system

Abstract

We provide the system. [Solution] An input means for receiving the survey objective and target information from the user, A generation means that automatically generates a questionnaire based on the information received by the input means, A collection method for distributing generated questionnaires to survey subjects and collecting response data, An analytical means for aggregating, analyzing, and visualizing collected data in real time, A generation means that automatically generates a report based on the analysis results obtained by the aforementioned analysis means, A presentation means for displaying data collection and analysis results in real time via a display device, 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 the conventional investigation process, there is a problem that a lot of time and labor are required for the design of questionnaires, data collection, analysis, and report creation. Especially in situations where quick decision-making is necessary, this has become a major obstacle. Also, in order to improve the accuracy of investigations, specialized knowledge is often required, and there is a need for means that anyone can easily conduct effective investigations.

Means for Solving the Problems

[0005] This invention provides a means for automatically generating questionnaires using AI based on research objectives obtained from users. This means enables the rapid design of questionnaires even without specialized knowledge. Furthermore, by aggregating and analyzing collected data in real time and visualizing it immediately, it becomes possible to make rapid decisions based on the research results. In addition, it provides a means for automatically generating reports based on the analysis results, streamlining post-survey processing.

[0006] "Input method" refers to an interface for receiving information such as research objectives and target information from the user.

[0007] "Generation means" refers to a system function that automatically creates questionnaires and reports based on the information received.

[0008] "Methods of data collection" refers to the processes and tools used to distribute questionnaires and collect response data.

[0009] "Analysis tools" refer to functions for aggregating collected data, performing statistical analysis, and visualizing the results.

[0010] "Visualization" refers to the method of displaying analyzed data in the form of graphs, charts, and other visuals so that users can understand it intuitively.

[0011] A "report" is a document generated based on analysis results, and it refers to a systematic record of the findings and proposals of the investigation. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4]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.

Embodiments for Carrying Out the Invention

[0013] 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.

[0014] First, the language used in the following description will be explained.

[0015] In the following embodiments, the numbered 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.

[0016] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. 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.

[0018] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0019] 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."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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".

[0033] This invention relates to a system that efficiently supports survey work, and in particular to a technology that automates a series of processes from questionnaire design to data collection, analysis, and report creation.

[0034] When a user uses this system, they first access a terminal and enter information about the purpose and target of their research. For example, if they want to conduct market research on a new product, they would enter information such as the product's features, target customer base, and expected market information.

[0035] The server receives this input information and uses AI to automatically generate a questionnaire containing the most appropriate questions. This generated questionnaire is sent to the user's device, where the user can review the content and make any necessary modifications. The server then distributes the questionnaire via online platforms or email, reaching the intended target audience.

[0036] As data collection progresses, the server begins to aggregate incoming response data in real time. As more data is gathered, the server uses AI algorithms to perform statistical and trend analyses, displaying the results on the terminal as interactive graphs and charts. For example, the degree of interest in products by age group of the survey participants can be visualized, allowing users to intuitively recognize the trends.

[0037] Ultimately, the server automatically generates a detailed report based on the analysis results. This report includes an overview of the study, key insights, statistics, relevant graphs, and suggestions for future actions. In this way, users can quickly and efficiently make decisions based on the insights derived from the study.

[0038] As a result, this invention significantly streamlines each process of investigation work and supports more accurate and rapid decision-making, and its scope of application is wide.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] Users access the terminal and input information about the purpose and target audience of the research. Specifically, for market research on a new product, they would fill in an overview of the new product, the target customer base, and specific research items.

[0042] Step 2:

[0043] Information entered from the terminal is sent to the server. The server uses an AI algorithm to automatically generate questionnaire questions based on this information. For example, questions about the preferences and needs of the target customer group are generated.

[0044] Step 3:

[0045] The generated questionnaire is sent to the terminal, where the user reviews its contents. If any changes are needed to the content or order of the questions, the user can make corrections through the interface.

[0046] Step 4:

[0047] The server receives the revised questionnaire, and it is then distributed to the survey participants via an online platform or email. During this process, participants are provided with URLs or links that they can access.

[0048] Step 5:

[0049] Once the response data from the survey participants is collected on the server, the server begins aggregating the data in real time. Statistical information for each response is accumulated and immediately organized into a dataset for visualization.

[0050] Step 6:

[0051] The server analyzes aggregated data and performs statistical and trend analysis. It utilizes AI to identify important correlations and patterns, and generates easy-to-understand graphs and charts based on the results.

[0052] Step 7:

[0053] The generated graphs and charts are sent to the device, presenting the analysis results to the user in a visual format. Through this visualization, users can quickly grasp data trends and insights.

[0054] Step 8:

[0055] Finally, the server automatically generates a report summarizing the analysis results. The report includes the background of the study, all key findings, graphs and charts, and actionable suggestions.

[0056] Step 9:

[0057] The generated report is sent to the terminal and provided to the user. The user uses this report to apply the findings to business decision-making and strategy development.

[0058] (Example 1)

[0059] 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."

[0060] Traditional research methods often involved manual processes from questionnaire design to data collection, analysis, and report writing, resulting in significant time and effort. Furthermore, data analysis required highly specialized knowledge, hindering rapid and accurate decision-making. Additionally, determining whether the generated questionnaires were appropriate for the characteristics of the survey participants heavily depended on the experience of the person conducting the research, making efficient research difficult.

[0061] 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.

[0062] In this invention, the server includes an information input means for receiving survey objectives and target information from the user, an information generation means for automatically generating questionnaires using a generative artificial intelligence model and including optimized questions, and an information analysis means for aggregating collected data in real time, performing statistical analysis, and visualizing the results as digital graphs and charts. This automates survey work, improving work efficiency and enabling accurate and rapid decision-making.

[0063] "Information input means" refers to a means of receiving the research objectives and target information from the user, thereby obtaining basic information for the research.

[0064] "Information generation means" refers to a means of automatically generating questionnaires using a generative artificial intelligence model based on acquired information, and creating questionnaires that include optimized questions.

[0065] "Information gathering means" refers to the method of distributing generated questionnaires via digital communication and collecting response data, thereby efficiently collecting information from survey subjects.

[0066] "Information analysis tools" are means of aggregating collected data in real time, performing statistical analysis, and visualizing the results obtained as digital graphs or charts.

[0067] "Information generation means" (report generation) refers to a method that automatically generates a detailed research report based on the analysis results, including suggestions for future actions, and is intended to effectively communicate the research findings.

[0068] To properly implement this invention, it is necessary to construct a system that processes information over a network. Key components include servers, terminals, and software that connects them.

[0069] First, the user accesses the server using a terminal and enters the research objectives and target information. At this stage, the user uses a web browser such as Google Chrome® or Mozilla Firefox on the terminal to enter the necessary information through the user interface.

[0070] The server automatically generates questionnaires using a generative artificial intelligence model based on information received from the user. This process creates optimized questions using a generative AI model such as OpenAI®. For example, if the input prompt is "Generate a detailed questionnaire about fitness earphones targeting people in their 20s," the AI ​​model will generate specific questions that meet that requirement.

[0071] After the questionnaire is generated, the server distributes it via email or Google Forms. This ensures that the questionnaire is efficiently delivered to the survey participants, and as a result, the response data is collected.

[0072] The collected data is aggregated and analyzed in real time on the server. The data is structured using the Python Pandas library and visually displayed as digital graphs and charts using the Matplotlib library. This allows users to intuitively grasp the data trends.

[0073] Ultimately, the server automatically generates a detailed research report based on the analysis results. This report includes statistical analysis results, insights, and suggestions for future actions. Users can then make strategic decisions based on the generated report.

[0074] This system automates each process of the survey, significantly reducing time and effort, and enabling faster and more accurate decision-making.

[0075] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0076] Step 1:

[0077] Users access the server via their devices and input information about the purpose and target of the research. Specifically, users log in to a dedicated form using a web browser and input the research purpose, such as "market research for next-generation smartwatches." The input data is sent to the server and stored by the information input method. The data entered here forms the basis for subsequent processes.

[0078] Step 2:

[0079] The server creates and sends a prompt to the generative AI model based on the information it receives. This prompt might include something like, "Please create a survey about smartwatch features that would be of interest to users in their 20s and 30s." The generative AI model generates the most appropriate survey questions based on the prompt and returns them to the server. This generated list of questions becomes the material needed for the next data collection.

[0080] Step 3:

[0081] The server sends the generated questionnaire back to the terminal and prompts the user for confirmation. The user reviews the questions on the terminal and makes corrections if necessary. For example, the user might look at the generated questions and make a correction such as "Please add a question about smartwatch design." As a result, the revised questionnaire is finalized.

[0082] Step 4:

[0083] The server distributes the finalized questionnaire to respondents via digital distribution methods (e.g., email or online forms). The server selects from various distribution platforms, generates a survey link, and sends it to the respondents. This prepares the server for collecting response data from the survey respondents.

[0084] Step 5:

[0085] The server aggregates the received response data in real time. Using the Python Pandas library, it processes large datasets and performs necessary statistical analysis. For example, it identifies trends, calculates averages, and generates digital graphs and charts based on these results. This visual information serves as output to help users intuitively understand the analysis results.

[0086] Step 6:

[0087] The server generates a detailed report based on the analysis results. The generated report includes statistical insights and future recommendations, and is provided to the user as output. The report is automatically created in Microsoft® Word or Google Docs format and sent to the user via their device. The user can then use this information to make strategic decisions.

[0088] (Application Example 1)

[0089] 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."

[0090] In market research, the process from questionnaire design to data collection, analysis, and reporting is often done manually, resulting in challenges such as time and cost. Furthermore, real-time data visualization and presentation are difficult, often hindering rapid decision-making.

[0091] 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.

[0092] In this invention, the server includes an input means for receiving survey objectives and target information from a user; a generation means for automatically generating questionnaires based on the information received by the input means; a collection means for distributing the generated questionnaires to survey subjects and collecting response data; an analysis means for aggregating, analyzing, and visualizing the collected data in real time; and a presentation means for presenting the analysis results obtained by the analysis means in real time through a display device. This enables increased efficiency in the entire survey process and rapid decision-making through the rapid presentation of data.

[0093] "Input means" refers to a device or software for receiving information from the user regarding the purpose and subject of the investigation.

[0094] "Generation means" refers to a device or software for automatically creating questionnaires based on received information.

[0095] "Collection means" refers to a device or software for providing a generated questionnaire to the survey subjects and collecting response data.

[0096] "Analysis means" refers to a device or software that aggregates and analyzes collected data in real time and visualizes the results.

[0097] "Presentation means" refers to a device or software for presenting the analysis results obtained by the analysis means in real time through a display device.

[0098] In the system that realizes this invention, the user, server, and terminal cooperate to streamline the research process.

[0099] First, the user uses a terminal to input information about the purpose and target of the survey. The terminal is equipped with an interface to smoothly receive input from the user.

[0100] The server receives information sent from the terminal and automatically generates a questionnaire containing appropriate questions using a generative AI model. This generated questionnaire is then sent back to the terminal, where the user can review its contents and edit it as needed.

[0101] Next, the server distributes the generated questionnaires to the target group and collects the response data. This process utilizes online platforms and data transmission methods.

[0102] Once the response data is collected, the server begins aggregating and analyzing the data in real time. During this process, data analysis tools such as Python and R are used to perform statistical processing and trend analysis on the collected data.

[0103] The analysis results, including statistical information and trends, are presented in an interactive visual format. By using engines such as Unity to visualize the analysis results and presenting them through display devices such as smart glasses, users can intuitively understand the content.

[0104] Ultimately, the server automatically generates a detailed report based on the analysis results. This report includes an overview of the study, key insights, statistics, and relevant graphs, allowing users to make informed decisions.

[0105] A concrete example is its use in collecting feedback on a new product at an exhibition and deciding on the product strategy on the spot. In this way, it becomes possible to instantly select and incorporate real-time feedback into marketing activities.

[0106] An example of a prompt is: "Create a questionnaire to collect responses from target customers based on the product features of a new sports shoe. Provide instructions for building an application that analyzes and visualizes the response data in real time."

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

[0108] Step 1:

[0109] The user uses a terminal to input information about the purpose and target of the survey. Here, information about the attributes and purpose of the survey target is entered in text format. This input data is received by the terminal via keyboard or voice interface and sent to the server.

[0110] Step 2:

[0111] The server automatically generates a questionnaire using a generative AI model based on the received information. During this process, algorithms are applied to analyze the entered survey objectives and target information, and to design appropriate questions. The generated questionnaire is created as digital data and sent back to the terminal.

[0112] Step 3:

[0113] The terminal displays the questionnaire received by the user, allowing the user to review its contents and make corrections as needed. The user can examine the questionnaire in detail and use the editing function to modify, add, or delete questions. The edited data is then sent back to the server.

[0114] Step 4:

[0115] The server distributes the finalized questionnaires to participants and collects the response data. In this step, questionnaires are distributed to a wide range of respondents using various online platforms and data transmission methods. The response data entered by participants is stored on the server.

[0116] Step 5:

[0117] The server aggregates and analyzes the collected response data in real time and visualizes it. At this stage, software tools such as Python and R are used to statistically process the data and analyze trends and key insights. The resulting analysis is then formatted as visual data.

[0118] Step 6:

[0119] The server presents visualized analytical data to the user through a display device such as smart glasses. Here, an engine such as Unity is used to display the visual data on the smart glasses, allowing the user to understand the results intuitively in real time.

[0120] Step 7:

[0121] The server ultimately automatically generates a detailed report based on the analysis results and sends it to the user's device. This report includes a summary of the entire study, insights, and recommended actions, enabling the user to make quick decisions based on it.

[0122] 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.

[0123] This invention relates to a survey system incorporating an emotion engine, which provides a more personalized survey process by taking user emotions into consideration from questionnaire design to data collection, analysis, and final report generation.

[0124] When a user uses this system, they first input information about the research objectives and target audience into the terminal. During input, the emotion engine analyzes language patterns and input style to determine the user's emotional state. For example, when conducting market research on a product, the emotion engine recognizes expectations and concerns from the user's descriptions and generates research questions accordingly.

[0125] The server uses the results of this sentiment analysis to automatically generate an optimized questionnaire using AI. For example, if a user expresses strong expectations for a new product, questions will be created to specifically measure those expectations.

[0126] The generated questionnaires are verified by the user and then distributed to the survey participants via an online platform by the server. Once responses to the distributed questionnaires are collected, the server aggregates the data in real time and detects emotional trends from the data collected by the emotion engine.

[0127] The server also considers emotional insights related to the collected data when analyzing the aggregated data, and visualizes data patterns. These visualized graphs and charts are sent to the terminal, allowing the user to visually grasp the analysis results, including emotional trends at that time.

[0128] Ultimately, the server automatically generates a comprehensive report incorporating sentiment analysis. The report presents the background of the research, key analytical findings, and an integrated emotional perspective, enabling richer insights. Specifically, it includes suggestions on how the positive / negative emotions expressed by specific customer segments towards a product might impact marketing strategies.

[0129] In this way, the present invention provides a sensible approach to obtaining more accurate and effective survey results by understanding user emotions and tailoring the entire survey accordingly.

[0130] The following describes the processing flow.

[0131] Step 1:

[0132] Users access the terminal and input information about the purpose and target audience of the research. For example, in market research for a new product, they would input detailed information about the product's features and target customer base.

[0133] Step 2:

[0134] The terminal sends the input information to the server. The server uses an emotion engine to analyze this information and detect the user's emotional state. For example, the emotion engine might detect from the user's input that they have a positive interest.

[0135] Step 3:

[0136] The server uses an AI algorithm to automatically generate questionnaires based on the analysis results of the emotion engine. For example, if a user shows positive interest, the questionnaire will include questions designed to elicit that interest.

[0137] Step 4:

[0138] The generated questionnaire is sent to the terminal, where the user can review its contents and modify the questions as needed.

[0139] Step 5:

[0140] The revised questionnaire is sent back to the server, which then distributes it to the respondents via an online platform or email. This process provides respondents with an accessible link.

[0141] Step 6:

[0142] Once the response data from the survey participants is collected on the server, the server begins to aggregate the data in real time. Furthermore, an emotion engine analyzes the response data to identify emotional trends, for example, which questions respondents responded to positively.

[0143] Step 7:

[0144] The server visualizes the data based on aggregation and sentiment analysis results. The visualized analysis results are sent to the terminal, allowing users to visually grasp data trends, including emotional insights.

[0145] Step 8:

[0146] Ultimately, the server automatically generates a report incorporating the sentiment analysis results. The report includes a summary of the findings, key insights, and suggestions from an emotional perspective.

[0147] Step 9:

[0148] The generated report is sent to the device and presented to the user. Based on this report, the user can implement business strategies and make decisions that take emotions into account.

[0149] (Example 2)

[0150] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0151] Conventional survey systems have difficulty creating questionnaires that take users' emotions into account, and the analysis of emotional tendencies in the collected data has not been sufficient, resulting in insufficient accuracy and insight into the survey results. Therefore, there is a need for the generation of survey items that correspond to the emotional state of users and for data analysis that takes emotional tendencies into account.

[0152] 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.

[0153] In this invention, the server includes data receiving means, emotion analysis means, and item generation means. This allows for the analysis of emotions based on user input information, the generation of corresponding survey items, and further analysis of emotional tendencies from the collected data, thereby enabling the acquisition of more accurate survey results.

[0154] "Data receiving means" refers to a device or method for receiving information provided by a user and incorporating it into the system.

[0155] "Emotion analysis means" refers to a device or method for determining a user's emotions by analyzing language patterns and expression styles based on data received from the user.

[0156] "Item generation means" refers to a device or method for automatically creating items necessary for a survey based on the results of sentiment analysis.

[0157] "Data collection means" refers to a device or method for collecting response information from survey participants and storing it in a format necessary for analysis.

[0158] "Analysis means" refers to a device or method for aggregating collected data in real time, analyzing statistical and emotional trends, and visually representing them.

[0159] "Report generation means" refers to a device or method for automatically generating research results in the form of a report based on the analysis results.

[0160] This invention is a survey system that takes user emotions into consideration, and aims to be implemented comprehensively throughout the process from questionnaire design to data collection, analysis, and report creation. Its specific form is shown below.

[0161] The server uses data receiving means to receive information about the survey from the user. This means includes an interface in which the user operates a terminal to input information about the survey objectives and target objects. In particular, sentiment analysis means are used to analyze the user's input and determine the user's emotions from language patterns and input style. This is achieved by making full use of natural language processing technology and machine learning algorithms.

[0162] For example, consider a scenario where users conduct market research on a new product. They log into a research platform and input their responses to questions. The system identifies positive expectations and negative concerns as sentiment tags based on the words and writing style used. Based on these sentiment analysis results, the server automatically generates optimized research questions using a generative AI model.

[0163] The generated survey items are distributed to the target audience via data collection methods, including email and distribution through a dedicated application. The collected data is aggregated in real time by a server, and data visualization is performed based on the results of sentiment analysis. At this stage, not only is statistical analysis performed, but emotional trends are represented in graphs and charts to make them easy for users to understand.

[0164] The report generation tool then automatically generates a comprehensive report based on the analysis results. This report includes the background of the research, key metrics, and sentiment-based insights, providing essential insights for marketing and strategy development.

[0165] An example of a prompt would be: "Create a questionnaire to capture user expectations regarding the new product. Based on the data collected from this survey, visualize and demonstrate the emotional trends you analyzed." This allows users to go through a more personalized research process and achieve collaborative and effective data aggregation.

[0166] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0167] Step 1:

[0168] Users input research objectives and target information using a terminal. The terminal transmits this information to the server via a data receiving device. The input data, along with language patterns and input style, is recorded and serves as foundational data for sentiment analysis.

[0169] Step 2:

[0170] The server analyzes the emotional state based on the received data, using sentiment analysis tools. It processes language patterns and writing style using analysis algorithms to generate sentiment tags. This process outputs the user's positive expectations and negative concerns as quantified data.

[0171] Step 3:

[0172] Based on the results of sentiment analysis, the server automatically generates survey items using a generative AI model. The item generation method takes sentiment tags into consideration, adjusts the survey items, and designs questions that address the user's expectations and concerns. This results in a survey questionnaire that is tailored to the user.

[0173] Step 4:

[0174] The server distributes the generated questionnaires using data collection methods. The questionnaires are delivered to the target survey participants via email or a dedicated application. This output indicates the completion of questionnaire distribution.

[0175] Step 5:

[0176] Participants enter their answers via a terminal, and this data is sent to a server. The server aggregates the responses in a database in real time and processes them using analytical tools to identify emotional tendencies. The aggregated data is then used for analysis.

[0177] Step 6:

[0178] The server uses analytical tools to visualize data trends based on collected data and sentiment tags. The results, derived from statistical calculations and visualization of sentiment insights, are presented to the user via the terminal in the form of graphs and charts.

[0179] Step 7:

[0180] Ultimately, the server automatically generates a comprehensive report based on the analysis results using a reporting mechanism. The report includes background information, data analysis, and sentiment insights, and is sent to the user. The output of this step is a complete research report.

[0181] (Application Example 2)

[0182] 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".

[0183] Conventional survey and advertising creation systems fail to adequately consider users' emotional states for personalization, resulting in information gathering that does not meet user expectations and reduced advertising effectiveness. Therefore, there was a need for a means to analyze user emotions in real time and provide customized information and advertisements accordingly.

[0184] 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.

[0185] In this invention, the server includes an information receiving means for receiving survey objectives and target information from the user, an emotion analysis means for analyzing the information received by the information receiving means and determining the user's emotional state, and a data generation means for automatically generating questionnaires or advertising materials based on the emotional state determined by the emotion analysis means. This makes it possible to provide personalized information based on the user's emotional state.

[0186] An "information receiving method" is an interface for collecting information from users regarding the purpose and target of the survey.

[0187] An "emotion analysis tool" is a processing mechanism that analyzes and determines the user's emotional state based on the information received.

[0188] "Data generation means" refers to a process for automatically creating questionnaires and advertising materials based on identified emotional states.

[0189] A "data collection method" is a system for collecting response data obtained from questionnaires or advertising materials that have been created or presented.

[0190] An "analysis and display means" is a function for analyzing collected data and displaying it as a visual report that includes emotional insights.

[0191] A "result generation means" is a process that provides the functionality to automatically generate a final report based on the analysis results.

[0192] This invention is a system for providing personalized information adapted to the user's emotions. The main components necessary to realize the system are an information receiving means, an emotion analysis means, a data generation means, a data collection means, an analysis display means, and a result generation means.

[0193] The server receives information from the user regarding the purpose and target of the survey through an information receiving mechanism. This information is analyzed by an emotion analysis mechanism to determine the user's emotional state. Google Cloud Natural Language API is used as the natural language processing tool for this analysis.

[0194] Based on the identified emotional state, the server uses a generative AI model to generate questionnaires or advertising materials. OpenAI's GPT is suitable for this generation. The generated materials and questionnaires are distributed through data collection mechanisms to collect user response data.

[0195] The server stores the collected data using Firebase, analyzes it in real time using analytical display tools, and visualizes emotional insights. Tableau is used for this visualization.

[0196] Finally, the results generation system generates a detailed report based on the analysis results and provides it to the user. This allows the user to obtain results that include insights based on their emotional state.

[0197] For example, if a user inputs information such as "I want to create an advertisement that conveys the fun of a new product," the server will identify a positive emotion. Based on this emotional state, the generative AI model will prompt the system to create advertising copy that conveys a fun atmosphere.

[0198] Example prompt: "Create advertising copy that conveys a positive and fun atmosphere. The new product's features are ○○."

[0199] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0200] Step 1:

[0201] The user inputs the purpose and target information of the survey via a terminal. The entered information is sent to the server as a means of receiving information. This received information becomes the input for the next process.

[0202] Step 2:

[0203] The server uses sentiment analysis techniques to determine the user's emotional state based on the received information. Specifically, it utilizes the Google Cloud Natural Language API to analyze language patterns and identify the emotional state. The results of this analysis become the output for the next processing step.

[0204] Step 3:

[0205] The server generates questionnaires or advertising materials using a generative AI model based on the emotional state obtained through emotion analysis. OpenAI's GPT model is used to generate text that matches the emotional state. The materials generated here become the output for the next step.

[0206] Step 4:

[0207] The generated questionnaires or advertising materials are distributed to users or target audiences using data collection methods. Responses and answers to the distributed materials are collected as data. This data serves as input for analysis in the next process.

[0208] Step 5:

[0209] The server stores the data collected via Firebase and performs real-time analysis using analytical display tools. Specifically, it performs statistical analysis of the data and visualizes trends, including emotional insights. This visualized data is then used in the next step.

[0210] Step 6:

[0211] Finally, the server uses a results generation system to create a report based on the visualized data obtained. This report is provided to the user and presents detailed analytical results, including insights based on emotional state.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] [Second Embodiment]

[0216] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0217] 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.

[0218] 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).

[0219] 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.

[0220] 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.

[0221] 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).

[0222] 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.

[0223] 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.

[0224] 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.

[0225] 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.

[0226] 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.

[0227] 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".

[0228] This invention relates to a system that efficiently supports survey work, and in particular to a technology that automates a series of processes from questionnaire design to data collection, analysis, and report creation.

[0229] When a user uses this system, they first access a terminal and enter information about the purpose and target of their research. For example, if they want to conduct market research on a new product, they would enter information such as the product's features, target customer base, and expected market information.

[0230] The server receives this input information and uses AI to automatically generate a questionnaire containing the most appropriate questions. This generated questionnaire is sent to the user's device, where the user can review the content and make any necessary modifications. The server then distributes the questionnaire via online platforms or email, reaching the intended target audience.

[0231] As data collection progresses, the server begins to aggregate incoming response data in real time. As more data is gathered, the server uses AI algorithms to perform statistical and trend analyses, displaying the results on the terminal as interactive graphs and charts. For example, the degree of interest in products by age group of the survey participants can be visualized, allowing users to intuitively recognize the trends.

[0232] Ultimately, the server automatically generates a detailed report based on the analysis results. This report includes an overview of the study, key insights, statistics, relevant graphs, and suggestions for future actions. In this way, users can quickly and efficiently make decisions based on the insights derived from the study.

[0233] As a result, this invention significantly streamlines each process of investigation work and supports more accurate and rapid decision-making, and its scope of application is wide.

[0234] The following describes the processing flow.

[0235] Step 1:

[0236] Users access the terminal and input information about the purpose and target audience of the research. Specifically, for market research on a new product, they would fill in an overview of the new product, the target customer base, and specific research items.

[0237] Step 2:

[0238] Information entered from the terminal is sent to the server. The server uses an AI algorithm to automatically generate questionnaire questions based on this information. For example, questions about the preferences and needs of the target customer group are generated.

[0239] Step 3:

[0240] The generated questionnaire is sent to the terminal, where the user reviews its contents. If any changes are needed to the content or order of the questions, the user can make corrections through the interface.

[0241] Step 4:

[0242] The server receives the revised questionnaire, and it is then distributed to the survey participants via an online platform or email. During this process, participants are provided with URLs or links that they can access.

[0243] Step 5:

[0244] Once the response data from the survey participants is collected on the server, the server begins aggregating the data in real time. Statistical information for each response is accumulated and immediately organized into a dataset for visualization.

[0245] Step 6:

[0246] The server analyzes aggregated data and performs statistical and trend analysis. It utilizes AI to identify important correlations and patterns, and generates easy-to-understand graphs and charts based on the results.

[0247] Step 7:

[0248] The generated graphs and charts are sent to the device, presenting the analysis results to the user in a visual format. Through this visualization, users can quickly grasp data trends and insights.

[0249] Step 8:

[0250] Finally, the server automatically generates a report summarizing the analysis results. The report includes the background of the study, all key findings, graphs and charts, and actionable suggestions.

[0251] Step 9:

[0252] The generated report is sent to the terminal and provided to the user. The user uses this report to apply the findings to business decision-making and strategy development.

[0253] (Example 1)

[0254] 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."

[0255] Traditional research methods often involved manual processes from questionnaire design to data collection, analysis, and report writing, resulting in significant time and effort. Furthermore, data analysis required highly specialized knowledge, hindering rapid and accurate decision-making. Additionally, determining whether the generated questionnaires were appropriate for the characteristics of the survey participants heavily depended on the experience of the person conducting the research, making efficient research difficult.

[0256] 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.

[0257] In this invention, the server includes an information input means for receiving survey objectives and target information from the user, an information generation means for automatically generating questionnaires using a generative artificial intelligence model and including optimized questions, and an information analysis means for aggregating collected data in real time, performing statistical analysis, and visualizing the results as digital graphs and charts. This automates survey work, improving work efficiency and enabling accurate and rapid decision-making.

[0258] "Information input means" refers to a means of receiving the research objectives and target information from the user, thereby obtaining basic information for the research.

[0259] "Information generation means" refers to a means of automatically generating questionnaires using a generative artificial intelligence model based on acquired information, and creating questionnaires that include optimized questions.

[0260] "Information gathering means" refers to the method of distributing generated questionnaires via digital communication and collecting response data, thereby efficiently collecting information from survey subjects.

[0261] "Information analysis tools" are means of aggregating collected data in real time, performing statistical analysis, and visualizing the results obtained as digital graphs or charts.

[0262] "Information generation means" (report generation) refers to a method that automatically generates a detailed research report based on the analysis results, including suggestions for future actions, and is intended to effectively communicate the research findings.

[0263] To properly implement this invention, it is necessary to construct a system that processes information over a network. Key components include servers, terminals, and software that connects them.

[0264] First, the user accesses the server using their device and enters the research objectives and target information. At this stage, they use a web browser such as Google Chrome or Mozilla Firefox on their device and enter the necessary information through the user interface.

[0265] The server automatically generates questionnaires using a generative artificial intelligence model based on information received from the user. This process creates optimized questions using a generative AI model such as OpenAI. For example, if the input prompt is "Generate a detailed questionnaire about fitness earphones targeting people in their 20s," the AI ​​model will generate specific questions that meet that requirement.

[0266] After the questionnaire is generated, the server distributes it via email or Google Forms. This ensures that the questionnaire is efficiently delivered to the survey participants, and as a result, the response data is collected.

[0267] The collected data is aggregated and analyzed in real time on the server. The data is structured using the Python Pandas library and visually displayed as digital graphs and charts using the Matplotlib library. This allows users to intuitively grasp the data trends.

[0268] Ultimately, the server automatically generates a detailed research report based on the analysis results. This report includes statistical analysis results, insights, and suggestions for future actions. Users can then make strategic decisions based on the generated report.

[0269] This system automates each process of the survey, significantly reducing time and effort, and enabling faster and more accurate decision-making.

[0270] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0271] Step 1:

[0272] Users access the server via their devices and input information about the purpose and target of the research. Specifically, users log in to a dedicated form using a web browser and input the research purpose, such as "market research for next-generation smartwatches." The input data is sent to the server and stored by the information input method. The data entered here forms the basis for subsequent processes.

[0273] Step 2:

[0274] The server creates and sends a prompt to the generative AI model based on the information it receives. This prompt might include something like, "Please create a survey about smartwatch features that would be of interest to users in their 20s and 30s." The generative AI model generates the most appropriate survey questions based on the prompt and returns them to the server. This generated list of questions becomes the material needed for the next data collection.

[0275] Step 3:

[0276] The server sends the generated questionnaire back to the terminal and prompts the user for confirmation. The user reviews the questions on the terminal and makes corrections if necessary. For example, the user might look at the generated questions and make a correction such as "Please add a question about smartwatch design." As a result, the revised questionnaire is finalized.

[0277] Step 4:

[0278] The server distributes the finalized questionnaire to respondents via digital distribution methods (e.g., email or online forms). The server selects from various distribution platforms, generates a survey link, and sends it to the respondents. This prepares the server for collecting response data from the survey respondents.

[0279] Step 5:

[0280] The server aggregates the received response data in real time. It uses the Pandas library in Python to process large-scale data and perform the necessary statistical analysis. For example, it grasps trends and calculates average values, and based on this, generates digital graphs and charts. This visual information serves as the output for users to intuitively understand the analysis results.

[0281] Step 6:

[0282] The server generates a detailed report based on the analysis results. The generated report includes statistical insights and future proposals and is provided as an output to the user. The report is automatically created in the form of Microsoft Word or Google Docs and is sent to the user through the terminal. The user can make strategic decisions based on this.

[0283] (Application Example 1)

[0284] 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".

[0285] In market research, the process from questionnaire design to data collection, analysis, and result reporting is often carried out manually, which has the problem of taking a lot of time and cost. Also, it is difficult to visualize and present data in real time, and quick decision-making is often hindered.

[0286] 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.

[0287] In this invention, the server includes an input means for receiving survey objectives and target information from a user; a generation means for automatically generating questionnaires based on the information received by the input means; a collection means for distributing the generated questionnaires to survey subjects and collecting response data; an analysis means for aggregating, analyzing, and visualizing the collected data in real time; and a presentation means for presenting the analysis results obtained by the analysis means in real time through a display device. This enables increased efficiency in the entire survey process and rapid decision-making through the rapid presentation of data.

[0288] "Input means" refers to a device or software for receiving information from the user regarding the purpose and subject of the investigation.

[0289] "Generation means" refers to a device or software for automatically creating questionnaires based on received information.

[0290] "Collection means" refers to a device or software for providing a generated questionnaire to the survey subjects and collecting response data.

[0291] "Analysis means" refers to a device or software that aggregates and analyzes collected data in real time and visualizes the results.

[0292] "Presentation means" refers to a device or software for presenting the analysis results obtained by the analysis means in real time through a display device.

[0293] In the system that realizes this invention, the user, server, and terminal cooperate to streamline the research process.

[0294] First, the user uses a terminal to input information about the purpose and target of the survey. The terminal is equipped with an interface to smoothly receive input from the user.

[0295] The server receives information sent from the terminal and automatically generates a questionnaire containing appropriate questions using a generative AI model. This generated questionnaire is then sent back to the terminal, where the user can review its contents and edit it as needed.

[0296] Next, the server distributes the generated questionnaires to the target group and collects the response data. This process utilizes online platforms and data transmission methods.

[0297] Once the response data is collected, the server begins aggregating and analyzing the data in real time. During this process, data analysis tools such as Python and R are used to perform statistical processing and trend analysis on the collected data.

[0298] The analysis results, including statistical information and trends, are presented in an interactive visual format. By using engines such as Unity to visualize the analysis results and presenting them through display devices such as smart glasses, users can intuitively understand the content.

[0299] Ultimately, the server automatically generates a detailed report based on the analysis results. This report includes an overview of the study, key insights, statistics, and relevant graphs, allowing users to make informed decisions.

[0300] A concrete example is its use in collecting feedback on a new product at an exhibition and deciding on the product strategy on the spot. In this way, it becomes possible to instantly select and incorporate real-time feedback into marketing activities.

[0301] An example of a prompt is: "Create a questionnaire to collect responses from target customers based on the product features of a new sports shoe. Provide instructions for building an application that analyzes and visualizes the response data in real time."

[0302] The process of the specific processing in Application Example 1 will be described using FIG. 12.

[0303] Step 1:

[0304] The user uses the terminal to input information about the purpose and target of the survey. Here, information regarding the attributes and purpose of the survey target is input in text format. This input data is received by the terminal via the keyboard or voice interface and transmitted to the server.

[0305] Step 2:

[0306] Based on the received information, the server uses the generated AI model to automatically generate a survey form. In this process, the input information about the survey purpose and target is analyzed, and an algorithm for designing appropriate questions is applied. The generated survey form is generated as digital data and sent back to the terminal.

[0307] Step 3:

[0308] The terminal displays the survey form received by the user, and the user checks the content and makes corrections if necessary. The user can check the survey form in detail and use the editing function to modify, add, or delete questions. The edited data is transmitted to the server again.

[0309] Step 4:

[0310] The server distributes the finalized survey form to the respondents and collects the response data. In this step, various online platforms and data transmission means are utilized to distribute the survey form to a wide range of survey targets. The response data input by the respondents is accumulated on the server.

[0311] [[ID=3,6]]Step 5:

[0312] The server aggregates and analyzes the collected response data in real time and visualizes it. At this stage, software tools such as Python and R are used to statistically process the data and analyze trends and key insights. The resulting analysis is then formatted as visual data.

[0313] Step 6:

[0314] The server presents visualized analytical data to the user through a display device such as smart glasses. Here, an engine such as Unity is used to display the visual data on the smart glasses, allowing the user to understand the results intuitively in real time.

[0315] Step 7:

[0316] The server ultimately automatically generates a detailed report based on the analysis results and sends it to the user's device. This report includes a summary of the entire study, insights, and recommended actions, enabling the user to make quick decisions based on it.

[0317] 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.

[0318] This invention relates to a survey system incorporating an emotion engine, which provides a more personalized survey process by taking user emotions into consideration from questionnaire design to data collection, analysis, and final report generation.

[0319] When a user uses this system, they first input information about the research objectives and target audience into the terminal. During input, the emotion engine analyzes language patterns and input style to determine the user's emotional state. For example, when conducting market research on a product, the emotion engine recognizes expectations and concerns from the user's descriptions and generates research questions accordingly.

[0320] The server uses the results of this sentiment analysis to automatically generate an optimized questionnaire using AI. For example, if a user expresses strong expectations for a new product, questions will be created to specifically measure those expectations.

[0321] The generated questionnaires are verified by the user and then distributed to the survey participants via an online platform by the server. Once responses to the distributed questionnaires are collected, the server aggregates the data in real time and detects emotional trends from the data collected by the emotion engine.

[0322] The server also considers emotional insights related to the collected data when analyzing the aggregated data, and visualizes data patterns. These visualized graphs and charts are sent to the terminal, allowing the user to visually grasp the analysis results, including emotional trends at that time.

[0323] Ultimately, the server automatically generates a comprehensive report incorporating sentiment analysis. The report presents the background of the research, key analytical findings, and an integrated emotional perspective, enabling richer insights. Specifically, it includes suggestions on how the positive / negative emotions expressed by specific customer segments towards a product might impact marketing strategies.

[0324] In this way, the present invention provides a sensible approach to obtaining more accurate and effective survey results by understanding user emotions and tailoring the entire survey accordingly.

[0325] The following describes the processing flow.

[0326] Step 1:

[0327] Users access the terminal and input information about the purpose and target audience of the research. For example, in market research for a new product, they would input detailed information about the product's features and target customer base.

[0328] Step 2:

[0329] The terminal sends the input information to the server. The server uses an emotion engine to analyze this information and detect the user's emotional state. For example, the emotion engine might detect from the user's input that they have a positive interest.

[0330] Step 3:

[0331] The server uses an AI algorithm to automatically generate questionnaires based on the analysis results of the emotion engine. For example, if a user shows positive interest, the questionnaire will include questions designed to elicit that interest.

[0332] Step 4:

[0333] The generated questionnaire is sent to the terminal, where the user can review its contents and modify the questions as needed.

[0334] Step 5:

[0335] The revised questionnaire is sent back to the server, which then distributes it to the respondents via an online platform or email. This process provides respondents with an accessible link.

[0336] Step 6:

[0337] Once the response data from the survey participants is collected on the server, the server begins to aggregate the data in real time. Furthermore, an emotion engine analyzes the response data to identify emotional trends, for example, which questions respondents responded to positively.

[0338] Step 7:

[0339] The server visualizes the data based on aggregation and sentiment analysis results. The visualized analysis results are sent to the terminal, allowing users to visually grasp data trends, including emotional insights.

[0340] Step 8:

[0341] Ultimately, the server automatically generates a report incorporating the sentiment analysis results. The report includes a summary of the findings, key insights, and suggestions from an emotional perspective.

[0342] Step 9:

[0343] The generated report is sent to the device and presented to the user. Based on this report, the user can implement business strategies and make decisions that take emotions into account.

[0344] (Example 2)

[0345] 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".

[0346] Conventional survey systems have difficulty creating questionnaires that take users' emotions into account, and the analysis of emotional tendencies in the collected data has not been sufficient, resulting in insufficient accuracy and insight into the survey results. Therefore, there is a need for the generation of survey items that correspond to the emotional state of users and for data analysis that takes emotional tendencies into account.

[0347] 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.

[0348] In this invention, the server includes data receiving means, emotion analysis means, and item generation means. This allows for the analysis of emotions based on user input information, the generation of corresponding survey items, and further analysis of emotional tendencies from the collected data, thereby enabling the acquisition of more accurate survey results.

[0349] "Data receiving means" refers to a device or method for receiving information provided by a user and incorporating it into the system.

[0350] "Emotion analysis means" refers to a device or method for determining a user's emotions by analyzing language patterns and expression styles based on data received from the user.

[0351] "Item generation means" refers to a device or method for automatically creating items necessary for a survey based on the results of sentiment analysis.

[0352] "Data collection means" refers to a device or method for collecting response information from survey participants and storing it in a format necessary for analysis.

[0353] "Analysis means" refers to a device or method for aggregating collected data in real time, analyzing statistical and emotional trends, and visually representing them.

[0354] "Report generation means" refers to a device or method for automatically generating research results in the form of a report based on the analysis results.

[0355] This invention is a survey system that takes user emotions into consideration, and aims to be implemented comprehensively throughout the process from questionnaire design to data collection, analysis, and report creation. Its specific form is shown below.

[0356] The server uses data receiving means to receive information about the survey from the user. This means includes an interface in which the user operates a terminal to input information about the survey objectives and target objects. In particular, sentiment analysis means are used to analyze the user's input and determine the user's emotions from language patterns and input style. This is achieved by making full use of natural language processing technology and machine learning algorithms.

[0357] For example, consider a scenario where users conduct market research on a new product. They log into a research platform and input their responses to questions. The system identifies positive expectations and negative concerns as sentiment tags based on the words and writing style used. Based on these sentiment analysis results, the server automatically generates optimized research questions using a generative AI model.

[0358] The generated survey items are distributed to the target audience via data collection methods, including email and distribution through a dedicated application. The collected data is aggregated in real time by a server, and data visualization is performed based on the results of sentiment analysis. At this stage, not only is statistical analysis performed, but emotional trends are represented in graphs and charts to make them easy for users to understand.

[0359] The report generation tool then automatically generates a comprehensive report based on the analysis results. This report includes the background of the research, key metrics, and sentiment-based insights, providing essential insights for marketing and strategy development.

[0360] An example of a prompt would be: "Create a questionnaire to capture user expectations regarding the new product. Based on the data collected from this survey, visualize and demonstrate the emotional trends you analyzed." This allows users to go through a more personalized research process and achieve collaborative and effective data aggregation.

[0361] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0362] Step 1:

[0363] Users input research objectives and target information using a terminal. The terminal transmits this information to the server via a data receiving device. The input data, along with language patterns and input style, is recorded and serves as foundational data for sentiment analysis.

[0364] Step 2:

[0365] The server analyzes the emotional state based on the received data, using sentiment analysis tools. It processes language patterns and writing style using analysis algorithms to generate sentiment tags. This process outputs the user's positive expectations and negative concerns as quantified data.

[0366] Step 3:

[0367] Based on the results of sentiment analysis, the server automatically generates survey items using a generative AI model. The item generation method takes sentiment tags into consideration, adjusts the survey items, and designs questions that address the user's expectations and concerns. This results in a survey questionnaire that is tailored to the user.

[0368] Step 4:

[0369] The server distributes the generated questionnaires using data collection methods. The questionnaires are delivered to the target survey participants via email or a dedicated application. This output indicates the completion of questionnaire distribution.

[0370] Step 5:

[0371] Participants enter their answers via a terminal, and this data is sent to a server. The server aggregates the responses in a database in real time and processes them using analytical tools to identify emotional tendencies. The aggregated data is then used for analysis.

[0372] Step 6:

[0373] The server uses analytical tools to visualize data trends based on collected data and sentiment tags. The results, derived from statistical calculations and visualization of sentiment insights, are presented to the user via the terminal in the form of graphs and charts.

[0374] Step 7:

[0375] Ultimately, the server automatically generates a comprehensive report based on the analysis results using a reporting mechanism. The report includes background information, data analysis, and sentiment insights, and is sent to the user. The output of this step is a complete research report.

[0376] (Application Example 2)

[0377] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0378] Conventional survey and advertising creation systems fail to adequately consider users' emotional states for personalization, resulting in information gathering that does not meet user expectations and reduced advertising effectiveness. Therefore, there was a need for a means to analyze user emotions in real time and provide customized information and advertisements accordingly.

[0379] 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.

[0380] In this invention, the server includes an information receiving means for receiving survey objectives and target information from the user, an emotion analysis means for analyzing the information received by the information receiving means and determining the user's emotional state, and a data generation means for automatically generating questionnaires or advertising materials based on the emotional state determined by the emotion analysis means. This makes it possible to provide personalized information based on the user's emotional state.

[0381] An "information receiving method" is an interface for collecting information from users regarding the purpose and target of the survey.

[0382] An "emotion analysis tool" is a processing mechanism that analyzes and determines the user's emotional state based on the information received.

[0383] "Data generation means" refers to a process for automatically creating questionnaires and advertising materials based on identified emotional states.

[0384] A "data collection method" is a system for collecting response data obtained from questionnaires or advertising materials that have been created or presented.

[0385] An "analysis and display means" is a function for analyzing collected data and displaying it as a visual report that includes emotional insights.

[0386] A "result generation means" is a process that provides the functionality to automatically generate a final report based on the analysis results.

[0387] This invention is a system for providing personalized information adapted to the user's emotions. The main components necessary to realize the system are an information receiving means, an emotion analysis means, a data generation means, a data collection means, an analysis display means, and a result generation means.

[0388] The server receives information from the user regarding the purpose and target of the survey through an information receiving mechanism. This information is analyzed by an emotion analysis mechanism to determine the user's emotional state. Google Cloud Natural Language API is used as the natural language processing tool for this analysis.

[0389] Based on the identified emotional state, the server uses a generative AI model to generate questionnaires or advertising materials. OpenAI's GPT is suitable for this generation. The generated materials and questionnaires are distributed through data collection mechanisms to collect user response data.

[0390] The server stores the collected data using Firebase, analyzes it in real time using analytical display tools, and visualizes emotional insights. Tableau is used for this visualization.

[0391] Finally, the results generation system generates a detailed report based on the analysis results and provides it to the user. This allows the user to obtain results that include insights based on their emotional state.

[0392] For example, if a user inputs information such as "I want to create an advertisement that conveys the fun of a new product," the server will identify a positive emotion. Based on this emotional state, the generative AI model will prompt the system to create advertising copy that conveys a fun atmosphere.

[0393] Example prompt: "Create advertising copy that conveys a positive and fun atmosphere. The new product's features are ○○."

[0394] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0395] Step 1:

[0396] The user inputs the purpose and target information of the survey via a terminal. The entered information is sent to the server as a means of receiving information. This received information becomes the input for the next process.

[0397] Step 2:

[0398] The server uses sentiment analysis techniques to determine the user's emotional state based on the received information. Specifically, it utilizes the Google Cloud Natural Language API to analyze language patterns and identify the emotional state. The results of this analysis become the output for the next processing step.

[0399] Step 3:

[0400] The server generates questionnaires or advertising materials using a generative AI model based on the emotional state obtained through emotion analysis. OpenAI's GPT model is used to generate text that matches the emotional state. The materials generated here become the output for the next step.

[0401] Step 4:

[0402] The generated questionnaires or advertising materials are distributed to users or target audiences using data collection methods. Responses and answers to the distributed materials are collected as data. This data serves as input for analysis in the next process.

[0403] Step 5:

[0404] The server stores the data collected via Firebase and performs real-time analysis using analytical display tools. Specifically, it performs statistical analysis of the data and visualizes trends, including emotional insights. This visualized data is then used in the next step.

[0405] Step 6:

[0406] Finally, the server uses a results generation system to create a report based on the visualized data obtained. This report is provided to the user and presents detailed analytical results, including insights based on emotional state.

[0407] 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.

[0408] 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.

[0409] 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.

[0410] [Third Embodiment]

[0411] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0412] 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.

[0413] 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).

[0414] 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.

[0415] 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.

[0416] 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).

[0417] 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.

[0418] 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.

[0419] 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.

[0420] 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.

[0421] 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.

[0422] 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".

[0423] This invention relates to a system that efficiently supports survey work, and in particular to a technology that automates a series of processes from questionnaire design to data collection, analysis, and report creation.

[0424] When a user uses this system, they first access a terminal and enter information about the purpose and target of their research. For example, if they want to conduct market research on a new product, they would enter information such as the product's features, target customer base, and expected market information.

[0425] The server receives this input information and uses AI to automatically generate a questionnaire containing the most appropriate questions. This generated questionnaire is sent to the user's device, where the user can review the content and make any necessary modifications. The server then distributes the questionnaire via online platforms or email, reaching the intended target audience.

[0426] As data collection progresses, the server begins to aggregate incoming response data in real time. As more data is gathered, the server uses AI algorithms to perform statistical and trend analyses, displaying the results on the terminal as interactive graphs and charts. For example, the degree of interest in products by age group of the survey participants can be visualized, allowing users to intuitively recognize the trends.

[0427] Ultimately, the server automatically generates a detailed report based on the analysis results. This report includes an overview of the study, key insights, statistics, relevant graphs, and suggestions for future actions. In this way, users can quickly and efficiently make decisions based on the insights derived from the study.

[0428] As a result, this invention significantly streamlines each process of investigation work and supports more accurate and rapid decision-making, and its scope of application is wide.

[0429] The following describes the processing flow.

[0430] Step 1:

[0431] Users access the terminal and input information about the purpose and target audience of the research. Specifically, for market research on a new product, they would fill in an overview of the new product, the target customer base, and specific research items.

[0432] Step 2:

[0433] Information entered from the terminal is sent to the server. The server uses an AI algorithm to automatically generate questionnaire questions based on this information. For example, questions about the preferences and needs of the target customer group are generated.

[0434] Step 3:

[0435] The generated questionnaire is sent to the terminal, where the user reviews its contents. If any changes are needed to the content or order of the questions, the user can make corrections through the interface.

[0436] Step 4:

[0437] The server receives the revised questionnaire, and it is then distributed to the survey participants via an online platform or email. During this process, participants are provided with URLs or links that they can access.

[0438] Step 5:

[0439] Once the response data from the survey participants is collected on the server, the server begins aggregating the data in real time. Statistical information for each response is accumulated and immediately organized into a dataset for visualization.

[0440] Step 6:

[0441] The server analyzes aggregated data and performs statistical and trend analysis. It utilizes AI to identify important correlations and patterns, and generates easy-to-understand graphs and charts based on the results.

[0442] Step 7:

[0443] The generated graphs and charts are sent to the device, presenting the analysis results to the user in a visual format. Through this visualization, users can quickly grasp data trends and insights.

[0444] Step 8:

[0445] Finally, the server automatically generates a report summarizing the analysis results. The report includes the background of the study, all key findings, graphs and charts, and actionable suggestions.

[0446] Step 9:

[0447] The generated report is sent to the terminal and provided to the user. The user uses this report to apply the findings to business decision-making and strategy development.

[0448] (Example 1)

[0449] 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."

[0450] Traditional research methods often involved manual processes from questionnaire design to data collection, analysis, and report writing, resulting in significant time and effort. Furthermore, data analysis required highly specialized knowledge, hindering rapid and accurate decision-making. Additionally, determining whether the generated questionnaires were appropriate for the characteristics of the survey participants heavily depended on the experience of the person conducting the research, making efficient research difficult.

[0451] 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.

[0452] In this invention, the server includes an information input means for receiving survey objectives and target information from the user, an information generation means for automatically generating questionnaires using a generative artificial intelligence model and including optimized questions, and an information analysis means for aggregating collected data in real time, performing statistical analysis, and visualizing the results as digital graphs and charts. This automates survey work, improving work efficiency and enabling accurate and rapid decision-making.

[0453] "Information input means" refers to a means of receiving the research objectives and target information from the user, thereby obtaining basic information for the research.

[0454] "Information generation means" refers to a means of automatically generating questionnaires using a generative artificial intelligence model based on acquired information, and creating questionnaires that include optimized questions.

[0455] "Information gathering means" refers to the method of distributing generated questionnaires via digital communication and collecting response data, thereby efficiently collecting information from survey subjects.

[0456] "Information analysis tools" are means of aggregating collected data in real time, performing statistical analysis, and visualizing the results obtained as digital graphs or charts.

[0457] "Information generation means" (report generation) refers to a method that automatically generates a detailed research report based on the analysis results, including suggestions for future actions, and is intended to effectively communicate the research findings.

[0458] To properly implement this invention, it is necessary to construct a system that processes information over a network. Key components include servers, terminals, and software that connects them.

[0459] First, the user accesses the server using their device and enters the research objectives and target information. At this stage, they use a web browser such as Google Chrome or Mozilla Firefox on their device and enter the necessary information through the user interface.

[0460] The server automatically generates questionnaires using a generative artificial intelligence model based on information received from the user. This process creates optimized questions using a generative AI model such as OpenAI. For example, if the input prompt is "Generate a detailed questionnaire about fitness earphones targeting people in their 20s," the AI ​​model will generate specific questions that meet that requirement.

[0461] After the questionnaire is generated, the server distributes it via email or Google Forms. This ensures that the questionnaire is efficiently delivered to the survey participants, and as a result, the response data is collected.

[0462] The collected data is aggregated and analyzed in real time on the server. The data is structured using the Python Pandas library and visually displayed as digital graphs and charts using the Matplotlib library. This allows users to intuitively grasp the data trends.

[0463] Ultimately, the server automatically generates a detailed research report based on the analysis results. This report includes statistical analysis results, insights, and suggestions for future actions. Users can then make strategic decisions based on the generated report.

[0464] This system automates each process of the survey, significantly reducing time and effort, and enabling faster and more accurate decision-making.

[0465] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0466] Step 1:

[0467] Users access the server via their devices and input information about the purpose and target of the research. Specifically, users log in to a dedicated form using a web browser and input the research purpose, such as "market research for next-generation smartwatches." The input data is sent to the server and stored by the information input method. The data entered here forms the basis for subsequent processes.

[0468] Step 2:

[0469] The server creates and sends a prompt to the generative AI model based on the information it receives. This prompt might include something like, "Please create a survey about smartwatch features that would be of interest to users in their 20s and 30s." The generative AI model generates the most appropriate survey questions based on the prompt and returns them to the server. This generated list of questions becomes the material needed for the next data collection.

[0470] Step 3:

[0471] The server sends the generated questionnaire back to the terminal and prompts the user for confirmation. The user reviews the questions on the terminal and makes corrections if necessary. For example, the user might look at the generated questions and make a correction such as "Please add a question about smartwatch design." As a result, the revised questionnaire is finalized.

[0472] Step 4:

[0473] The server distributes the finalized questionnaire to respondents via digital distribution methods (e.g., email or online forms). The server selects from various distribution platforms, generates a survey link, and sends it to the respondents. This prepares the server for collecting response data from the survey respondents.

[0474] Step 5:

[0475] The server aggregates the received response data in real time. Using the Python Pandas library, it processes large datasets and performs necessary statistical analysis. For example, it identifies trends, calculates averages, and generates digital graphs and charts based on these results. This visual information serves as output to help users intuitively understand the analysis results.

[0476] Step 6:

[0477] The server generates a detailed report based on the analysis results. This report includes statistical insights and future recommendations, and is provided to the user. The report is automatically generated in Microsoft Word or Google Docs format and sent to the user via their device. The user can then use this information to make strategic decisions.

[0478] (Application Example 1)

[0479] 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."

[0480] In market research, the process from questionnaire design to data collection, analysis, and reporting is often done manually, resulting in challenges such as time and cost. Furthermore, real-time data visualization and presentation are difficult, often hindering rapid decision-making.

[0481] 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.

[0482] In this invention, the server includes an input means for receiving survey objectives and target information from a user; a generation means for automatically generating questionnaires based on the information received by the input means; a collection means for distributing the generated questionnaires to survey subjects and collecting response data; an analysis means for aggregating, analyzing, and visualizing the collected data in real time; and a presentation means for presenting the analysis results obtained by the analysis means in real time through a display device. This enables increased efficiency in the entire survey process and rapid decision-making through the rapid presentation of data.

[0483] "Input means" refers to a device or software for receiving information from the user regarding the purpose and subject of the investigation.

[0484] "Generation means" refers to a device or software for automatically creating questionnaires based on received information.

[0485] "Collection means" refers to a device or software for providing a generated questionnaire to the survey subjects and collecting response data.

[0486] "Analysis means" refers to a device or software that aggregates and analyzes collected data in real time and visualizes the results.

[0487] "Presentation means" refers to a device or software for presenting the analysis results obtained by the analysis means in real time through a display device.

[0488] In the system that realizes this invention, the user, server, and terminal cooperate to streamline the research process.

[0489] First, the user uses a terminal to input information about the purpose and target of the survey. The terminal is equipped with an interface to smoothly receive input from the user.

[0490] The server receives information sent from the terminal and automatically generates a questionnaire containing appropriate questions using a generative AI model. This generated questionnaire is then sent back to the terminal, where the user can review its contents and edit it as needed.

[0491] Next, the server distributes the generated questionnaires to the target group and collects the response data. This process utilizes online platforms and data transmission methods.

[0492] Once the response data is collected, the server begins aggregating and analyzing the data in real time. During this process, data analysis tools such as Python and R are used to perform statistical processing and trend analysis on the collected data.

[0493] The analysis results, including statistical information and trends, are presented in an interactive visual format. By using engines such as Unity to visualize the analysis results and presenting them through display devices such as smart glasses, users can intuitively understand the content.

[0494] Ultimately, the server automatically generates a detailed report based on the analysis results. This report includes an overview of the study, key insights, statistics, and relevant graphs, allowing users to make informed decisions.

[0495] A concrete example is its use in collecting feedback on a new product at an exhibition and deciding on the product strategy on the spot. In this way, it becomes possible to instantly select and incorporate real-time feedback into marketing activities.

[0496] An example of a prompt is: "Create a questionnaire to collect responses from target customers based on the product features of a new sports shoe. Provide instructions for building an application that analyzes and visualizes the response data in real time."

[0497] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0498] Step 1:

[0499] The user uses a terminal to input information about the purpose and target of the survey. Here, information about the attributes and purpose of the survey target is entered in text format. This input data is received by the terminal via keyboard or voice interface and sent to the server.

[0500] Step 2:

[0501] The server automatically generates a questionnaire using a generative AI model based on the received information. During this process, algorithms are applied to analyze the entered survey objectives and target information, and to design appropriate questions. The generated questionnaire is created as digital data and sent back to the terminal.

[0502] Step 3:

[0503] The terminal displays the questionnaire received by the user, allowing the user to review its contents and make corrections as needed. The user can examine the questionnaire in detail and use the editing function to modify, add, or delete questions. The edited data is then sent back to the server.

[0504] Step 4:

[0505] The server distributes the finalized questionnaires to participants and collects the response data. In this step, questionnaires are distributed to a wide range of respondents using various online platforms and data transmission methods. The response data entered by participants is stored on the server.

[0506] Step 5:

[0507] The server aggregates and analyzes the collected response data in real time and visualizes it. At this stage, software tools such as Python and R are used to statistically process the data and analyze trends and key insights. The resulting analysis is then formatted as visual data.

[0508] Step 6:

[0509] The server presents visualized analytical data to the user through a display device such as smart glasses. Here, an engine such as Unity is used to display the visual data on the smart glasses, allowing the user to understand the results intuitively in real time.

[0510] Step 7:

[0511] The server ultimately automatically generates a detailed report based on the analysis results and sends it to the user's device. This report includes a summary of the entire study, insights, and recommended actions, enabling the user to make quick decisions based on it.

[0512] 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.

[0513] This invention relates to a survey system incorporating an emotion engine, which provides a more personalized survey process by taking user emotions into consideration from questionnaire design to data collection, analysis, and final report generation.

[0514] When a user uses this system, they first input information about the research objectives and target audience into the terminal. During input, the emotion engine analyzes language patterns and input style to determine the user's emotional state. For example, when conducting market research on a product, the emotion engine recognizes expectations and concerns from the user's descriptions and generates research questions accordingly.

[0515] The server uses the results of this sentiment analysis to automatically generate an optimized questionnaire using AI. For example, if a user expresses strong expectations for a new product, questions will be created to specifically measure those expectations.

[0516] The generated questionnaires are verified by the user and then distributed to the survey participants via an online platform by the server. Once responses to the distributed questionnaires are collected, the server aggregates the data in real time and detects emotional trends from the data collected by the emotion engine.

[0517] The server also considers emotional insights related to the collected data when analyzing the aggregated data, and visualizes data patterns. These visualized graphs and charts are sent to the terminal, allowing the user to visually grasp the analysis results, including emotional trends at that time.

[0518] Ultimately, the server automatically generates a comprehensive report incorporating sentiment analysis. The report presents the background of the research, key analytical findings, and an integrated emotional perspective, enabling richer insights. Specifically, it includes suggestions on how the positive / negative emotions expressed by specific customer segments towards a product might impact marketing strategies.

[0519] In this way, the present invention provides a sensible approach to obtaining more accurate and effective survey results by understanding user emotions and tailoring the entire survey accordingly.

[0520] The following describes the processing flow.

[0521] Step 1:

[0522] Users access the terminal and input information about the purpose and target audience of the research. For example, in market research for a new product, they would input detailed information about the product's features and target customer base.

[0523] Step 2:

[0524] The terminal sends the input information to the server. The server uses an emotion engine to analyze this information and detect the user's emotional state. For example, the emotion engine might detect from the user's input that they have a positive interest.

[0525] Step 3:

[0526] The server uses an AI algorithm to automatically generate questionnaires based on the analysis results of the emotion engine. For example, if a user shows positive interest, the questionnaire will include questions designed to elicit that interest.

[0527] Step 4:

[0528] The generated questionnaire is sent to the terminal, where the user can review its contents and modify the questions as needed.

[0529] Step 5:

[0530] The revised questionnaire is sent back to the server, which then distributes it to the respondents via an online platform or email. This process provides respondents with an accessible link.

[0531] Step 6:

[0532] Once the response data from the survey participants is collected on the server, the server begins to aggregate the data in real time. Furthermore, an emotion engine analyzes the response data to identify emotional trends, for example, which questions respondents responded to positively.

[0533] Step 7:

[0534] The server visualizes the data based on aggregation and sentiment analysis results. The visualized analysis results are sent to the terminal, allowing users to visually grasp data trends, including emotional insights.

[0535] Step 8:

[0536] Ultimately, the server automatically generates a report incorporating the sentiment analysis results. The report includes a summary of the findings, key insights, and suggestions from an emotional perspective.

[0537] Step 9:

[0538] The generated report is sent to the device and presented to the user. Based on this report, the user can implement business strategies and make decisions that take emotions into account.

[0539] (Example 2)

[0540] 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."

[0541] Conventional survey systems have difficulty creating questionnaires that take users' emotions into account, and the analysis of emotional tendencies in the collected data has not been sufficient, resulting in insufficient accuracy and insight into the survey results. Therefore, there is a need for the generation of survey items that correspond to the emotional state of users and for data analysis that takes emotional tendencies into account.

[0542] 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.

[0543] In this invention, the server includes data receiving means, emotion analysis means, and item generation means. This allows for the analysis of emotions based on user input information, the generation of corresponding survey items, and further analysis of emotional tendencies from the collected data, thereby enabling the acquisition of more accurate survey results.

[0544] "Data receiving means" refers to a device or method for receiving information provided by a user and incorporating it into the system.

[0545] "Emotion analysis means" refers to a device or method for determining a user's emotions by analyzing language patterns and expression styles based on data received from the user.

[0546] "Item generation means" refers to a device or method for automatically creating items necessary for a survey based on the results of sentiment analysis.

[0547] "Data collection means" refers to a device or method for collecting response information from survey participants and storing it in a format necessary for analysis.

[0548] "Analysis means" refers to a device or method for aggregating collected data in real time, analyzing statistical and emotional trends, and visually representing them.

[0549] "Report generation means" refers to a device or method for automatically generating research results in the form of a report based on the analysis results.

[0550] This invention is a survey system that takes user emotions into consideration, and aims to be implemented comprehensively throughout the process from questionnaire design to data collection, analysis, and report creation. Its specific form is shown below.

[0551] The server uses data receiving means to receive information about the survey from the user. This means includes an interface in which the user operates a terminal to input information about the survey objectives and target objects. In particular, sentiment analysis means are used to analyze the user's input and determine the user's emotions from language patterns and input style. This is achieved by making full use of natural language processing technology and machine learning algorithms.

[0552] For example, consider a scenario where users conduct market research on a new product. They log into a research platform and input their responses to questions. The system identifies positive expectations and negative concerns as sentiment tags based on the words and writing style used. Based on these sentiment analysis results, the server automatically generates optimized research questions using a generative AI model.

[0553] The generated survey items are distributed to the target audience via data collection methods, including email and distribution through a dedicated application. The collected data is aggregated in real time by a server, and data visualization is performed based on the results of sentiment analysis. At this stage, not only is statistical analysis performed, but emotional trends are represented in graphs and charts to make them easy for users to understand.

[0554] The report generation tool then automatically generates a comprehensive report based on the analysis results. This report includes the background of the research, key metrics, and sentiment-based insights, providing essential insights for marketing and strategy development.

[0555] An example of a prompt would be: "Create a questionnaire to capture user expectations regarding the new product. Based on the data collected from this survey, visualize and demonstrate the emotional trends you analyzed." This allows users to go through a more personalized research process and achieve collaborative and effective data aggregation.

[0556] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0557] Step 1:

[0558] Users input research objectives and target information using a terminal. The terminal transmits this information to the server via a data receiving device. The input data, along with language patterns and input style, is recorded and serves as foundational data for sentiment analysis.

[0559] Step 2:

[0560] The server analyzes the emotional state based on the received data, using sentiment analysis tools. It processes language patterns and writing style using analysis algorithms to generate sentiment tags. This process outputs the user's positive expectations and negative concerns as quantified data.

[0561] Step 3:

[0562] Based on the results of sentiment analysis, the server automatically generates survey items using a generative AI model. The item generation method takes sentiment tags into consideration, adjusts the survey items, and designs questions that address the user's expectations and concerns. This results in a survey questionnaire that is tailored to the user.

[0563] Step 4:

[0564] The server distributes the generated questionnaires using data collection methods. The questionnaires are delivered to the target survey participants via email or a dedicated application. This output indicates the completion of questionnaire distribution.

[0565] Step 5:

[0566] Participants enter their answers via a terminal, and this data is sent to a server. The server aggregates the responses in a database in real time and processes them using analytical tools to identify emotional tendencies. The aggregated data is then used for analysis.

[0567] Step 6:

[0568] The server uses analytical tools to visualize data trends based on collected data and sentiment tags. The results, derived from statistical calculations and visualization of sentiment insights, are presented to the user via the terminal in the form of graphs and charts.

[0569] Step 7:

[0570] Ultimately, the server automatically generates a comprehensive report based on the analysis results using a reporting mechanism. The report includes background information, data analysis, and sentiment insights, and is sent to the user. The output of this step is a complete research report.

[0571] (Application Example 2)

[0572] 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."

[0573] Conventional survey and advertising creation systems fail to adequately consider users' emotional states for personalization, resulting in information gathering that does not meet user expectations and reduced advertising effectiveness. Therefore, there was a need for a means to analyze user emotions in real time and provide customized information and advertisements accordingly.

[0574] 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.

[0575] In this invention, the server includes an information receiving means for receiving survey objectives and target information from the user, an emotion analysis means for analyzing the information received by the information receiving means and determining the user's emotional state, and a data generation means for automatically generating questionnaires or advertising materials based on the emotional state determined by the emotion analysis means. This makes it possible to provide personalized information based on the user's emotional state.

[0576] An "information receiving method" is an interface for collecting information from users regarding the purpose and target of the survey.

[0577] An "emotion analysis tool" is a processing mechanism that analyzes and determines the user's emotional state based on the information received.

[0578] "Data generation means" refers to a process for automatically creating questionnaires and advertising materials based on identified emotional states.

[0579] A "data collection method" is a system for collecting response data obtained from questionnaires or advertising materials that have been created or presented.

[0580] An "analysis and display means" is a function for analyzing collected data and displaying it as a visual report that includes emotional insights.

[0581] A "result generation means" is a process that provides the functionality to automatically generate a final report based on the analysis results.

[0582] This invention is a system for providing personalized information adapted to the user's emotions. The main components necessary to realize the system are an information receiving means, an emotion analysis means, a data generation means, a data collection means, an analysis display means, and a result generation means.

[0583] The server receives information from the user regarding the purpose and target of the survey through an information receiving mechanism. This information is analyzed by an emotion analysis mechanism to determine the user's emotional state. Google Cloud Natural Language API is used as the natural language processing tool for this analysis.

[0584] Based on the identified emotional state, the server uses a generative AI model to generate questionnaires or advertising materials. OpenAI's GPT is suitable for this generation. The generated materials and questionnaires are distributed through data collection mechanisms to collect user response data.

[0585] The server stores the collected data using Firebase, analyzes it in real time using analytical display tools, and visualizes emotional insights. Tableau is used for this visualization.

[0586] Finally, the results generation system generates a detailed report based on the analysis results and provides it to the user. This allows the user to obtain results that include insights based on their emotional state.

[0587] For example, if a user inputs information such as "I want to create an advertisement that conveys the fun of a new product," the server will identify a positive emotion. Based on this emotional state, the generative AI model will prompt the system to create advertising copy that conveys a fun atmosphere.

[0588] Example prompt: "Create advertising copy that conveys a positive and fun atmosphere. The new product's features are ○○."

[0589] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0590] Step 1:

[0591] The user inputs the purpose and target information of the survey via a terminal. The entered information is sent to the server as a means of receiving information. This received information becomes the input for the next process.

[0592] Step 2:

[0593] The server uses sentiment analysis techniques to determine the user's emotional state based on the received information. Specifically, it utilizes the Google Cloud Natural Language API to analyze language patterns and identify the emotional state. The results of this analysis become the output for the next processing step.

[0594] Step 3:

[0595] The server generates questionnaires or advertising materials using a generative AI model based on the emotional state obtained through emotion analysis. OpenAI's GPT model is used to generate text that matches the emotional state. The materials generated here become the output for the next step.

[0596] Step 4:

[0597] The generated questionnaires or advertising materials are distributed to users or target audiences using data collection methods. Responses and answers to the distributed materials are collected as data. This data serves as input for analysis in the next process.

[0598] Step 5:

[0599] The server stores the data collected via Firebase and performs real-time analysis using analytical display tools. Specifically, it performs statistical analysis of the data and visualizes trends, including emotional insights. This visualized data is then used in the next step.

[0600] Step 6:

[0601] Finally, the server uses a results generation system to create a report based on the visualized data obtained. This report is provided to the user and presents detailed analytical results, including insights based on emotional state.

[0602] 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.

[0603] 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.

[0604] 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.

[0605] [Fourth Embodiment]

[0606] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0607] 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.

[0608] 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).

[0609] 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.

[0610] 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.

[0611] 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).

[0612] 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.

[0613] 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.

[0614] 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.

[0615] 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.

[0616] 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.

[0617] 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.

[0618] 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".

[0619] This invention relates to a system that efficiently supports survey work, and in particular to a technology that automates a series of processes from questionnaire design to data collection, analysis, and report creation.

[0620] When a user uses this system, they first access a terminal and enter information about the purpose and target of their research. For example, if they want to conduct market research on a new product, they would enter information such as the product's features, target customer base, and expected market information.

[0621] The server receives this input information and uses AI to automatically generate a questionnaire containing the most appropriate questions. This generated questionnaire is sent to the user's device, where the user can review the content and make any necessary modifications. The server then distributes the questionnaire via online platforms or email, reaching the intended target audience.

[0622] As data collection progresses, the server begins to aggregate incoming response data in real time. As more data is gathered, the server uses AI algorithms to perform statistical and trend analyses, displaying the results on the terminal as interactive graphs and charts. For example, the degree of interest in products by age group of the survey participants can be visualized, allowing users to intuitively recognize the trends.

[0623] Ultimately, the server automatically generates a detailed report based on the analysis results. This report includes an overview of the study, key insights, statistics, relevant graphs, and suggestions for future actions. In this way, users can quickly and efficiently make decisions based on the insights derived from the study.

[0624] As a result, this invention significantly streamlines each process of investigation work and supports more accurate and rapid decision-making, and its scope of application is wide.

[0625] The following describes the processing flow.

[0626] Step 1:

[0627] Users access the terminal and input information about the purpose and target audience of the research. Specifically, for market research on a new product, they would fill in an overview of the new product, the target customer base, and specific research items.

[0628] Step 2:

[0629] Information entered from the terminal is sent to the server. The server uses an AI algorithm to automatically generate questionnaire questions based on this information. For example, questions about the preferences and needs of the target customer group are generated.

[0630] Step 3:

[0631] The generated questionnaire is sent to the terminal, where the user reviews its contents. If any changes are needed to the content or order of the questions, the user can make corrections through the interface.

[0632] Step 4:

[0633] The server receives the revised questionnaire, and it is then distributed to the survey participants via an online platform or email. During this process, participants are provided with URLs or links that they can access.

[0634] Step 5:

[0635] Once the response data from the survey participants is collected on the server, the server begins aggregating the data in real time. Statistical information for each response is accumulated and immediately organized into a dataset for visualization.

[0636] Step 6:

[0637] The server analyzes aggregated data and performs statistical and trend analysis. It utilizes AI to identify important correlations and patterns, and generates easy-to-understand graphs and charts based on the results.

[0638] Step 7:

[0639] The generated graphs and charts are sent to the device, presenting the analysis results to the user in a visual format. Through this visualization, users can quickly grasp data trends and insights.

[0640] Step 8:

[0641] Finally, the server automatically generates a report summarizing the analysis results. The report includes the background of the study, all key findings, graphs and charts, and actionable suggestions.

[0642] Step 9:

[0643] The generated report is sent to the terminal and provided to the user. The user uses this report to apply the findings to business decision-making and strategy development.

[0644] (Example 1)

[0645] 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".

[0646] Traditional research methods often involved manual processes from questionnaire design to data collection, analysis, and report writing, resulting in significant time and effort. Furthermore, data analysis required highly specialized knowledge, hindering rapid and accurate decision-making. Additionally, determining whether the generated questionnaires were appropriate for the characteristics of the survey participants heavily depended on the experience of the person conducting the research, making efficient research difficult.

[0647] 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.

[0648] In this invention, the server includes an information input means for receiving survey objectives and target information from the user, an information generation means for automatically generating questionnaires using a generative artificial intelligence model and including optimized questions, and an information analysis means for aggregating collected data in real time, performing statistical analysis, and visualizing the results as digital graphs and charts. This automates survey work, improving work efficiency and enabling accurate and rapid decision-making.

[0649] "Information input means" refers to a means of receiving the research objectives and target information from the user, thereby obtaining basic information for the research.

[0650] "Information generation means" refers to a means of automatically generating questionnaires using a generative artificial intelligence model based on acquired information, and creating questionnaires that include optimized questions.

[0651] "Information gathering means" refers to the method of distributing generated questionnaires via digital communication and collecting response data, thereby efficiently collecting information from survey subjects.

[0652] "Information analysis tools" are means of aggregating collected data in real time, performing statistical analysis, and visualizing the results obtained as digital graphs or charts.

[0653] "Information generation means" (report generation) refers to a method that automatically generates a detailed research report based on the analysis results, including suggestions for future actions, and is intended to effectively communicate the research findings.

[0654] To properly implement this invention, it is necessary to construct a system that processes information over a network. Key components include servers, terminals, and software that connects them.

[0655] First, the user accesses the server using their device and enters the research objectives and target information. At this stage, they use a web browser such as Google Chrome or Mozilla Firefox on their device and enter the necessary information through the user interface.

[0656] The server automatically generates questionnaires using a generative artificial intelligence model based on information received from the user. This process creates optimized questions using a generative AI model such as OpenAI. For example, if the input prompt is "Generate a detailed questionnaire about fitness earphones targeting people in their 20s," the AI ​​model will generate specific questions that meet that requirement.

[0657] After the questionnaire is generated, the server distributes it via email or Google Forms. This ensures that the questionnaire is efficiently delivered to the survey participants, and as a result, the response data is collected.

[0658] The collected data is aggregated and analyzed in real time on the server. The data is structured using the Python Pandas library and visually displayed as digital graphs and charts using the Matplotlib library. This allows users to intuitively grasp the data trends.

[0659] Ultimately, the server automatically generates a detailed research report based on the analysis results. This report includes statistical analysis results, insights, and suggestions for future actions. Users can then make strategic decisions based on the generated report.

[0660] This system automates each process of the survey, significantly reducing time and effort, and enabling faster and more accurate decision-making.

[0661] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0662] Step 1:

[0663] Users access the server via their devices and input information about the purpose and target of the research. Specifically, users log in to a dedicated form using a web browser and input the research purpose, such as "market research for next-generation smartwatches." The input data is sent to the server and stored by the information input method. The data entered here forms the basis for subsequent processes.

[0664] Step 2:

[0665] The server creates and sends a prompt to the generative AI model based on the information it receives. This prompt might include something like, "Please create a survey about smartwatch features that would be of interest to users in their 20s and 30s." The generative AI model generates the most appropriate survey questions based on the prompt and returns them to the server. This generated list of questions becomes the material needed for the next data collection.

[0666] Step 3:

[0667] The server sends the generated questionnaire back to the terminal and prompts the user for confirmation. The user reviews the questions on the terminal and makes corrections if necessary. For example, the user might look at the generated questions and make a correction such as "Please add a question about smartwatch design." As a result, the revised questionnaire is finalized.

[0668] Step 4:

[0669] The server distributes the finalized questionnaire to respondents via digital distribution methods (e.g., email or online forms). The server selects from various distribution platforms, generates a survey link, and sends it to the respondents. This prepares the server for collecting response data from the survey respondents.

[0670] Step 5:

[0671] The server aggregates the received response data in real time. Using the Python Pandas library, it processes large datasets and performs necessary statistical analysis. For example, it identifies trends, calculates averages, and generates digital graphs and charts based on these results. This visual information serves as output to help users intuitively understand the analysis results.

[0672] Step 6:

[0673] The server generates a detailed report based on the analysis results. This report includes statistical insights and future recommendations, and is provided to the user. The report is automatically generated in Microsoft Word or Google Docs format and sent to the user via their device. The user can then use this information to make strategic decisions.

[0674] (Application Example 1)

[0675] 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".

[0676] In market research, the process from questionnaire design to data collection, analysis, and reporting is often done manually, resulting in challenges such as time and cost. Furthermore, real-time data visualization and presentation are difficult, often hindering rapid decision-making.

[0677] 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.

[0678] In this invention, the server includes an input means for receiving survey objectives and target information from a user; a generation means for automatically generating questionnaires based on the information received by the input means; a collection means for distributing the generated questionnaires to survey subjects and collecting response data; an analysis means for aggregating, analyzing, and visualizing the collected data in real time; and a presentation means for presenting the analysis results obtained by the analysis means in real time through a display device. This enables increased efficiency in the entire survey process and rapid decision-making through the rapid presentation of data.

[0679] "Input means" refers to a device or software for receiving information from the user regarding the purpose and subject of the investigation.

[0680] "Generation means" refers to a device or software for automatically creating questionnaires based on received information.

[0681] "Collection means" refers to a device or software for providing a generated questionnaire to the survey subjects and collecting response data.

[0682] "Analysis means" refers to a device or software that aggregates and analyzes collected data in real time and visualizes the results.

[0683] "Presentation means" refers to a device or software for presenting the analysis results obtained by the analysis means in real time through a display device.

[0684] In the system that realizes this invention, the user, server, and terminal cooperate to streamline the research process.

[0685] First, the user uses a terminal to input information about the purpose and target of the survey. The terminal is equipped with an interface to smoothly receive input from the user.

[0686] The server receives information sent from the terminal and automatically generates a questionnaire containing appropriate questions using a generative AI model. This generated questionnaire is then sent back to the terminal, where the user can review its contents and edit it as needed.

[0687] Next, the server distributes the generated questionnaires to the target group and collects the response data. This process utilizes online platforms and data transmission methods.

[0688] Once the response data is collected, the server begins aggregating and analyzing the data in real time. During this process, data analysis tools such as Python and R are used to perform statistical processing and trend analysis on the collected data.

[0689] The analysis results, including statistical information and trends, are presented in an interactive visual format. By using engines such as Unity to visualize the analysis results and presenting them through display devices such as smart glasses, users can intuitively understand the content.

[0690] Ultimately, the server automatically generates a detailed report based on the analysis results. This report includes an overview of the study, key insights, statistics, and relevant graphs, allowing users to make informed decisions.

[0691] A concrete example is its use in collecting feedback on a new product at an exhibition and deciding on the product strategy on the spot. In this way, it becomes possible to instantly select and incorporate real-time feedback into marketing activities.

[0692] An example of a prompt is: "Create a questionnaire to collect responses from target customers based on the product features of a new sports shoe. Provide instructions for building an application that analyzes and visualizes the response data in real time."

[0693] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0694] Step 1:

[0695] The user uses a terminal to input information about the purpose and target of the survey. Here, information about the attributes and purpose of the survey target is entered in text format. This input data is received by the terminal via keyboard or voice interface and sent to the server.

[0696] Step 2:

[0697] The server automatically generates a questionnaire using a generative AI model based on the received information. During this process, algorithms are applied to analyze the entered survey objectives and target information, and to design appropriate questions. The generated questionnaire is created as digital data and sent back to the terminal.

[0698] Step 3:

[0699] The terminal displays the questionnaire received by the user, allowing the user to review its contents and make corrections as needed. The user can examine the questionnaire in detail and use the editing function to modify, add, or delete questions. The edited data is then sent back to the server.

[0700] Step 4:

[0701] The server distributes the finalized questionnaires to participants and collects the response data. In this step, questionnaires are distributed to a wide range of respondents using various online platforms and data transmission methods. The response data entered by participants is stored on the server.

[0702] Step 5:

[0703] The server aggregates and analyzes the collected response data in real time and visualizes it. At this stage, software tools such as Python and R are used to statistically process the data and analyze trends and key insights. The resulting analysis is then formatted as visual data.

[0704] Step 6:

[0705] The server presents visualized analytical data to the user through a display device such as smart glasses. Here, an engine such as Unity is used to display the visual data on the smart glasses, allowing the user to understand the results intuitively in real time.

[0706] Step 7:

[0707] The server ultimately automatically generates a detailed report based on the analysis results and sends it to the user's device. This report includes a summary of the entire study, insights, and recommended actions, enabling the user to make quick decisions based on it.

[0708] 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.

[0709] This invention relates to a survey system incorporating an emotion engine, which provides a more personalized survey process by taking user emotions into consideration from questionnaire design to data collection, analysis, and final report generation.

[0710] When a user uses this system, they first input information about the research objectives and target audience into the terminal. During input, the emotion engine analyzes language patterns and input style to determine the user's emotional state. For example, when conducting market research on a product, the emotion engine recognizes expectations and concerns from the user's descriptions and generates research questions accordingly.

[0711] The server uses the results of this sentiment analysis to automatically generate an optimized questionnaire using AI. For example, if a user expresses strong expectations for a new product, questions will be created to specifically measure those expectations.

[0712] The generated questionnaires are verified by the user and then distributed to the survey participants via an online platform by the server. Once responses to the distributed questionnaires are collected, the server aggregates the data in real time and detects emotional trends from the data collected by the emotion engine.

[0713] The server also considers emotional insights related to the collected data when analyzing the aggregated data, and visualizes data patterns. These visualized graphs and charts are sent to the terminal, allowing the user to visually grasp the analysis results, including emotional trends at that time.

[0714] Ultimately, the server automatically generates a comprehensive report incorporating sentiment analysis. The report presents the background of the research, key analytical findings, and an integrated emotional perspective, enabling richer insights. Specifically, it includes suggestions on how the positive / negative emotions expressed by specific customer segments towards a product might impact marketing strategies.

[0715] In this way, the present invention provides a sensible approach to obtaining more accurate and effective survey results by understanding user emotions and tailoring the entire survey accordingly.

[0716] The following describes the processing flow.

[0717] Step 1:

[0718] Users access the terminal and input information about the purpose and target audience of the research. For example, in market research for a new product, they would input detailed information about the product's features and target customer base.

[0719] Step 2:

[0720] The terminal sends the input information to the server. The server uses an emotion engine to analyze this information and detect the user's emotional state. For example, the emotion engine might detect from the user's input that they have a positive interest.

[0721] Step 3:

[0722] The server uses an AI algorithm to automatically generate questionnaires based on the analysis results of the emotion engine. For example, if a user shows positive interest, the questionnaire will include questions designed to elicit that interest.

[0723] Step 4:

[0724] The generated questionnaire is sent to the terminal, where the user can review its contents and modify the questions as needed.

[0725] Step 5:

[0726] The revised questionnaire is sent back to the server, which then distributes it to the respondents via an online platform or email. This process provides respondents with an accessible link.

[0727] Step 6:

[0728] Once the response data from the survey participants is collected on the server, the server begins to aggregate the data in real time. Furthermore, an emotion engine analyzes the response data to identify emotional trends, for example, which questions respondents responded to positively.

[0729] Step 7:

[0730] The server visualizes the data based on aggregation and sentiment analysis results. The visualized analysis results are sent to the terminal, allowing users to visually grasp data trends, including emotional insights.

[0731] Step 8:

[0732] Ultimately, the server automatically generates a report incorporating the sentiment analysis results. The report includes a summary of the findings, key insights, and suggestions from an emotional perspective.

[0733] Step 9:

[0734] The generated report is sent to the device and presented to the user. Based on this report, the user can implement business strategies and make decisions that take emotions into account.

[0735] (Example 2)

[0736] 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".

[0737] Conventional survey systems have difficulty creating questionnaires that take users' emotions into account, and the analysis of emotional tendencies in the collected data has not been sufficient, resulting in insufficient accuracy and insight into the survey results. Therefore, there is a need for the generation of survey items that correspond to the emotional state of users and for data analysis that takes emotional tendencies into account.

[0738] 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.

[0739] In this invention, the server includes data receiving means, emotion analysis means, and item generation means. This allows for the analysis of emotions based on user input information, the generation of corresponding survey items, and further analysis of emotional tendencies from the collected data, thereby enabling the acquisition of more accurate survey results.

[0740] "Data receiving means" refers to a device or method for receiving information provided by a user and incorporating it into the system.

[0741] "Emotion analysis means" refers to a device or method for determining a user's emotions by analyzing language patterns and expression styles based on data received from the user.

[0742] "Item generation means" refers to a device or method for automatically creating items necessary for a survey based on the results of sentiment analysis.

[0743] "Data collection means" refers to a device or method for collecting response information from survey participants and storing it in a format necessary for analysis.

[0744] "Analysis means" refers to a device or method for aggregating collected data in real time, analyzing statistical and emotional trends, and visually representing them.

[0745] "Report generation means" refers to a device or method for automatically generating research results in the form of a report based on the analysis results.

[0746] This invention is a survey system that takes user emotions into consideration, and aims to be implemented comprehensively throughout the process from questionnaire design to data collection, analysis, and report creation. Its specific form is shown below.

[0747] The server uses data receiving means to receive information about the survey from the user. This means includes an interface in which the user operates a terminal to input information about the survey objectives and target objects. In particular, sentiment analysis means are used to analyze the user's input and determine the user's emotions from language patterns and input style. This is achieved by making full use of natural language processing technology and machine learning algorithms.

[0748] For example, consider a scenario where users conduct market research on a new product. They log into a research platform and input their responses to questions. The system identifies positive expectations and negative concerns as sentiment tags based on the words and writing style used. Based on these sentiment analysis results, the server automatically generates optimized research questions using a generative AI model.

[0749] The generated survey items are distributed to the target audience via data collection methods, including email and distribution through a dedicated application. The collected data is aggregated in real time by a server, and data visualization is performed based on the results of sentiment analysis. At this stage, not only is statistical analysis performed, but emotional trends are represented in graphs and charts to make them easy for users to understand.

[0750] The report generation tool then automatically generates a comprehensive report based on the analysis results. This report includes the background of the research, key metrics, and sentiment-based insights, providing essential insights for marketing and strategy development.

[0751] An example of a prompt would be: "Create a questionnaire to capture user expectations regarding the new product. Based on the data collected from this survey, visualize and demonstrate the emotional trends you analyzed." This allows users to go through a more personalized research process and achieve collaborative and effective data aggregation.

[0752] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0753] Step 1:

[0754] Users input research objectives and target information using a terminal. The terminal transmits this information to the server via a data receiving device. The input data, along with language patterns and input style, is recorded and serves as foundational data for sentiment analysis.

[0755] Step 2:

[0756] The server analyzes the emotional state based on the received data, using sentiment analysis tools. It processes language patterns and writing style using analysis algorithms to generate sentiment tags. This process outputs the user's positive expectations and negative concerns as quantified data.

[0757] Step 3:

[0758] Based on the results of sentiment analysis, the server automatically generates survey items using a generative AI model. The item generation method takes sentiment tags into consideration, adjusts the survey items, and designs questions that address the user's expectations and concerns. This results in a survey questionnaire that is tailored to the user.

[0759] Step 4:

[0760] The server distributes the generated questionnaires using data collection methods. The questionnaires are delivered to the target survey participants via email or a dedicated application. This output indicates the completion of questionnaire distribution.

[0761] Step 5:

[0762] Participants enter their answers via a terminal, and this data is sent to a server. The server aggregates the responses in a database in real time and processes them using analytical tools to identify emotional tendencies. The aggregated data is then used for analysis.

[0763] Step 6:

[0764] The server uses analytical tools to visualize data trends based on collected data and sentiment tags. The results, derived from statistical calculations and visualization of sentiment insights, are presented to the user via the terminal in the form of graphs and charts.

[0765] Step 7:

[0766] Ultimately, the server automatically generates a comprehensive report based on the analysis results using a reporting mechanism. The report includes background information, data analysis, and sentiment insights, and is sent to the user. The output of this step is a complete research report.

[0767] (Application Example 2)

[0768] 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".

[0769] Conventional survey and advertising creation systems fail to adequately consider users' emotional states for personalization, resulting in information gathering that does not meet user expectations and reduced advertising effectiveness. Therefore, there was a need for a means to analyze user emotions in real time and provide customized information and advertisements accordingly.

[0770] 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.

[0771] In this invention, the server includes an information receiving means for receiving survey objectives and target information from the user, an emotion analysis means for analyzing the information received by the information receiving means and determining the user's emotional state, and a data generation means for automatically generating questionnaires or advertising materials based on the emotional state determined by the emotion analysis means. This makes it possible to provide personalized information based on the user's emotional state.

[0772] An "information receiving method" is an interface for collecting information from users regarding the purpose and target of the survey.

[0773] An "emotion analysis tool" is a processing mechanism that analyzes and determines the user's emotional state based on the information received.

[0774] "Data generation means" refers to a process for automatically creating questionnaires and advertising materials based on identified emotional states.

[0775] A "data collection method" is a system for collecting response data obtained from questionnaires or advertising materials that have been created or presented.

[0776] An "analysis and display means" is a function for analyzing collected data and displaying it as a visual report that includes emotional insights.

[0777] A "result generation means" is a process that provides the functionality to automatically generate a final report based on the analysis results.

[0778] This invention is a system for providing personalized information adapted to the user's emotions. The main components necessary to realize the system are an information receiving means, an emotion analysis means, a data generation means, a data collection means, an analysis display means, and a result generation means.

[0779] The server receives information from the user regarding the purpose and target of the survey through an information receiving mechanism. This information is analyzed by an emotion analysis mechanism to determine the user's emotional state. Google Cloud Natural Language API is used as the natural language processing tool for this analysis.

[0780] Based on the identified emotional state, the server uses a generative AI model to generate questionnaires or advertising materials. OpenAI's GPT is suitable for this generation. The generated materials and questionnaires are distributed through data collection mechanisms to collect user response data.

[0781] The server stores the collected data using Firebase, analyzes it in real time using analytical display tools, and visualizes emotional insights. Tableau is used for this visualization.

[0782] Finally, the results generation system generates a detailed report based on the analysis results and provides it to the user. This allows the user to obtain results that include insights based on their emotional state.

[0783] For example, if a user inputs information such as "I want to create an advertisement that conveys the fun of a new product," the server will identify a positive emotion. Based on this emotional state, the generative AI model will prompt the system to create advertising copy that conveys a fun atmosphere.

[0784] Example prompt: "Create advertising copy that conveys a positive and fun atmosphere. The new product's features are ○○."

[0785] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0786] Step 1:

[0787] The user inputs the purpose and target information of the survey via a terminal. The entered information is sent to the server as a means of receiving information. This received information becomes the input for the next process.

[0788] Step 2:

[0789] The server uses sentiment analysis techniques to determine the user's emotional state based on the received information. Specifically, it utilizes the Google Cloud Natural Language API to analyze language patterns and identify the emotional state. The results of this analysis become the output for the next processing step.

[0790] Step 3:

[0791] The server generates questionnaires or advertising materials using a generative AI model based on the emotional state obtained through emotion analysis. OpenAI's GPT model is used to generate text that matches the emotional state. The materials generated here become the output for the next step.

[0792] Step 4:

[0793] The generated questionnaires or advertising materials are distributed to users or target audiences using data collection methods. Responses and answers to the distributed materials are collected as data. This data serves as input for analysis in the next process.

[0794] Step 5:

[0795] The server stores the data collected via Firebase and performs real-time analysis using analytical display tools. Specifically, it performs statistical analysis of the data and visualizes trends, including emotional insights. This visualized data is then used in the next step.

[0796] Step 6:

[0797] Finally, the server uses a results generation system to create a report based on the visualized data obtained. This report is provided to the user and presents detailed analytical results, including insights based on emotional state.

[0798] 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.

[0799] 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.

[0800] 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.

[0801] 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.

[0802] 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.

[0803] 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.

[0804] 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.

[0805] 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.

[0806] 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."

[0807] 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.

[0808] 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.

[0809] 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.

[0810] 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.

[0811] 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.

[0812] 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.

[0813] 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.

[0814] 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.

[0815] 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.

[0816] 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.

[0817] 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.

[0818] 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.

[0819] The following is further disclosed regarding the embodiments described above.

[0820] (Claim 1)

[0821] An input means for receiving the survey objective and target information from the user,

[0822] A generation means that automatically generates a questionnaire based on the information received by the input means,

[0823] A collection method for distributing generated questionnaires to survey subjects and collecting response data,

[0824] An analytical means for aggregating, analyzing, and visualizing collected data in real time,

[0825] A system including a generation means for automatically generating a report based on the analysis results obtained by the aforementioned analysis means.

[0826] (Claim 2)

[0827] The system according to claim 1, characterized in that the input means has an editing function that allows the questions to be changed according to the subject of the survey.

[0828] (Claim 3)

[0829] The system according to claim 1, characterized in that the analysis means has the function of performing statistical analysis of collected data and identifying data trends between different groups.

[0830] "Example 1"

[0831] (Claim 1)

[0832] An information input means for receiving the purpose and target information of the survey from the user,

[0833] An information generation means that, based on the information received by the aforementioned information input means, automatically generates a questionnaire using a generative artificial intelligence model and creates a questionnaire that includes optimized questions,

[0834] A means of collecting information by distributing generated questionnaires to survey subjects via digital communication and collecting response data,

[0835] An information analysis tool that aggregates collected data in real time, performs statistical analysis, and visualizes the results as digital graphs and charts,

[0836] A system that automatically generates a detailed investigation report based on the analysis results obtained by the aforementioned information analysis means, and includes an information generation means that includes suggestions for future actions.

[0837] (Claim 2)

[0838] The system according to claim 1, characterized in that the information input means has an editing function that allows the questions to be changed according to the subject of the survey.

[0839] (Claim 3)

[0840] The system according to claim 1, characterized in that the information analysis means has the function of performing statistical analysis of collected data, identifying data trends between different groups, and making suggestions based thereon.

[0841] "Application Example 1"

[0842] (Claim 1)

[0843] An input means for receiving the survey objective and target information from the user,

[0844] A generation means that automatically generates a questionnaire based on the information received by the input means,

[0845] A collection method for distributing generated questionnaires to survey subjects and collecting response data,

[0846] An analytical means for aggregating, analyzing, and visualizing collected data in real time,

[0847] A generation means that automatically generates a report based on the analysis results obtained by the aforementioned analysis means,

[0848] A presentation means for displaying data collection and analysis results in real time via a display device,

[0849] A system that includes this.

[0850] (Claim 2)

[0851] The system according to claim 1, characterized in that the input means has an editing function that allows the questions to be changed according to the survey target, and has a function that automatically improves the questions according to the purpose of the survey using a generating AI model.

[0852] (Claim 3)

[0853] The system according to claim 1, characterized in that the analysis means has the function of performing statistical analysis of collected data and identifying data trends between different groups, as well as the function of using a presentation means to present data with visual effects based on the collected response data.

[0854] "Example 2 of combining an emotion engine"

[0855] (Claim 1)

[0856] A data receiving means for receiving information from the user,

[0857] An emotion analysis means that analyzes the emotional state based on the information received by the data receiving means,

[0858] An item generation means that automatically generates survey items based on the results of the emotion analysis means,

[0859] A data collection means for distributing generated survey items and collecting response data,

[0860] An analytical means for aggregating the aforementioned response data in real time and analyzing emotional tendencies,

[0861] A system including a report generation means that automatically generates a report based on the analysis results obtained by the aforementioned analysis means.

[0862] (Claim 2)

[0863] The system according to claim 1, characterized by comprising the item generation means having an editing function that changes the question according to the input data.

[0864] (Claim 3)

[0865] The system according to claim 1, characterized by comprising the analytical means having the function of performing statistical analysis of collected data and identifying emotional trends between different groups.

[0866] "Application example 2 when combining with an emotional engine"

[0867] (Claim 1)

[0868] A means of receiving information from users regarding the purpose of the survey and the target information,

[0869] An emotion analysis means analyzes the information received by the aforementioned information receiving means and determines the user's emotional state,

[0870] A data generation means that automatically generates questionnaires or advertising materials based on the emotional state determined by the aforementioned emotion analysis means,

[0871] A data collection means for distributing or presenting generated questionnaires or advertising materials and collecting response data or user response data,

[0872] An analytical display means that aggregates and analyzes collected data in real time and visualizes it while taking emotional insights into account,

[0873] A system including a result generation means that automatically generates a report based on the analysis results obtained by the analysis display means.

[0874] (Claim 2)

[0875] The system according to claim 1, characterized in that the information receiving means has an editing function that allows for changing questions or materials according to the survey target or advertising campaign.

[0876] (Claim 3)

[0877] The system according to claim 1, characterized in that the analysis and display means has the function of performing statistical analysis of collected data, identifying data trends between different groups, and providing visualizations including emotional trends. [Explanation of Symbols]

[0878] 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. An input means for receiving the survey objective and target information from the user, A generation means that automatically generates a questionnaire based on the information received by the input means, A collection method for distributing generated questionnaires to survey subjects and collecting response data, An analytical means for aggregating, analyzing, and visualizing collected data in real time, A generation means that automatically generates a report based on the analysis results obtained by the aforementioned analysis means, A presentation means for displaying data collection and analysis results in real time via a display device, A system that includes this.

2. The system according to claim 1, characterized in that the input means has an editing function that allows the questions to be changed according to the survey target, and has a function that automatically improves the questions according to the purpose of the survey using a generating AI model.

3. The system according to claim 1, characterized in that the analysis means has the function of performing statistical analysis of collected data and identifying data trends between different groups, as well as the function of using a presentation means to present data with visual effects based on the collected response data.

Images