items generated using statistical models,

[0825] A means for analyzing user feedback and generating information to recommend personalized content,

[0826] A means of distributing the generated questionnaires and content to the target audience and collecting responses and feedback,

[0827] A means for analyzing collected responses and feedback data and aggregating the results,

[0828] A system that includes this.

[0829] (Claim 2)

[0830] The system according to claim 1, which analyzes collected responses and feedback data in real time.

[0831] (Claim 3)

[0832] The system according to claim 1, which dynamically modifies survey items and content in response to feedback from the target audience.

[0833] "Example 2 of combining an emotion engine"

[0834] (Claim 1)

[0835] A method for extracting keywords based on the research theme using natural language processing,

[0836] A means for automatically generating survey items based on keywords extracted by an artificial intelligence agent and sentiment analysis data,

[0837] A method for collecting user emotional data in real time using an emotion analysis engine and reflecting it in survey questions,

[0838] A means for distributing the generated questionnaire to an information display device and collecting response information,

[0839] A means for analyzing collected reaction information, aggregating the results, and generating a report,

[0840] A system that includes this.

[0841] (Claim 2)

[0842] The system according to claim 1, which analyzes collected response information in real time and adjusts questionnaire items based on the emotional responses of the subjects.

[0843] (Claim 3)

[0844] The system according to claim 1, which dynamically modifies questionnaire items in response to feedback from participants and improves the report using sentiment insight.

[0845] "Application example 2 when combining with an emotional engine"

[0846] (Claim 1)

[0847] A method for extracting keywords based on the research theme using natural language processing,

[0848] A means for automatically generating question items based on keywords extracted by an artificial intelligence agent,

[0849] A means of optimizing questionnaire items generated using statistical models,

[0850] A means of distributing generated questions to the target audience and collecting their responses,

[0851] A means of analyzing the emotional state of the subject in real time,

[0852] A means of dynamically adjusting questionnaire items based on emotional state,

[0853] A means for analyzing collected response data and sentiment data, and for aggregating the results,

[0854] A system that includes this.

[0855] (Claim 2)

[0856] The system according to claim 1, which analyzes collected response data and sentiment data in real time.

[0857] (Claim 3)

[0858] The system according to claim 1, which dynamically modifies the questionnaire items in response to feedback and emotional state from the subject. [Explanation of Symbols]

[0859] 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 method for extracting keywords based on the research theme using natural language processing, A means of automatically generating survey items based on keywords extracted by an artificial intelligence agent, A method for optimizing survey items generated using statistical models, A means for analyzing user feedback and generating information to recommend personalized content, A means of distributing the generated questionnaires and content to the target audience and collecting responses and feedback, A means for analyzing collected responses and feedback data and aggregating the results, A system that includes this.

2. The system according to claim 1, which analyzes collected responses and feedback data in real time.

3. The system according to claim 1, which dynamically modifies survey items and content in response to feedback from the target audience.

Images