system

Abstract

We provide the system. [Solution] The primary means of receiving data input from users, A second means for obtaining related information from information storage based on the data input, A third means that uses the acquired information to generate the optimal question using artificial intelligence, A fourth means for formatting the generated questions and creating an electronic questionnaire, A fifth method for distributing the questionnaire to the target persons, A sixth method involves collecting and analyzing responses from the target individuals after distribution. 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 method for controlling a persona chatbot, which is 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 as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a questionnaire survey conducted within a company, there is a problem that it takes a lot of labor and time for the person in charge to create questions, while the effectiveness and reliability of the generated survey content are unclear. Also, due to this, the frequency of the survey is limited, and there is a problem that it is difficult to continuously collect opinions from employees.

Means for Solving the Problems

[0005] This invention collects data to form the basis for creating questions by using means to receive data input from users and acquiring relevant information from information storage. Furthermore, by utilizing artificial intelligence to generate optimal questions, it reduces man-hours and creates effective questionnaires in a short time. In addition, by adding means to create electronic questionnaires and distribute them to target individuals, the system simplifies the distribution of questionnaires and the collection of responses, and provides a system that enables the continuous collection of reliable data.

[0006] A "user" is someone who initiates the process of inputting data into the system and creating a questionnaire.

[0007] "Data entry" refers to the act of providing the system with specific information about the purpose of the survey and the information you want to obtain.

[0008] "Information storage" refers to databases and storage devices that store past survey results and related data.

[0009] "Artificial intelligence" is an algorithm or programming technology that analyzes data and generates optimal survey questions based on relevant theories and past results.

[0010] A "question" refers to a specific question posed to the target audience within a survey.

[0011] An "electronic questionnaire" refers to a survey form provided in a digital format, which can be distributed and answered online.

[0012] "Target audience" refers to employees who receive the survey or those who are asked to answer it.

[0013] A "response" is a record of the responses and opinions that the respondents give to the questionnaire.

[0014] "Data aggregation" is the process of compiling responses and performing statistical analysis.

[0015] "Analysis" refers to the operation of analyzing trends and patterns based on aggregation results to obtain insights.

Brief Description of Drawings

[0016] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple 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 a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiment for Carrying Out the Invention

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a 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.

[0020] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0021] In the following embodiments, a 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.

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] 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."

[0024] [First Embodiment]

[0025] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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".

[0037] This invention provides a system for users to efficiently and effectively create internal company questionnaires. This system significantly reduces time and effort by receiving data input from users, retrieving relevant information from information storage, and generating optimal questions using artificial intelligence. Furthermore, it automates the entire process of generating electronic questionnaires, distributing them to target individuals, and compiling and analyzing responses.

[0038] The server is the core of the system. After receiving data input from users, it uses natural language processing technology to analyze the input and extract relevant keywords. It then accesses the company's internal information storage to retrieve past survey results and other relevant data. This retrieved data is used as a reference for creating new surveys.

[0039] Next, the artificial intelligence module on the server starts up and generates optimal questions based on the user's objectives. The AI ​​refers to relevant theories and past survey results to construct a list of questions. This includes ranking questions based on their appropriateness and importance, and is a process for selecting the most effective questions.

[0040] The generated questions are formatted by the server as an electronic questionnaire. The questionnaire is designed in a digital format, and its interface is optimized for intuitive use by participants. This questionnaire is automatically distributed to participants by the server. Distribution methods include email and the company's internal portal site.

[0041] Participants access the survey using their devices and answer the designated questions. The responses are sent to the server in real time, and the server receives, immediately compiles, and analyzes them. The analyzed data is evaluated using statistical methods, and the server provides the results to the users.

[0042] For example, if a user wants to evaluate their satisfaction with their remote work environment, they would input "satisfaction with the remote work environment" as their objective into their device. The server would then retrieve relevant data, and artificial intelligence would generate questions such as "satisfaction with the work environment" and "quality of communication." Based on the responses collected through the distributed questionnaires, the server would create a detailed analysis of satisfaction levels and provide it to the user.

[0043] Thus, the present invention enables efficient and effective design, implementation, data collection, and analysis of questionnaires.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] Users use their devices to input the purpose of the survey and the information they want to collect. This input data is then sent to the server.

[0047] Step 2:

[0048] The server analyzes the received data using natural language processing techniques to extract relevant keywords and intents.

[0049] Step 3:

[0050] The server accesses the company's internal information storage and retrieves past survey data and internal statistics related to the extracted keywords.

[0051] Step 4:

[0052] An artificial intelligence module within the server operates to generate an optimal list of questions based on the acquired information and the input objective. This process takes into account relevant theories and past success stories.

[0053] Step 5:

[0054] The server formats the generated questions into an electronic questionnaire and optimizes the user interface. This questionnaire is designed to be easy for the respondents to understand.

[0055] Step 6:

[0056] The server initiates the distribution process, sending questionnaires to recipients via email and the company portal.

[0057] Step 7:

[0058] Users access the survey using their devices and answer the questions. The responses are sent to the server in real time.

[0059] Step 8:

[0060] The server immediately aggregates the collected responses and performs statistical analysis. This analysis reveals trends and patterns in the responses.

[0061] Step 9:

[0062] The server generates analysis results in report format and provides them to the user. This allows the user to quickly understand the degree to which the survey objectives were achieved and the opinions of employees.

[0063] (Example 1)

[0064] 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."

[0065] To conduct surveys efficiently and effectively, users need to be able to easily design questionnaires, quickly obtain relevant information, and optimize questions. However, traditional methods require a lot of time and effort for design and information acquisition, making efficient data collection difficult.

[0066] 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.

[0067] In this invention, the server includes processing means for receiving information input from users, acquisition means for acquiring relevant knowledge from a storage area, and generation means for generating optimal inquiries using a data processing device. This automates the entire process from questionnaire design to data collection and analysis, enabling efficient research.

[0068] A "user" is someone who operates this system and provides input for conducting the survey.

[0069] "Information input" refers to data that users provide to the system, including the purpose and theme of the survey.

[0070] "Processing means" refers to devices and methods for a system to receive and analyze information input from users.

[0071] A "storage area" is a storage device or space where related information and historical data are stored.

[0072] "Acquisition means" refers to the methods or devices that a system uses to acquire necessary information from its storage area.

[0073] A "data processing device" is a device that uses artificial intelligence technology to automatically generate optimal queries.

[0074] "Generation means" refers to methods or devices that create inquiries suitable for investigation based on information collected by the system.

[0075] "Investigation documents" refer to digital or paper documents presented to the patient, including any generated inquiries.

[0076] A "patient" is someone who receives the survey documents and answers the questions written therein.

[0077] "Data aggregation means" refers to methods or devices for collecting and compiling responses obtained from patients.

[0078] "Analysis means" refers to methods or devices for analyzing aggregated responses and deriving survey results.

[0079] Modes for carrying out the invention

[0080] The system implementing this invention enables users to create and conduct questionnaires efficiently and effectively. By combining multiple means, this system aims to reduce the burden on users while obtaining highly accurate survey results.

[0081] The user enters the purpose and theme of the survey into the terminal. The terminal processes the entered information and sends it to the server. The server analyzes this information using natural language processing technology. Through this analysis, relevant keywords and themes can be extracted. Software called a natural language processing engine is used for this analysis.

[0082] The server accesses the company's internal database based on the analyzed results. The database stores past survey results and related information, and by retrieving this information, the server collects useful data for designing the survey.

[0083] Next, a data processing unit on the server uses artificial intelligence technology to generate the most suitable list of questions. This process utilizes a generative AI model. This model has the ability to create questions that are appropriate for the user's purpose by referencing the results of past surveys and related theories. For example, a prompt such as "Generate questions to evaluate satisfaction with the remote work environment" might be used.

[0084] The generated questions are formatted by the server as electronic questionnaires, presented in a way that is intuitively easy for respondents to answer. Digital formatting design tools are used for this process. The completed questionnaires are distributed to respondents via email or the company portal.

[0085] Participants will answer this questionnaire using a terminal. The responses will be sent to the server in real time, and the server will immediately organize the data using an aggregation module. Subsequently, statistical analysis will be performed through analytical tools, and the results will be reflected in the results provided to the user.

[0086] Thus, the present invention is a system that automates a series of processes, enabling efficient and simple questionnaire creation and data collection for users.

[0087] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0088] Step 1:

[0089] The user fills in the purpose and theme for creating the survey in the input form on the device. The information entered is in text format, and this information serves as the system's initial data. The device sends this information to the server as digital data.

[0090] Step 2:

[0091] The server receives information sent from the terminal and analyzes it using natural language processing technology. This analysis extracts relevant keywords and issues. The input data is theme information entered by the user, and the output is a list of keywords obtained from the analysis. A natural language processing engine is used in this analysis process.

[0092] Step 3:

[0093] The server queries the company's internal database based on the extracted keywords to retrieve relevant information. The input is a keyword list, and the database search outputs relevant past survey data and additional knowledge. This collects data that can be used as a reference for creating questionnaires.

[0094] Step 4:

[0095] The data processing unit on the server generates optimal questions using a generative AI model based on the acquired information. In this process, relevant prompt sentences are supplied to the generative AI model, giving instructions such as, "Extract the most suitable questions from similar past survey results and create a list." The input is a collection of acquired information, and the output is a list of questions.

[0096] Step 5:

[0097] The server formats the generated questions and creates an electronic questionnaire. Using design tools, the questions are transformed into a natural and easy-to-read format. The input is a list of questions, and the output is a digital questionnaire. This questionnaire is designed with usability in mind.

[0098] Step 6:

[0099] The server distributes the questionnaires to the respondents. Specifically, it sends the questionnaires using an email distribution system or an internal information sharing platform. The input is a digital questionnaire, and the output is the questionnaire received on each respondent's device.

[0100] Step 7:

[0101] Participants access the distributed questionnaire using a terminal and answer the questions. The responses are transmitted to the server in real time in digital format. The input is the participant's response, and the output is the response data.

[0102] Step 8:

[0103] The server aggregates the received response data and performs analysis using analytical tools. During this process, statistical methods are used to reveal data trends. The input is the response data, and the output is the analysis results, which are provided to the user as a visual report.

[0104] (Application Example 1)

[0105] 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."

[0106] While there is a need to improve safety awareness and the working environment in factory settings, there is a problem in efficiently collecting feedback from workers and quickly identifying issues in the work environment. The present invention aims to solve these problems and provide a system that contributes to improving workers' safety awareness and the working environment.

[0107] 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.

[0108] In this invention, the server includes means for receiving data input from users, means for acquiring relevant information from an information storage device, means for generating optimal questions using machine learning technology, means for a robot to present a survey form to a target individual and collect responses, and means for detecting areas for improvement in the on-site environment. This makes it possible to efficiently conduct surveys on safety awareness and to quickly improve the on-site environment.

[0109] The "first method" is a mechanism for receiving data input from users.

[0110] The "second method" is a mechanism that retrieves relevant information from an information storage device based on data input from the user.

[0111] The "third method" is a mechanism that uses acquired information to generate optimal questions using machine learning technology.

[0112] The "fourth method" is a mechanism that formats the generated questions and creates an electronic survey form.

[0113] The "fifth method" is a mechanism for distributing survey forms to target individuals.

[0114] The "sixth method" is a mechanism for collecting and evaluating responses from target individuals after distribution.

[0115] The "seventh method" is a mechanism in which a robot presents a survey form to the target individual and collects their responses.

[0116] The "eighth method" is a mechanism for detecting areas for improvement in the on-site environment based on the collected responses.

[0117] "Machine learning technology" is a technique that uses algorithms to analyze data and use that information to generate questions and evaluate answers.

[0118] In this invention, a server is central to operating the system. The server first receives safety-related data input from users via terminals. The received data is analyzed using natural language processing technology within the server, and relevant information is retrieved from information storage devices. In particular, data on past work environments and standard safety guidelines are referenced.

[0119] Next, machine learning technology on the server is used to automatically generate optimal questions. In this generation process, the appropriateness and importance of the questions are evaluated based on relevant theories and past research results, and finally an electronic survey form is created. This survey form is sent to a robot via a terminal and presented to the worker by the robot.

[0120] The robot autonomously moves around the factory, presenting survey forms to workers and collecting responses in real time. The collected response data is sent to a server, where an evaluation algorithm identifies areas for improvement in the work environment. These results are immediately reported to factory managers, facilitating improvements on-site.

[0121] For example, if a new machine is introduced at a factory, the server can input a prompt message such as "Please create questions about the work environment after the introduction of the new equipment" into the AI ​​model, and then conduct a survey using the resulting questions.

[0122] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0123] Step 1:

[0124] The server accepts data input from users via a terminal. Users input data related to new safety standards, and this input data is analyzed using natural language processing technology. The results of the analysis include relevant keywords and contextual information.

[0125] Step 2:

[0126] Based on the analysis results, the server retrieves relevant past survey results and reference data from its information storage device. During this process, the retrieved data is filtered to select the information most relevant to the user's input.

[0127] Step 3:

[0128] The server uses the acquired information to leverage a machine learning model to generate optimal questions. A prompt such as "Please create questions about the workplace environment after the introduction of new equipment" is input, and the AI ​​model generates questions based on this.

[0129] Step 4:

[0130] The server formats the generated questions and creates an electronic survey form. During the formatting process, the layout and usability of the questions are optimized, resulting in an intuitive interface.

[0131] Step 5:

[0132] The terminal sends a survey form to the robot, which then uses it to present it to the worker. The robot moves around the factory and conducts the survey with the corresponding worker. This is coordinated by the robot's motion planning algorithm.

[0133] Step 6:

[0134] The robot collects responses from workers in real time and sends them to a server via a terminal. The response data is designed to be analyzed immediately, ensuring efficient data collection.

[0135] Step 7:

[0136] The server uses an analysis algorithm to detect areas for improvement in the field environment from the response data. The results of the analysis include specific areas requiring improvement and suggestions for improvement.

[0137] Step 8:

[0138] The server reports the analysis results to the factory manager and proposes necessary corrective actions. Based on these results, the manager promotes appropriate improvements to the on-site environment.

[0139] 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.

[0140] This invention relates to a system that, when receiving data input from a user, uses an emotion engine to recognize the user's emotions and generates optimal questions based on those emotions. This system creates questionnaires that take the user's emotional state into account, allowing for deeper insights.

[0141] The server uses an emotion engine to analyze emotional elements based on the text data received from the user. This emotion engine combines natural language processing technology and machine learning models to identify the emotional nuances contained in the sentences entered by the user.

[0142] Using the analyzed sentiment data, an artificial intelligence module on the server activates to generate an optimal set of questions that correspond to the user's emotional state. The generated questions are designed to encourage the user to respond more sincerely, taking into account how the questions relate to the user's current emotions.

[0143] After generating the questions, the server formats them into an electronic questionnaire. The questionnaire is designed to be intuitive and easy for respondents to answer. The questionnaire is then distributed to respondents through a designated medium.

[0144] Users answer the survey using their devices. The server collects the responses in real time and performs detailed statistical analysis, including sentiment analysis. The analyzed results are compiled into a report that reflects the user's emotional state and delivered to the information provider.

[0145] For example, if a user is dissatisfied with remote work, the emotion engine analyzes that dissatisfaction and generates questions about stress and fatigue. The data collected in this way can be used not only to improve the work environment but also to implement measures that take into account the psychological support of employees.

[0146] Thus, by incorporating emotion recognition, the present invention enhances the added value of the survey system and enables more reliable data collection.

[0147] The following describes the processing flow.

[0148] Step 1:

[0149] Users use their devices to input data, including the purpose of the survey and the information they want to know. The entered data is then sent to the server.

[0150] Step 2:

[0151] The server inputs the received data into an emotion engine, which uses natural language processing technology to analyze the emotional state of the text entered by the user. In this process, emotional nuances and keywords contained in the text are identified.

[0152] Step 3:

[0153] The server accesses the company's internal information storage and searches for past survey data and internal resources related to the extracted emotions. This integrates the results of the emotion analysis with the historical data.

[0154] Step 4:

[0155] An artificial intelligence module within the server generates a list of questions best suited to the user's emotional state based on this integrated data. This generation process reflects past success stories and relevant theories, selecting effective questions that align with the user's emotions.

[0156] Step 5:

[0157] The server formats the generated questions into an electronic questionnaire and optimizes the user interface. The questionnaire is designed to be intuitive and easy for respondents to answer.

[0158] Step 6:

[0159] The server handles the process of distributing questionnaires to the target individuals, which are then provided via email or the company's internal portal.

[0160] Step 7:

[0161] Users access the distributed survey using their device and enter their answers to the generated questions. The answers are immediately sent to the server.

[0162] Step 8:

[0163] The server aggregates responses in real time and performs detailed statistical analysis, including sentiment analysis results. In this process, the collected data is trended and patterns are identified.

[0164] Step 9:

[0165] The server generates a report based on the analysis results and provides it to the user. This report includes data insights linked to the user's emotional state, which can be used to develop practical strategies.

[0166] (Example 2)

[0167] 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".

[0168] Conventional data collection systems have struggled to generate flexible questions that take into account the emotional state of users, making it difficult to improve the accuracy and reliability of the data. Furthermore, there was a need for a mechanism that could generate questions appropriate to the emotions of the target audience and gain deeper insights.

[0169] 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.

[0170] In this invention, the server includes means for receiving information from the user and analyzing the natural state, means for generating optimal inquiries using generative artificial intelligence, and means for formatting the generated inquiries and creating an electronic questionnaire. This enables the generation of questions based on the user's emotional state and the collection of highly accurate data.

[0171] A "user" is an individual or legal entity that operates the system and provides or receives information.

[0172] "Information" refers to the text and data entered into a system, and analysis and processing are performed based on their content.

[0173] "Natural state" refers to the emotional or psychological nuances contained in the text data entered by the user.

[0174] "Emotional information" refers to data that indicates the user's emotions and psychological state, identified through natural language processing.

[0175] "Generative artificial intelligence" is a technology that uses machine learning models to generate optimal inquiries and creative content based on input information.

[0176] An "inquiry" refers to a question or command that is generated based on the user's emotions or state of mind.

[0177] An "electronic questionnaire" is a set of questions formatted in a digital format, used to conduct surveys with recipients.

[0178] "Statistical analysis" is a method for quantitatively analyzing collected data to identify trends and patterns.

[0179] This invention provides a system for generating questions based on the user's emotional state. First, the server receives information transmitted from the user via a terminal. This information includes feedback and comments. The received information is analyzed using natural language processing technology to identify the user's natural state, i.e., emotional or psychological nuances. Specifically, a machine learning model is used as the emotion engine to tokenize text and calculate an emotion score.

[0180] Based on the analyzed emotional information, the generative artificial intelligence on the server generates the most appropriate inquiry. In this process, a generative AI model is used to create prompts that match the user's emotional state, and then the question is designed based on these prompts. For example, if a user inputs "I am feeling stressed about remote work," the emotional engine can analyze that emotion and generate a question such as, "What kind of support do you think would be effective in alleviating the stress you feel while working remotely?"

[0181] The generated inquiries are formatted by the server and provided to the user as an electronic questionnaire. This questionnaire is designed to be easy for respondents to understand and answer. The questionnaire is distributed via email or a dedicated app, and users answer it using their devices.

[0182] The collected responses are aggregated on a server and statistically analyzed. In particular, by integrating sentiment analysis, it is possible to understand the changes and trends in users' emotions in detail. Based on this, the analysis results are created as a report and sent to the information provider. The analysis results are visualized in graphs and charts, providing information that accurately represents the user's emotional state, such as "stress tendencies in remote work."

[0183] An example of a prompt message is, "Analyze the user's sentiment from their input text and generate appropriate survey questions." In this way, flexible and highly accurate data collection tailored to the user's emotions is achieved.

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

[0185] Step 1:

[0186] The server receives information sent from the user via the terminal. This information includes user feedback and comments in text format. The server then temporarily stores the received data for analysis in the next step.

[0187] Step 2:

[0188] The server begins analyzing the received text data using natural language processing techniques. Specifically, it tokenizes the text and performs data calculations to identify emotional nuances using an emotion engine. The output of this analysis is data with an emotion score assigned to each word.

[0189] Step 3:

[0190] The server uses generative artificial intelligence to generate optimal questions, taking the emotional information obtained from the analysis as input. Here, the generative AI model operates, constructing prompt sentences based on the user's natural state, and designing a set of questions based on those prompts. The output of this step is the specific set of questions to be presented to the user.

[0191] Step 4:

[0192] The server formats the generated set of questions and creates an electronic questionnaire in a user-friendly format. Specifically, it adjusts the layout of the questionnaire and designs an interface that allows users to intuitively input their answers. The output is a distributable digital questionnaire.

[0193] Step 5:

[0194] The server distributes electronic questionnaires to users via email or app. The terminal opens the received questionnaire and provides functionality to enable users to enter their answers. The output in this step is the questionnaire in a state accessible to the user.

[0195] Step 6:

[0196] The user answers a questionnaire and sends it to the server via their device. The server receives the response data as input in real time and performs aggregation. It also performs sentiment analysis again and processes the data based on the aggregation results. The output of this step is aggregated data that includes the response data and the analysis results.

[0197] Step 7:

[0198] The server performs detailed statistical analysis based on the aggregated data and creates a report of the analysis results. Specifically, it generates graphs and charts to visually represent the user's emotional state and response trends. This report is then distributed to the information provider.

[0199] (Application Example 2)

[0200] 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".

[0201] When collecting customer feedback in physical stores, traditional surveys often fail to consider customer emotions, making it difficult to grasp true needs and problems. Furthermore, delays in addressing customer dissatisfaction can lead to decreased customer satisfaction.

[0202] 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.

[0203] In this invention, the server includes means for receiving data input from a user, means for recognizing the user's emotions using an emotion engine based on the data input, and means for generating optimal questions using artificial intelligence based on the recognized emotions. This makes it possible to quickly generate detailed and accurate questions based on customer emotions and improve the quality of surveys.

[0204] "Users" refer to end users who use this system and provide data.

[0205] "Data entry" refers to the information and feedback that users provide to the system.

[0206] An "emotion engine" is a processing device used to analyze the emotional elements contained in the user's data input.

[0207] "Recognizing emotions" refers to the process of identifying a user's emotional state from the input data.

[0208] Artificial intelligence is a technology that uses machine learning models to mimic human intellectual work.

[0209] "Generating questions" is the process of constructing appropriate questions based on user input data.

[0210] A "questionnaire" is a collection of questions presented to a user.

[0211] "Emotional analysis" is a technique that analyzes user response data to identify emotional tendencies.

[0212] The system implementing this invention understands the emotions of users when they provide feedback in a physical store and generates appropriate questions. The central components of this system include a server, a terminal, and an emotion engine.

[0213] The server accepts data input through terminals available in the store and through users' mobile devices. This data input includes free-form text and specific feedback from users, and the server receives this information in real time.

[0214] Next, the server uses an emotion engine to analyze the input text data and recognize the user's emotional state. This emotion engine utilizes technologies such as Google's Cloud Natural Language API or similar natural language processing (NLP) techniques to extract emotional characteristics such as positive, negative, and neutral from the user's statements.

[0215] After the emotional state is identified, an artificial intelligence module on the server activates and generates individually optimized questions using a generative AI model. This question generation process utilizes OpenAI®'s GPT-3® or other similar natural language generation models. The AI ​​module appropriately formats questions according to the user's emotional state and presents them immediately to the user's device, improving the user experience.

[0216] As a concrete example of this system, if a user enters dissatisfaction with a service delay, the emotion engine identifies the negative emotion and instantly generates and presents a question to the user such as, "We apologize for the delay. Specifically, which service improvements would you like to see?"

[0217] An example of a prompt for the generative AI model is: "Analyze the customer's sentiment from the following text and generate the most appropriate question based on that sentiment. Text: {customer input text}".

[0218] In this way, we aim to create a system that enhances the emotional basis of user interaction, contributing to improved store services and increased customer satisfaction.

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

[0220] Step 1:

[0221] The server accepts data input from the user's terminal. This data input consists of text information provided by the user. The server temporarily stores the received input data and prepares it for subsequent processing.

[0222] Step 2:

[0223] The server analyzes the input text data using an emotion engine. This emotion engine processes the input data using natural language processing techniques and classifies the user's emotional state as positive, negative, or neutral. Based on the analysis, it outputs tags and scores corresponding to the user's emotions.

[0224] Step 3:

[0225] An artificial intelligence module on the server uses a generative AI model to generate optimal questions based on the user's emotions. An example of a prompt is: "Analyze the customer's emotions from the following text and generate the optimal question based on those emotions. Text: {User input text}". This prompt is input to the AI ​​model, which then outputs an appropriate question.

[0226] Step 4:

[0227] The server formats the generated questions and converts them into a format that can be displayed on the user's device. By presenting questions in a format that is most relevant to the user's emotions, it enhances user engagement.

[0228] Step 5:

[0229] The terminal presents the user with a formatted question. The user answers the question, and the answer is sent back to the server. The server collects the user's answers in real time and stores them for further sentiment analysis.

[0230] Step 6:

[0231] The server performs statistical analysis, including sentiment analysis, based on the collected data. Based on the results of this analysis, it generates reports to improve the service quality of physical stores and provides them to managers and relevant parties.

[0232] 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.

[0233] 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.

[0234] 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.

[0235] [Second Embodiment]

[0236] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0237] 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.

[0238] 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).

[0239] 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.

[0240] 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.

[0241] 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).

[0242] 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.

[0243] 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.

[0244] 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.

[0245] 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.

[0246] 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.

[0247] 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".

[0248] This invention provides a system for users to efficiently and effectively create internal company questionnaires. This system significantly reduces time and effort by receiving data input from users, retrieving relevant information from information storage, and generating optimal questions using artificial intelligence. Furthermore, it automates the entire process of generating electronic questionnaires, distributing them to target individuals, and compiling and analyzing responses.

[0249] The server is the core of the system. After receiving data input from users, it uses natural language processing technology to analyze the input and extract relevant keywords. It then accesses the company's internal information storage to retrieve past survey results and other relevant data. This retrieved data is used as a reference for creating new surveys.

[0250] Next, the artificial intelligence module on the server starts up and generates optimal questions based on the user's objectives. The AI ​​refers to relevant theories and past survey results to construct a list of questions. This includes ranking questions based on their appropriateness and importance, and is a process for selecting the most effective questions.

[0251] The generated questions are formatted by the server as an electronic questionnaire. The questionnaire is designed in a digital format, and its interface is optimized for intuitive use by participants. This questionnaire is automatically distributed to participants by the server. Distribution methods include email and the company's internal portal site.

[0252] Participants access the survey using their devices and answer the designated questions. The responses are sent to the server in real time, and the server receives, immediately compiles, and analyzes them. The analyzed data is evaluated using statistical methods, and the server provides the results to the users.

[0253] For example, if a user wants to evaluate their satisfaction with their remote work environment, they would input "satisfaction with the remote work environment" as their objective into their device. The server would then retrieve relevant data, and artificial intelligence would generate questions such as "satisfaction with the work environment" and "quality of communication." Based on the responses collected through the distributed questionnaires, the server would create a detailed analysis of satisfaction levels and provide it to the user.

[0254] Thus, the present invention enables efficient and effective design, implementation, data collection, and analysis of questionnaires.

[0255] The following describes the processing flow.

[0256] Step 1:

[0257] Users use their devices to input the purpose of the survey and the information they want to collect. This input data is then sent to the server.

[0258] Step 2:

[0259] The server analyzes the received data using natural language processing techniques to extract relevant keywords and intents.

[0260] Step 3:

[0261] The server accesses the company's internal information storage and retrieves past survey data and internal statistics related to the extracted keywords.

[0262] Step 4:

[0263] An artificial intelligence module within the server operates to generate an optimal list of questions based on the acquired information and the input objective. This process takes into account relevant theories and past success stories.

[0264] Step 5:

[0265] The server formats the generated questions into an electronic questionnaire and optimizes the user interface. This questionnaire is designed to be easy for the respondents to understand.

[0266] Step 6:

[0267] The server initiates the distribution process, sending questionnaires to recipients via email and the company portal.

[0268] Step 7:

[0269] Users access the survey using their devices and answer the questions. The responses are sent to the server in real time.

[0270] Step 8:

[0271] The server immediately aggregates the collected responses and performs statistical analysis. This analysis reveals trends and patterns in the responses.

[0272] Step 9:

[0273] The server generates analysis results in report format and provides them to the user. This allows the user to quickly understand the degree to which the survey objectives were achieved and the opinions of employees.

[0274] (Example 1)

[0275] 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."

[0276] To conduct surveys efficiently and effectively, users need to be able to easily design questionnaires, quickly obtain relevant information, and optimize questions. However, traditional methods require a lot of time and effort for design and information acquisition, making efficient data collection difficult.

[0277] 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.

[0278] In this invention, the server includes processing means for receiving information input from users, acquisition means for acquiring relevant knowledge from a storage area, and generation means for generating optimal inquiries using a data processing device. This automates the entire process from questionnaire design to data collection and analysis, enabling efficient research.

[0279] "User" refers to a person who operates this system and provides inputs for conducting an investigation.

[0280] "Information input" refers to the data provided by the user to the system, including the purpose and theme of the questionnaire.

[0281] "Processing means" refers to a device or method by which the system receives and analyzes information input from the user.

[0282] "Storage area" refers to a storage device or space where related information and past data are stored.

[0283] "Acquisition means" refers to a method or device by which the system acquires necessary information from the storage area.

[0284] "Data processing device" refers to a device that automatically generates optimal inquiries using artificial intelligence technology.

[0285] "Generation means" refers to a method or device by which the system creates inquiries suitable for the investigation based on the information collected.

[0286] "Investigation document" refers to a digital or paper document presented to the examinee, including the generated inquiries.

[0287] "Examinee" refers to a person who receives the investigation document and answers the inquiries described therein.

[0288] "Aggregation means" refers to a method or device that collects and summarizes the responses obtained from the examinees.

[0289] "Analysis means" refers to a method or device that analyzes the aggregated responses and derives the investigation results.

[0290] Modes for Carrying Out the Invention

[0291] The system implementing this invention enables users to create and conduct questionnaires efficiently and effectively. By combining multiple means, this system aims to reduce the burden on users while obtaining highly accurate survey results.

[0292] The user enters the purpose and theme of the survey into the terminal. The terminal processes the entered information and sends it to the server. The server analyzes this information using natural language processing technology. Through this analysis, relevant keywords and themes can be extracted. Software called a natural language processing engine is used for this analysis.

[0293] The server accesses the company's internal database based on the analyzed results. The database stores past survey results and related information, and by retrieving this information, the server collects useful data for designing the survey.

[0294] Next, a data processing unit on the server uses artificial intelligence technology to generate the most suitable list of questions. This process utilizes a generative AI model. This model has the ability to create questions that are appropriate for the user's purpose by referencing the results of past surveys and related theories. For example, a prompt such as "Generate questions to evaluate satisfaction with the remote work environment" might be used.

[0295] The generated questions are formatted by the server as electronic questionnaires, presented in a way that is intuitively easy for respondents to answer. Digital formatting design tools are used for this process. The completed questionnaires are distributed to respondents via email or the company portal.

[0296] Participants will answer this questionnaire using a terminal. The responses will be sent to the server in real time, and the server will immediately organize the data using an aggregation module. Subsequently, statistical analysis will be performed through analytical tools, and the results will be reflected in the results provided to the user.

[0297] Thus, the present invention is a system that automates a series of processes, enabling efficient and simple questionnaire creation and data collection for users.

[0298] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0299] Step 1:

[0300] The user fills in the purpose and theme for creating the survey in the input form on the device. The information entered is in text format, and this information serves as the system's initial data. The device sends this information to the server as digital data.

[0301] Step 2:

[0302] The server receives information sent from the terminal and analyzes it using natural language processing technology. This analysis extracts relevant keywords and issues. The input data is theme information entered by the user, and the output is a list of keywords obtained from the analysis. A natural language processing engine is used in this analysis process.

[0303] Step 3:

[0304] The server queries the company's internal database based on the extracted keywords to retrieve relevant information. The input is a keyword list, and the database search outputs relevant past survey data and additional knowledge. This collects data that can be used as a reference for creating questionnaires.

[0305] Step 4:

[0306] The data processing device in the server generates an optimal question using a generative AI model based on the acquired information. In this process, relevant prompt sentences are supplied to the generative AI model, giving an instruction such as "Extract the optimal questions from similar past questionnaire results and list them." The input is the set of acquired information, and the output is a list of questions.

[0307] Step 5:

[0308] The server formats the generated questions and creates an electronic questionnaire. Using a design tool, the questions are converted into a natural and easy-to-read format. The input is the list of questions, and the output is a digital-format questionnaire. This questionnaire is designed considering user usability.

[0309] Step 6:

[0310] The server distributes the questionnaire to the target persons. As a specific operation, the questionnaire is sent using a mail delivery system or an in-house information sharing platform. The input is the digital-format questionnaire, and the output is the questionnaire received on each target person's terminal.

[0311] Step 7:

[0312] The target persons access the distributed questionnaire using their terminals and answer the questions. The answers are sent to the server in digital format in real time. The input is the target persons' answers, and the output is the answer data.

[0313] Step 8:

[0314] The server aggregates the received answer data and performs analysis through analysis means. In this process, statistical methods are used to clarify the data trends. The input is the answer data, and the output is the analysis result, which is provided to the user as a visual report.

[0315] (Application Example Ⅰ)

[0316] 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 glasses 214 will be referred to as the "terminal."

[0317] While there is a need to improve safety awareness and the working environment in factory settings, there is a problem in efficiently collecting feedback from workers and quickly identifying issues in the work environment. The present invention aims to solve these problems and provide a system that contributes to improving workers' safety awareness and the working environment.

[0318] 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.

[0319] In this invention, the server includes means for receiving data input from users, means for acquiring relevant information from an information storage device, means for generating optimal questions using machine learning technology, means for a robot to present a survey form to a target individual and collect responses, and means for detecting areas for improvement in the on-site environment. This makes it possible to efficiently conduct surveys on safety awareness and to quickly improve the on-site environment.

[0320] The "first method" is a mechanism for receiving data input from users.

[0321] The "second method" is a mechanism that retrieves relevant information from an information storage device based on data input from the user.

[0322] The "third method" is a mechanism that uses acquired information to generate optimal questions using machine learning technology.

[0323] The "fourth method" is a mechanism that formats the generated questions and creates an electronic survey form.

[0324] The "fifth method" is a mechanism for distributing survey forms to target individuals.

[0325] The "sixth method" is a mechanism for collecting and evaluating responses from target individuals after distribution.

[0326] The "seventh method" is a mechanism in which a robot presents a survey form to the target individual and collects their responses.

[0327] The "eighth method" is a mechanism for detecting areas for improvement in the on-site environment based on the collected responses.

[0328] "Machine learning technology" is a technique that uses algorithms to analyze data and use that information to generate questions and evaluate answers.

[0329] In this invention, a server is central to operating the system. The server first receives safety-related data input from users via terminals. The received data is analyzed using natural language processing technology within the server, and relevant information is retrieved from information storage devices. In particular, data on past work environments and standard safety guidelines are referenced.

[0330] Next, machine learning technology on the server is used to automatically generate optimal questions. In this generation process, the appropriateness and importance of the questions are evaluated based on relevant theories and past research results, and finally an electronic survey form is created. This survey form is sent to a robot via a terminal and presented to the worker by the robot.

[0331] The robot autonomously moves around the factory, presenting survey forms to workers and collecting responses in real time. The collected response data is sent to a server, where an evaluation algorithm identifies areas for improvement in the work environment. These results are immediately reported to factory managers, facilitating improvements on-site.

[0332] For example, if a new machine is introduced at a factory, the server can input a prompt message such as "Please create questions about the work environment after the introduction of the new equipment" into the AI ​​model, and then conduct a survey using the resulting questions.

[0333] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0334] Step 1:

[0335] The server accepts data input from users via a terminal. Users input data related to new safety standards, and this input data is analyzed using natural language processing technology. The results of the analysis include relevant keywords and contextual information.

[0336] Step 2:

[0337] Based on the analysis results, the server retrieves relevant past survey results and reference data from its information storage device. During this process, the retrieved data is filtered to select the information most relevant to the user's input.

[0338] Step 3:

[0339] The server uses the acquired information to leverage a machine learning model to generate optimal questions. A prompt such as "Please create questions about the workplace environment after the introduction of new equipment" is input, and the AI ​​model generates questions based on this.

[0340] Step 4:

[0341] The server formats the generated questions and creates an electronic survey form. During the formatting process, the layout and usability of the questions are optimized, resulting in an intuitive interface.

[0342] Step 5:

[0343] The terminal sends a survey form to the robot, which then uses it to present it to the worker. The robot moves around the factory and conducts the survey with the corresponding worker. This is coordinated by the robot's motion planning algorithm.

[0344] Step 6:

[0345] The robot collects responses from workers in real time and sends them to a server via a terminal. The response data is designed to be analyzed immediately, ensuring efficient data collection.

[0346] Step 7:

[0347] The server uses an analysis algorithm to detect areas for improvement in the field environment from the response data. The results of the analysis include specific areas requiring improvement and suggestions for improvement.

[0348] Step 8:

[0349] The server reports the analysis results to the factory manager and proposes necessary corrective actions. Based on these results, the manager promotes appropriate improvements to the on-site environment.

[0350] 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.

[0351] This invention relates to a system that, when receiving data input from a user, uses an emotion engine to recognize the user's emotions and generates optimal questions based on those emotions. This system creates questionnaires that take the user's emotional state into account, allowing for deeper insights.

[0352] The server uses an emotion engine to analyze emotional elements based on the text data received from the user. This emotion engine combines natural language processing technology and machine learning models to identify the emotional nuances contained in the sentences entered by the user.

[0353] Using the analyzed sentiment data, an artificial intelligence module on the server activates to generate an optimal set of questions that correspond to the user's emotional state. The generated questions are designed to encourage the user to respond more sincerely, taking into account how the questions relate to the user's current emotions.

[0354] After generating the questions, the server formats them into an electronic questionnaire. The questionnaire is designed to be intuitive and easy for respondents to answer. The questionnaire is then distributed to respondents through a designated medium.

[0355] Users answer the survey using their devices. The server collects the responses in real time and performs detailed statistical analysis, including sentiment analysis. The analyzed results are compiled into a report that reflects the user's emotional state and delivered to the information provider.

[0356] For example, if a user is dissatisfied with remote work, the emotion engine analyzes that dissatisfaction and generates questions about stress and fatigue. The data collected in this way can be used not only to improve the work environment but also to implement measures that take into account the psychological support of employees.

[0357] Thus, by incorporating emotion recognition, the present invention enhances the added value of the survey system and enables more reliable data collection.

[0358] The following describes the processing flow.

[0359] Step 1:

[0360] Users use their devices to input data, including the purpose of the survey and the information they want to know. The entered data is then sent to the server.

[0361] Step 2:

[0362] The server inputs the received data into an emotion engine, which uses natural language processing technology to analyze the emotional state of the text entered by the user. In this process, emotional nuances and keywords contained in the text are identified.

[0363] Step 3:

[0364] The server accesses the company's internal information storage and searches for past survey data and internal resources related to the extracted emotions. This integrates the results of the emotion analysis with the historical data.

[0365] Step 4:

[0366] An artificial intelligence module within the server generates a list of questions best suited to the user's emotional state based on this integrated data. This generation process reflects past success stories and relevant theories, selecting effective questions that align with the user's emotions.

[0367] Step 5:

[0368] The server formats the generated questions into an electronic questionnaire and optimizes the user interface. The questionnaire is designed to be intuitive and easy for respondents to answer.

[0369] Step 6:

[0370] The server handles the process of distributing questionnaires to the target individuals, which are then provided via email or the company's internal portal.

[0371] Step 7:

[0372] Users access the distributed survey using their device and enter their answers to the generated questions. The answers are immediately sent to the server.

[0373] Step 8:

[0374] The server aggregates responses in real time and performs detailed statistical analysis, including sentiment analysis results. In this process, the collected data is trended and patterns are identified.

[0375] Step 9:

[0376] The server generates a report based on the analysis results and provides it to the user. This report includes data insights linked to the user's emotional state, which can be used to develop practical strategies.

[0377] (Example 2)

[0378] 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".

[0379] Conventional data collection systems have struggled to generate flexible questions that take into account the emotional state of users, making it difficult to improve the accuracy and reliability of the data. Furthermore, there was a need for a mechanism that could generate questions appropriate to the emotions of the target audience and gain deeper insights.

[0380] 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.

[0381] In this invention, the server includes means for receiving information from the user and analyzing the natural state, means for generating optimal inquiries using generative artificial intelligence, and means for formatting the generated inquiries and creating an electronic questionnaire. This enables the generation of questions based on the user's emotional state and the collection of highly accurate data.

[0382] A "user" is an individual or legal entity that operates the system and provides or receives information.

[0383] "Information" refers to the text and data entered into a system, and analysis and processing are performed based on their content.

[0384] "Natural state" refers to the emotional or psychological nuances contained in the text data entered by the user.

[0385] "Emotional information" refers to data that indicates the user's emotions and psychological state, identified through natural language processing.

[0386] "Generative artificial intelligence" is a technology that uses machine learning models to generate optimal inquiries and creative content based on input information.

[0387] An "inquiry" refers to a question or command that is generated based on the user's emotions or state of mind.

[0388] An "electronic questionnaire" is a set of questions formatted in a digital format, used to conduct surveys with recipients.

[0389] "Statistical analysis" is a method for quantitatively analyzing collected data to identify trends and patterns.

[0390] This invention provides a system for generating questions based on the user's emotional state. First, the server receives information transmitted from the user via a terminal. This information includes feedback and comments. The received information is analyzed using natural language processing technology to identify the user's natural state, i.e., emotional or psychological nuances. Specifically, a machine learning model is used as the emotion engine to tokenize text and calculate an emotion score.

[0391] Based on the analyzed emotional information, the generative artificial intelligence on the server generates the most appropriate inquiry. In this process, a generative AI model is used to create prompts that match the user's emotional state, and then the question is designed based on these prompts. For example, if a user inputs "I am feeling stressed about remote work," the emotional engine can analyze that emotion and generate a question such as, "What kind of support do you think would be effective in alleviating the stress you feel while working remotely?"

[0392] The generated inquiries are formatted by the server and provided to the user as an electronic questionnaire. This questionnaire is designed to be easy for respondents to understand and answer. The questionnaire is distributed via email or a dedicated app, and users answer it using their devices.

[0393] The collected responses are aggregated on a server and statistically analyzed. In particular, by integrating sentiment analysis, it is possible to understand the changes and trends in users' emotions in detail. Based on this, the analysis results are created as a report and sent to the information provider. The analysis results are visualized in graphs and charts, providing information that accurately represents the user's emotional state, such as "stress tendencies in remote work."

[0394] An example of a prompt message is, "Analyze the user's sentiment from their input text and generate appropriate survey questions." In this way, flexible and highly accurate data collection tailored to the user's emotions is achieved.

[0395] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0396] Step 1:

[0397] The server receives information sent from the user via the terminal. This information includes user feedback and comments in text format. The server then temporarily stores the received data for analysis in the next step.

[0398] Step 2:

[0399] The server begins analyzing the received text data using natural language processing techniques. Specifically, it tokenizes the text and performs data calculations to identify emotional nuances using an emotion engine. The output of this analysis is data with an emotion score assigned to each word.

[0400] Step 3:

[0401] The server uses generative artificial intelligence to generate optimal questions, taking the emotional information obtained from the analysis as input. Here, the generative AI model operates, constructing prompt sentences based on the user's natural state, and designing a set of questions based on those prompts. The output of this step is the specific set of questions to be presented to the user.

[0402] Step 4:

[0403] The server formats the generated set of questions and creates an electronic questionnaire in a user-friendly format. Specifically, it adjusts the layout of the questionnaire and designs an interface that allows users to intuitively input their answers. The output is a distributable digital questionnaire.

[0404] Step 5:

[0405] The server distributes electronic questionnaires to users via email or app. The terminal opens the received questionnaire and provides functionality to enable users to enter their answers. The output in this step is the questionnaire in a state accessible to the user.

[0406] Step 6:

[0407] The user answers a questionnaire and sends it to the server via their device. The server receives the response data as input in real time and performs aggregation. It also performs sentiment analysis again and processes the data based on the aggregation results. The output of this step is aggregated data that includes the response data and the analysis results.

[0408] Step 7:

[0409] The server performs detailed statistical analysis based on the aggregated data and creates a report of the analysis results. Specifically, it generates graphs and charts to visually represent the user's emotional state and response trends. This report is then distributed to the information provider.

[0410] (Application Example 2)

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

[0412] When collecting customer feedback in physical stores, traditional surveys often fail to consider customer emotions, making it difficult to grasp true needs and problems. Furthermore, delays in addressing customer dissatisfaction can lead to decreased customer satisfaction.

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

[0414] In this invention, the server includes means for receiving data input from a user, means for recognizing the user's emotions using an emotion engine based on the data input, and means for generating optimal questions using artificial intelligence based on the recognized emotions. This makes it possible to quickly generate detailed and accurate questions based on customer emotions and improve the quality of surveys.

[0415] "Users" refer to end users who use this system and provide data.

[0416] "Data entry" refers to the information and feedback that users provide to the system.

[0417] An "emotion engine" is a processing device used to analyze the emotional elements contained in the user's data input.

[0418] "Recognizing emotions" refers to the process of identifying a user's emotional state from the input data.

[0419] Artificial intelligence is a technology that uses machine learning models to mimic human intellectual work.

[0420] "Generating questions" is the process of constructing appropriate questions based on user input data.

[0421] A "questionnaire" is a collection of questions presented to a user.

[0422] "Emotional analysis" is a technique that analyzes user response data to identify emotional tendencies.

[0423] The system implementing this invention understands the emotions of users when they provide feedback in a physical store and generates appropriate questions. The central components of this system include a server, a terminal, and an emotion engine.

[0424] The server accepts data input through terminals available in the store and through users' mobile devices. This data input includes free-form text and specific feedback from users, and the server receives this information in real time.

[0425] Next, the server uses an emotion engine to analyze the input text data and recognize the user's emotional state. This emotion engine utilizes technologies such as the Google Cloud Natural Language API or similar natural language processing (NLP) techniques to extract emotional characteristics such as positive, negative, and neutral from the user's statements.

[0426] After the emotional state is identified, an artificial intelligence module on the server activates and generates individually optimized questions using a generative AI model. This question generation process utilizes OpenAI's GPT-3 and other similar natural language generation models. The AI ​​module appropriately formats questions according to the user's emotional state and presents them immediately to the user's device, improving the user experience.

[0427] As a concrete example of this system, if a user enters dissatisfaction with a service delay, the emotion engine identifies the negative emotion and instantly generates and presents a question to the user such as, "We apologize for the delay. Specifically, which service improvements would you like to see?"

[0428] An example of a prompt for the generative AI model is: "Analyze the customer's sentiment from the following text and generate the most appropriate question based on that sentiment. Text: {customer input text}".

[0429] In this way, we aim to create a system that enhances the emotional basis of user interaction, contributing to improved store services and increased customer satisfaction.

[0430] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0431] Step 1:

[0432] The server accepts data input from the user's terminal. This data input consists of text information provided by the user. The server temporarily stores the received input data and prepares it for subsequent processing.

[0433] Step 2:

[0434] The server analyzes the input text data using an emotion engine. This emotion engine processes the input data using natural language processing techniques and classifies the user's emotional state as positive, negative, or neutral. Based on the analysis, it outputs tags and scores corresponding to the user's emotions.

[0435] Step 3:

[0436] An artificial intelligence module on the server uses a generative AI model to generate optimal questions based on the user's emotions. An example of a prompt is: "Analyze the customer's emotions from the following text and generate the optimal question based on those emotions. Text: {User input text}". This prompt is input to the AI ​​model, which then outputs an appropriate question.

[0437] Step 4:

[0438] The server formats the generated questions and converts them into a format that can be displayed on the user's device. By presenting questions in a format that is most relevant to the user's emotions, it enhances user engagement.

[0439] Step 5:

[0440] The terminal presents the user with a formatted question. The user answers the question, and the answer is sent back to the server. The server collects the user's answers in real time and stores them for further sentiment analysis.

[0441] Step 6:

[0442] The server performs statistical analysis, including sentiment analysis, based on the collected data. Based on the results of this analysis, it generates reports to improve the service quality of physical stores and provides them to managers and relevant parties.

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

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

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

[0446] [Third Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0459] This invention provides a system for users to efficiently and effectively create internal company questionnaires. This system significantly reduces time and effort by receiving data input from users, retrieving relevant information from information storage, and generating optimal questions using artificial intelligence. Furthermore, it automates the entire process of generating electronic questionnaires, distributing them to target individuals, and compiling and analyzing responses.

[0460] The server is the core of the system. After receiving data input from users, it uses natural language processing technology to analyze the input and extract relevant keywords. It then accesses the company's internal information storage to retrieve past survey results and other relevant data. This retrieved data is used as a reference for creating new surveys.

[0461] Next, the artificial intelligence module on the server starts up and generates optimal questions based on the user's objectives. The AI ​​refers to relevant theories and past survey results to construct a list of questions. This includes ranking questions based on their appropriateness and importance, and is a process for selecting the most effective questions.

[0462] The generated questions are formatted by the server as an electronic questionnaire. The questionnaire is designed in a digital format, and its interface is optimized for intuitive use by participants. This questionnaire is automatically distributed to participants by the server. Distribution methods include email and the company's internal portal site.

[0463] Participants access the survey using their devices and answer the designated questions. The responses are sent to the server in real time, and the server receives, immediately compiles, and analyzes them. The analyzed data is evaluated using statistical methods, and the server provides the results to the users.

[0464] For example, if a user wants to evaluate their satisfaction with their remote work environment, they would input "satisfaction with the remote work environment" as their objective into their device. The server would then retrieve relevant data, and artificial intelligence would generate questions such as "satisfaction with the work environment" and "quality of communication." Based on the responses collected through the distributed questionnaires, the server would create a detailed analysis of satisfaction levels and provide it to the user.

[0465] Thus, the present invention enables efficient and effective design, implementation, data collection, and analysis of questionnaires.

[0466] The following describes the processing flow.

[0467] Step 1:

[0468] Users use their devices to input the purpose of the survey and the information they want to collect. This input data is then sent to the server.

[0469] Step 2:

[0470] The server analyzes the received data using natural language processing techniques to extract relevant keywords and intents.

[0471] Step 3:

[0472] The server accesses the company's internal information storage and retrieves past survey data and internal statistics related to the extracted keywords.

[0473] Step 4:

[0474] An artificial intelligence module within the server operates to generate an optimal list of questions based on the acquired information and the input objective. This process takes into account relevant theories and past success stories.

[0475] Step 5:

[0476] The server formats the generated questions into an electronic questionnaire and optimizes the user interface. This questionnaire is designed to be easy for the respondents to understand.

[0477] Step 6:

[0478] The server initiates the distribution process, sending questionnaires to recipients via email and the company portal.

[0479] Step 7:

[0480] Users access the survey using their devices and answer the questions. The responses are sent to the server in real time.

[0481] Step 8:

[0482] The server immediately aggregates the collected responses and performs statistical analysis. This analysis reveals trends and patterns in the responses.

[0483] Step 9:

[0484] The server generates analysis results in report format and provides them to the user. This allows the user to quickly understand the degree to which the survey objectives were achieved and the opinions of employees.

[0485] (Example 1)

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

[0487] To conduct surveys efficiently and effectively, users need to be able to easily design questionnaires, quickly obtain relevant information, and optimize questions. However, traditional methods require a lot of time and effort for design and information acquisition, making efficient data collection difficult.

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

[0489] In this invention, the server includes processing means for receiving information input from users, acquisition means for acquiring relevant knowledge from a storage area, and generation means for generating optimal inquiries using a data processing device. This automates the entire process from questionnaire design to data collection and analysis, enabling efficient research.

[0490] A "user" is someone who operates this system and provides input for conducting the survey.

[0491] "Information input" refers to data that users provide to the system, including the purpose and theme of the survey.

[0492] "Processing means" refers to devices and methods for a system to receive and analyze information input from users.

[0493] A "storage area" is a storage device or space where related information and historical data are stored.

[0494] "Acquisition means" refers to the methods or devices that a system uses to acquire necessary information from its storage area.

[0495] A "data processing device" is a device that uses artificial intelligence technology to automatically generate optimal queries.

[0496] "Generation means" refers to methods or devices that create inquiries suitable for investigation based on information collected by the system.

[0497] "Investigation documents" refer to digital or paper documents presented to the patient, including any generated inquiries.

[0498] A "patient" is someone who receives the survey documents and answers the questions written therein.

[0499] "Data aggregation means" refers to methods or devices for collecting and compiling responses obtained from patients.

[0500] "Analysis means" refers to methods or devices for analyzing aggregated responses and deriving survey results.

[0501] Modes for carrying out the invention

[0502] The system implementing this invention enables users to create and conduct questionnaires efficiently and effectively. By combining multiple means, this system aims to reduce the burden on users while obtaining highly accurate survey results.

[0503] The user enters the purpose and theme of the survey into the terminal. The terminal processes the entered information and sends it to the server. The server analyzes this information using natural language processing technology. Through this analysis, relevant keywords and themes can be extracted. Software called a natural language processing engine is used for this analysis.

[0504] The server accesses the company's internal database based on the analyzed results. The database stores past survey results and related information, and by retrieving this information, the server collects useful data for designing the survey.

[0505] Next, a data processing unit on the server uses artificial intelligence technology to generate the most suitable list of questions. This process utilizes a generative AI model. This model has the ability to create questions that are appropriate for the user's purpose by referencing the results of past surveys and related theories. For example, a prompt such as "Generate questions to evaluate satisfaction with the remote work environment" might be used.

[0506] The generated questions are formatted by the server as electronic questionnaires, presented in a way that is intuitively easy for respondents to answer. Digital formatting design tools are used for this process. The completed questionnaires are distributed to respondents via email or the company portal.

[0507] Participants will answer this questionnaire using a terminal. The responses will be sent to the server in real time, and the server will immediately organize the data using an aggregation module. Subsequently, statistical analysis will be performed through analytical tools, and the results will be reflected in the results provided to the user.

[0508] Thus, the present invention is a system that automates a series of processes, enabling efficient and simple questionnaire creation and data collection for users.

[0509] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0510] Step 1:

[0511] The user fills in the purpose and theme for creating the survey in the input form on the device. The information entered is in text format, and this information serves as the system's initial data. The device sends this information to the server as digital data.

[0512] Step 2:

[0513] The server receives information sent from the terminal and analyzes it using natural language processing technology. This analysis extracts relevant keywords and issues. The input data is theme information entered by the user, and the output is a list of keywords obtained from the analysis. A natural language processing engine is used in this analysis process.

[0514] Step 3:

[0515] The server queries the company's internal database based on the extracted keywords to retrieve relevant information. The input is a keyword list, and the database search outputs relevant past survey data and additional knowledge. This collects data that can be used as a reference for creating questionnaires.

[0516] Step 4:

[0517] The data processing unit on the server generates optimal questions using a generative AI model based on the acquired information. In this process, relevant prompt sentences are supplied to the generative AI model, giving instructions such as, "Extract the most suitable questions from similar past survey results and create a list." The input is a collection of acquired information, and the output is a list of questions.

[0518] Step 5:

[0519] The server formats the generated questions and creates an electronic questionnaire. Using design tools, the questions are transformed into a natural and easy-to-read format. The input is a list of questions, and the output is a digital questionnaire. This questionnaire is designed with usability in mind.

[0520] Step 6:

[0521] The server distributes the questionnaires to the respondents. Specifically, it sends the questionnaires using an email distribution system or an internal information sharing platform. The input is a digital questionnaire, and the output is the questionnaire received on each respondent's device.

[0522] Step 7:

[0523] Participants access the distributed questionnaire using a terminal and answer the questions. The responses are transmitted to the server in real time in digital format. The input is the participant's response, and the output is the response data.

[0524] Step 8:

[0525] The server aggregates the received response data and performs analysis using analytical tools. During this process, statistical methods are used to reveal data trends. The input is the response data, and the output is the analysis results, which are provided to the user as a visual report.

[0526] (Application Example 1)

[0527] 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."

[0528] While there is a need to improve safety awareness and the working environment in factory settings, there is a problem in efficiently collecting feedback from workers and quickly identifying issues in the work environment. The present invention aims to solve these problems and provide a system that contributes to improving workers' safety awareness and the working environment.

[0529] 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.

[0530] In this invention, the server includes means for receiving data input from users, means for acquiring relevant information from an information storage device, means for generating optimal questions using machine learning technology, means for a robot to present a survey form to a target individual and collect responses, and means for detecting areas for improvement in the on-site environment. This makes it possible to efficiently conduct surveys on safety awareness and to quickly improve the on-site environment.

[0531] The "first method" is a mechanism for receiving data input from users.

[0532] The "second method" is a mechanism that retrieves relevant information from an information storage device based on data input from the user.

[0533] The "third method" is a mechanism that uses acquired information to generate optimal questions using machine learning technology.

[0534] The "fourth method" is a mechanism that formats the generated questions and creates an electronic survey form.

[0535] The "fifth method" is a mechanism for distributing survey forms to target individuals.

[0536] The "sixth method" is a mechanism for collecting and evaluating responses from target individuals after distribution.

[0537] The "seventh method" is a mechanism in which a robot presents a survey form to the target individual and collects their responses.

[0538] The "eighth method" is a mechanism for detecting areas for improvement in the on-site environment based on the collected responses.

[0539] "Machine learning technology" is a technique that uses algorithms to analyze data and use that information to generate questions and evaluate answers.

[0540] In this invention, a server is central to operating the system. The server first receives safety-related data input from users via terminals. The received data is analyzed using natural language processing technology within the server, and relevant information is retrieved from information storage devices. In particular, data on past work environments and standard safety guidelines are referenced.

[0541] Next, machine learning technology on the server is used to automatically generate optimal questions. In this generation process, the appropriateness and importance of the questions are evaluated based on relevant theories and past research results, and finally an electronic survey form is created. This survey form is sent to a robot via a terminal and presented to the worker by the robot.

[0542] The robot autonomously moves around the factory, presenting survey forms to workers and collecting responses in real time. The collected response data is sent to a server, where an evaluation algorithm identifies areas for improvement in the work environment. These results are immediately reported to factory managers, facilitating improvements on-site.

[0543] For example, if a new machine is introduced at a factory, the server can input a prompt message such as "Please create questions about the work environment after the introduction of the new equipment" into the AI ​​model, and then conduct a survey using the resulting questions.

[0544] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0545] Step 1:

[0546] The server accepts data input from users via a terminal. Users input data related to new safety standards, and this input data is analyzed using natural language processing technology. The results of the analysis include relevant keywords and contextual information.

[0547] Step 2:

[0548] Based on the analysis results, the server retrieves relevant past survey results and reference data from its information storage device. During this process, the retrieved data is filtered to select the information most relevant to the user's input.

[0549] Step 3:

[0550] The server uses the acquired information to leverage a machine learning model to generate optimal questions. A prompt such as "Please create questions about the workplace environment after the introduction of new equipment" is input, and the AI ​​model generates questions based on this.

[0551] Step 4:

[0552] The server formats the generated questions and creates an electronic survey form. During the formatting process, the layout and usability of the questions are optimized, resulting in an intuitive interface.

[0553] Step 5:

[0554] The terminal sends a survey form to the robot, which then uses it to present it to the worker. The robot moves around the factory and conducts the survey with the corresponding worker. This is coordinated by the robot's motion planning algorithm.

[0555] Step 6:

[0556] The robot collects responses from workers in real time and sends them to a server via a terminal. The response data is designed to be analyzed immediately, ensuring efficient data collection.

[0557] Step 7:

[0558] The server uses an analysis algorithm to detect areas for improvement in the field environment from the response data. The results of the analysis include specific areas requiring improvement and suggestions for improvement.

[0559] Step 8:

[0560] The server reports the analysis results to the factory manager and proposes necessary corrective actions. Based on these results, the manager promotes appropriate improvements to the on-site environment.

[0561] 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.

[0562] This invention relates to a system that, when receiving data input from a user, uses an emotion engine to recognize the user's emotions and generates optimal questions based on those emotions. This system creates questionnaires that take the user's emotional state into account, allowing for deeper insights.

[0563] The server uses an emotion engine to analyze emotional elements based on the text data received from the user. This emotion engine combines natural language processing technology and machine learning models to identify the emotional nuances contained in the sentences entered by the user.

[0564] Using the analyzed sentiment data, an artificial intelligence module on the server activates to generate an optimal set of questions that correspond to the user's emotional state. The generated questions are designed to encourage the user to respond more sincerely, taking into account how the questions relate to the user's current emotions.

[0565] After generating the questions, the server formats them into an electronic questionnaire. The questionnaire is designed to be intuitive and easy for respondents to answer. The questionnaire is then distributed to respondents through a designated medium.

[0566] Users answer the survey using their devices. The server collects the responses in real time and performs detailed statistical analysis, including sentiment analysis. The analyzed results are compiled into a report that reflects the user's emotional state and delivered to the information provider.

[0567] For example, if a user is dissatisfied with remote work, the emotion engine analyzes that dissatisfaction and generates questions about stress and fatigue. The data collected in this way can be used not only to improve the work environment but also to implement measures that take into account the psychological support of employees.

[0568] Thus, by incorporating emotion recognition, the present invention enhances the added value of the survey system and enables more reliable data collection.

[0569] The following describes the processing flow.

[0570] Step 1:

[0571] Users use their devices to input data, including the purpose of the survey and the information they want to know. The entered data is then sent to the server.

[0572] Step 2:

[0573] The server inputs the received data into an emotion engine, which uses natural language processing technology to analyze the emotional state of the text entered by the user. In this process, emotional nuances and keywords contained in the text are identified.

[0574] Step 3:

[0575] The server accesses the company's internal information storage and searches for past survey data and internal resources related to the extracted emotions. This integrates the results of the emotion analysis with the historical data.

[0576] Step 4:

[0577] An artificial intelligence module within the server generates a list of questions best suited to the user's emotional state based on this integrated data. This generation process reflects past success stories and relevant theories, selecting effective questions that align with the user's emotions.

[0578] Step 5:

[0579] The server formats the generated questions into an electronic questionnaire and optimizes the user interface. The questionnaire is designed to be intuitive and easy for respondents to answer.

[0580] Step 6:

[0581] The server handles the process of distributing questionnaires to the target individuals, which are then provided via email or the company's internal portal.

[0582] Step 7:

[0583] Users access the distributed survey using their device and enter their answers to the generated questions. The answers are immediately sent to the server.

[0584] Step 8:

[0585] The server aggregates responses in real time and performs detailed statistical analysis, including sentiment analysis results. In this process, the collected data is trended and patterns are identified.

[0586] Step 9:

[0587] The server generates a report based on the analysis results and provides it to the user. This report includes data insights linked to the user's emotional state, which can be used to develop practical strategies.

[0588] (Example 2)

[0589] 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."

[0590] Conventional data collection systems have struggled to generate flexible questions that take into account the emotional state of users, making it difficult to improve the accuracy and reliability of the data. Furthermore, there was a need for a mechanism that could generate questions appropriate to the emotions of the target audience and gain deeper insights.

[0591] 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.

[0592] In this invention, the server includes means for receiving information from the user and analyzing the natural state, means for generating optimal inquiries using generative artificial intelligence, and means for formatting the generated inquiries and creating an electronic questionnaire. This enables the generation of questions based on the user's emotional state and the collection of highly accurate data.

[0593] A "user" is an individual or legal entity that operates the system and provides or receives information.

[0594] "Information" refers to the text and data entered into a system, and analysis and processing are performed based on their content.

[0595] "Natural state" refers to the emotional or psychological nuances contained in the text data entered by the user.

[0596] "Emotional information" refers to data that indicates the user's emotions and psychological state, identified through natural language processing.

[0597] "Generative artificial intelligence" is a technology that uses machine learning models to generate optimal inquiries and creative content based on input information.

[0598] An "inquiry" refers to a question or command that is generated based on the user's emotions or state of mind.

[0599] An "electronic questionnaire" is a set of questions formatted in a digital format, used to conduct surveys with recipients.

[0600] "Statistical analysis" is a method for quantitatively analyzing collected data to identify trends and patterns.

[0601] This invention provides a system for generating questions based on the user's emotional state. First, the server receives information transmitted from the user via a terminal. This information includes feedback and comments. The received information is analyzed using natural language processing technology to identify the user's natural state, i.e., emotional or psychological nuances. Specifically, a machine learning model is used as the emotion engine to tokenize text and calculate an emotion score.

[0602] Based on the analyzed emotional information, the generative artificial intelligence on the server generates the most appropriate inquiry. In this process, a generative AI model is used to create prompts that match the user's emotional state, and then the question is designed based on these prompts. For example, if a user inputs "I am feeling stressed about remote work," the emotional engine can analyze that emotion and generate a question such as, "What kind of support do you think would be effective in alleviating the stress you feel while working remotely?"

[0603] The generated inquiries are formatted by the server and provided to the user as an electronic questionnaire. This questionnaire is designed to be easy for respondents to understand and answer. The questionnaire is distributed via email or a dedicated app, and users answer it using their devices.

[0604] The collected responses are aggregated on a server and statistically analyzed. In particular, by integrating sentiment analysis, it is possible to understand the changes and trends in users' emotions in detail. Based on this, the analysis results are created as a report and sent to the information provider. The analysis results are visualized in graphs and charts, providing information that accurately represents the user's emotional state, such as "stress tendencies in remote work."

[0605] An example of a prompt message is, "Analyze the user's sentiment from their input text and generate appropriate survey questions." In this way, flexible and highly accurate data collection tailored to the user's emotions is achieved.

[0606] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0607] Step 1:

[0608] The server receives information sent from the user via the terminal. This information includes user feedback and comments in text format. The server then temporarily stores the received data for analysis in the next step.

[0609] Step 2:

[0610] The server begins analyzing the received text data using natural language processing techniques. Specifically, it tokenizes the text and performs data calculations to identify emotional nuances using an emotion engine. The output of this analysis is data with an emotion score assigned to each word.

[0611] Step 3:

[0612] The server uses generative artificial intelligence to generate optimal questions, taking the emotional information obtained from the analysis as input. Here, the generative AI model operates, constructing prompt sentences based on the user's natural state, and designing a set of questions based on those prompts. The output of this step is the specific set of questions to be presented to the user.

[0613] Step 4:

[0614] The server formats the generated set of questions and creates an electronic questionnaire in a user-friendly format. Specifically, it adjusts the layout of the questionnaire and designs an interface that allows users to intuitively input their answers. The output is a distributable digital questionnaire.

[0615] Step 5:

[0616] The server distributes electronic questionnaires to users via email or app. The terminal opens the received questionnaire and provides functionality to enable users to enter their answers. The output in this step is the questionnaire in a state accessible to the user.

[0617] Step 6:

[0618] The user answers a questionnaire and sends it to the server via their device. The server receives the response data as input in real time and performs aggregation. It also performs sentiment analysis again and processes the data based on the aggregation results. The output of this step is aggregated data that includes the response data and the analysis results.

[0619] Step 7:

[0620] The server performs detailed statistical analysis based on the aggregated data and creates a report of the analysis results. Specifically, it generates graphs and charts to visually represent the user's emotional state and response trends. This report is then distributed to the information provider.

[0621] (Application Example 2)

[0622] 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."

[0623] When collecting customer feedback in physical stores, traditional surveys often fail to consider customer emotions, making it difficult to grasp true needs and problems. Furthermore, delays in addressing customer dissatisfaction can lead to decreased customer satisfaction.

[0624] 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.

[0625] In this invention, the server includes means for receiving data input from a user, means for recognizing the user's emotions using an emotion engine based on the data input, and means for generating optimal questions using artificial intelligence based on the recognized emotions. This makes it possible to quickly generate detailed and accurate questions based on customer emotions and improve the quality of surveys.

[0626] "Users" refer to end users who use this system and provide data.

[0627] "Data entry" refers to the information and feedback that users provide to the system.

[0628] An "emotion engine" is a processing device used to analyze the emotional elements contained in the user's data input.

[0629] "Recognizing emotions" refers to the process of identifying a user's emotional state from the input data.

[0630] Artificial intelligence is a technology that uses machine learning models to mimic human intellectual work.

[0631] "Generating questions" is the process of constructing appropriate questions based on user input data.

[0632] A "questionnaire" is a collection of questions presented to a user.

[0633] "Emotional analysis" is a technique that analyzes user response data to identify emotional tendencies.

[0634] The system implementing this invention understands the emotions of users when they provide feedback in a physical store and generates appropriate questions. The central components of this system include a server, a terminal, and an emotion engine.

[0635] The server accepts data input through terminals available in the store and through users' mobile devices. This data input includes free-form text and specific feedback from users, and the server receives this information in real time.

[0636] Next, the server uses an emotion engine to analyze the input text data and recognize the user's emotional state. This emotion engine utilizes technologies such as the Google Cloud Natural Language API or similar natural language processing (NLP) techniques to extract emotional characteristics such as positive, negative, and neutral from the user's statements.

[0637] After the emotional state is identified, an artificial intelligence module on the server activates and generates individually optimized questions using a generative AI model. This question generation process utilizes OpenAI's GPT-3 and other similar natural language generation models. The AI ​​module appropriately formats questions according to the user's emotional state and presents them immediately to the user's device, improving the user experience.

[0638] As a concrete example of this system, if a user enters dissatisfaction with a service delay, the emotion engine identifies the negative emotion and instantly generates and presents a question to the user such as, "We apologize for the delay. Specifically, which service improvements would you like to see?"

[0639] An example of a prompt for the generative AI model is: "Analyze the customer's sentiment from the following text and generate the most appropriate question based on that sentiment. Text: {customer input text}".

[0640] In this way, we aim to create a system that enhances the emotional basis of user interaction, contributing to improved store services and increased customer satisfaction.

[0641] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0642] Step 1:

[0643] The server accepts data input from the user's terminal. This data input consists of text information provided by the user. The server temporarily stores the received input data and prepares it for subsequent processing.

[0644] Step 2:

[0645] The server analyzes the input text data using an emotion engine. This emotion engine processes the input data using natural language processing techniques and classifies the user's emotional state as positive, negative, or neutral. Based on the analysis, it outputs tags and scores corresponding to the user's emotions.

[0646] Step 3:

[0647] An artificial intelligence module on the server uses a generative AI model to generate optimal questions based on the user's emotions. An example of a prompt is: "Analyze the customer's emotions from the following text and generate the optimal question based on those emotions. Text: {User input text}". This prompt is input to the AI ​​model, which then outputs an appropriate question.

[0648] Step 4:

[0649] The server formats the generated questions and converts them into a format that can be displayed on the user's device. By presenting questions in a format that is most relevant to the user's emotions, it enhances user engagement.

[0650] Step 5:

[0651] The terminal presents the user with a formatted question. The user answers the question, and the answer is sent back to the server. The server collects the user's answers in real time and stores them for further sentiment analysis.

[0652] Step 6:

[0653] The server performs statistical analysis, including sentiment analysis, based on the collected data. Based on the results of this analysis, it generates reports to improve the service quality of physical stores and provides them to managers and relevant parties.

[0654] 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.

[0655] 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.

[0656] 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.

[0657] [Fourth Embodiment]

[0658] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0659] 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.

[0660] 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).

[0661] 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.

[0662] 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.

[0663] 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).

[0664] 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.

[0665] 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.

[0666] 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.

[0667] 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.

[0668] 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.

[0669] 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.

[0670] 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".

[0671] This invention provides a system for users to efficiently and effectively create internal company questionnaires. This system significantly reduces time and effort by receiving data input from users, retrieving relevant information from information storage, and generating optimal questions using artificial intelligence. Furthermore, it automates the entire process of generating electronic questionnaires, distributing them to target individuals, and compiling and analyzing responses.

[0672] The server is the core of the system. After receiving data input from users, it uses natural language processing technology to analyze the input and extract relevant keywords. It then accesses the company's internal information storage to retrieve past survey results and other relevant data. This retrieved data is used as a reference for creating new surveys.

[0673] Next, the artificial intelligence module on the server starts up and generates optimal questions based on the user's objectives. The AI ​​refers to relevant theories and past survey results to construct a list of questions. This includes ranking questions based on their appropriateness and importance, and is a process for selecting the most effective questions.

[0674] The generated questions are formatted by the server as an electronic questionnaire. The questionnaire is designed in a digital format, and its interface is optimized for intuitive use by participants. This questionnaire is automatically distributed to participants by the server. Distribution methods include email and the company's internal portal site.

[0675] Participants access the survey using their devices and answer the designated questions. The responses are sent to the server in real time, and the server receives, immediately compiles, and analyzes them. The analyzed data is evaluated using statistical methods, and the server provides the results to the users.

[0676] For example, if a user wants to evaluate their satisfaction with their remote work environment, they would input "satisfaction with the remote work environment" as their objective into their device. The server would then retrieve relevant data, and artificial intelligence would generate questions such as "satisfaction with the work environment" and "quality of communication." Based on the responses collected through the distributed questionnaires, the server would create a detailed analysis of satisfaction levels and provide it to the user.

[0677] Thus, the present invention enables efficient and effective design, implementation, data collection, and analysis of questionnaires.

[0678] The following describes the processing flow.

[0679] Step 1:

[0680] Users use their devices to input the purpose of the survey and the information they want to collect. This input data is then sent to the server.

[0681] Step 2:

[0682] The server analyzes the received data using natural language processing techniques to extract relevant keywords and intents.

[0683] Step 3:

[0684] The server accesses the company's internal information storage and retrieves past survey data and internal statistics related to the extracted keywords.

[0685] Step 4:

[0686] An artificial intelligence module within the server operates to generate an optimal list of questions based on the acquired information and the input objective. This process takes into account relevant theories and past success stories.

[0687] Step 5:

[0688] The server formats the generated questions into an electronic questionnaire and optimizes the user interface. This questionnaire is designed to be easy for the respondents to understand.

[0689] Step 6:

[0690] The server initiates the distribution process, sending questionnaires to recipients via email and the company portal.

[0691] Step 7:

[0692] Users access the survey using their devices and answer the questions. The responses are sent to the server in real time.

[0693] Step 8:

[0694] The server immediately aggregates the collected responses and performs statistical analysis. This analysis reveals trends and patterns in the responses.

[0695] Step 9:

[0696] The server generates analysis results in report format and provides them to the user. This allows the user to quickly understand the degree to which the survey objectives were achieved and the opinions of employees.

[0697] (Example 1)

[0698] 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".

[0699] To conduct surveys efficiently and effectively, users need to be able to easily design questionnaires, quickly obtain relevant information, and optimize questions. However, traditional methods require a lot of time and effort for design and information acquisition, making efficient data collection difficult.

[0700] 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.

[0701] In this invention, the server includes processing means for receiving information input from users, acquisition means for acquiring relevant knowledge from a storage area, and generation means for generating optimal inquiries using a data processing device. This automates the entire process from questionnaire design to data collection and analysis, enabling efficient research.

[0702] A "user" is someone who operates this system and provides input for conducting the survey.

[0703] "Information input" refers to data that users provide to the system, including the purpose and theme of the survey.

[0704] "Processing means" refers to devices and methods for a system to receive and analyze information input from users.

[0705] A "storage area" is a storage device or space where related information and historical data are stored.

[0706] "Acquisition means" refers to the methods or devices that a system uses to acquire necessary information from its storage area.

[0707] A "data processing device" is a device that uses artificial intelligence technology to automatically generate optimal queries.

[0708] "Generation means" refers to methods or devices that create inquiries suitable for investigation based on information collected by the system.

[0709] "Investigation documents" refer to digital or paper documents presented to the patient, including any generated inquiries.

[0710] A "patient" is someone who receives the survey documents and answers the questions written therein.

[0711] "Data aggregation means" refers to methods or devices for collecting and compiling responses obtained from patients.

[0712] "Analysis means" refers to methods or devices for analyzing aggregated responses and deriving survey results.

[0713] Modes for carrying out the invention

[0714] The system implementing this invention enables users to create and conduct questionnaires efficiently and effectively. By combining multiple means, this system aims to reduce the burden on users while obtaining highly accurate survey results.

[0715] The user enters the purpose and theme of the survey into the terminal. The terminal processes the entered information and sends it to the server. The server analyzes this information using natural language processing technology. Through this analysis, relevant keywords and themes can be extracted. Software called a natural language processing engine is used for this analysis.

[0716] The server accesses the company's internal database based on the analyzed results. The database stores past survey results and related information, and by retrieving this information, the server collects useful data for designing the survey.

[0717] Next, a data processing unit on the server uses artificial intelligence technology to generate the most suitable list of questions. This process utilizes a generative AI model. This model has the ability to create questions that are appropriate for the user's purpose by referencing the results of past surveys and related theories. For example, a prompt such as "Generate questions to evaluate satisfaction with the remote work environment" might be used.

[0718] The generated questions are formatted by the server as electronic questionnaires, presented in a way that is intuitively easy for respondents to answer. Digital formatting design tools are used for this process. The completed questionnaires are distributed to respondents via email or the company portal.

[0719] Participants will answer this questionnaire using a terminal. The responses will be sent to the server in real time, and the server will immediately organize the data using an aggregation module. Subsequently, statistical analysis will be performed through analytical tools, and the results will be reflected in the results provided to the user.

[0720] Thus, the present invention is a system that automates a series of processes, enabling efficient and simple questionnaire creation and data collection for users.

[0721] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0722] Step 1:

[0723] The user fills in the purpose and theme for creating the survey in the input form on the device. The information entered is in text format, and this information serves as the system's initial data. The device sends this information to the server as digital data.

[0724] Step 2:

[0725] The server receives information sent from the terminal and analyzes it using natural language processing technology. This analysis extracts relevant keywords and issues. The input data is theme information entered by the user, and the output is a list of keywords obtained from the analysis. A natural language processing engine is used in this analysis process.

[0726] Step 3:

[0727] The server queries the company's internal database based on the extracted keywords to retrieve relevant information. The input is a keyword list, and the database search outputs relevant past survey data and additional knowledge. This collects data that can be used as a reference for creating questionnaires.

[0728] Step 4:

[0729] The data processing unit on the server generates optimal questions using a generative AI model based on the acquired information. In this process, relevant prompt sentences are supplied to the generative AI model, giving instructions such as, "Extract the most suitable questions from similar past survey results and create a list." The input is a collection of acquired information, and the output is a list of questions.

[0730] Step 5:

[0731] The server formats the generated questions and creates an electronic questionnaire. Using design tools, the questions are transformed into a natural and easy-to-read format. The input is a list of questions, and the output is a digital questionnaire. This questionnaire is designed with usability in mind.

[0732] Step 6:

[0733] The server distributes the questionnaires to the respondents. Specifically, it sends the questionnaires using an email distribution system or an internal information sharing platform. The input is a digital questionnaire, and the output is the questionnaire received on each respondent's device.

[0734] Step 7:

[0735] Participants access the distributed questionnaire using a terminal and answer the questions. The responses are transmitted to the server in real time in digital format. The input is the participant's response, and the output is the response data.

[0736] Step 8:

[0737] The server aggregates the received response data and performs analysis using analytical tools. During this process, statistical methods are used to reveal data trends. The input is the response data, and the output is the analysis results, which are provided to the user as a visual report.

[0738] (Application Example 1)

[0739] 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".

[0740] While there is a need to improve safety awareness and the working environment in factory settings, there is a problem in efficiently collecting feedback from workers and quickly identifying issues in the work environment. The present invention aims to solve these problems and provide a system that contributes to improving workers' safety awareness and the working environment.

[0741] 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.

[0742] In this invention, the server includes means for receiving data input from users, means for acquiring relevant information from an information storage device, means for generating optimal questions using machine learning technology, means for a robot to present a survey form to a target individual and collect responses, and means for detecting areas for improvement in the on-site environment. This makes it possible to efficiently conduct surveys on safety awareness and to quickly improve the on-site environment.

[0743] The "first method" is a mechanism for receiving data input from users.

[0744] The "second method" is a mechanism that retrieves relevant information from an information storage device based on data input from the user.

[0745] The "third method" is a mechanism that uses acquired information to generate optimal questions using machine learning technology.

[0746] The "fourth method" is a mechanism that formats the generated questions and creates an electronic survey form.

[0747] The "fifth method" is a mechanism for distributing survey forms to target individuals.

[0748] The "sixth method" is a mechanism for collecting and evaluating responses from target individuals after distribution.

[0749] The "seventh method" is a mechanism in which a robot presents a survey form to the target individual and collects their responses.

[0750] The "eighth method" is a mechanism for detecting areas for improvement in the on-site environment based on the collected responses.

[0751] "Machine learning technology" is a technique that uses algorithms to analyze data and use that information to generate questions and evaluate answers.

[0752] In this invention, a server is central to operating the system. The server first receives safety-related data input from users via terminals. The received data is analyzed using natural language processing technology within the server, and relevant information is retrieved from information storage devices. In particular, data on past work environments and standard safety guidelines are referenced.

[0753] Next, machine learning technology on the server is used to automatically generate optimal questions. In this generation process, the appropriateness and importance of the questions are evaluated based on relevant theories and past research results, and finally an electronic survey form is created. This survey form is sent to a robot via a terminal and presented to the worker by the robot.

[0754] The robot autonomously moves around the factory, presenting survey forms to workers and collecting responses in real time. The collected response data is sent to a server, where an evaluation algorithm identifies areas for improvement in the work environment. These results are immediately reported to factory managers, facilitating improvements on-site.

[0755] For example, if a new machine is introduced at a factory, the server can input a prompt message such as "Please create questions about the work environment after the introduction of the new equipment" into the AI ​​model, and then conduct a survey using the resulting questions.

[0756] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0757] Step 1:

[0758] The server accepts data input from users via a terminal. Users input data related to new safety standards, and this input data is analyzed using natural language processing technology. The results of the analysis include relevant keywords and contextual information.

[0759] Step 2:

[0760] Based on the analysis results, the server retrieves relevant past survey results and reference data from its information storage device. During this process, the retrieved data is filtered to select the information most relevant to the user's input.

[0761] Step 3:

[0762] The server uses the acquired information to leverage a machine learning model to generate optimal questions. A prompt such as "Please create questions about the workplace environment after the introduction of new equipment" is input, and the AI ​​model generates questions based on this.

[0763] Step 4:

[0764] The server formats the generated questions and creates an electronic survey form. During the formatting process, the layout and usability of the questions are optimized, resulting in an intuitive interface.

[0765] Step 5:

[0766] The terminal sends a survey form to the robot, which then uses it to present it to the worker. The robot moves around the factory and conducts the survey with the corresponding worker. This is coordinated by the robot's motion planning algorithm.

[0767] Step 6:

[0768] The robot collects responses from workers in real time and sends them to a server via a terminal. The response data is designed to be analyzed immediately, ensuring efficient data collection.

[0769] Step 7:

[0770] The server uses an analysis algorithm to detect areas for improvement in the field environment from the response data. The results of the analysis include specific areas requiring improvement and suggestions for improvement.

[0771] Step 8:

[0772] The server reports the analysis results to the factory manager and proposes necessary corrective actions. Based on these results, the manager promotes appropriate improvements to the on-site environment.

[0773] 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.

[0774] This invention relates to a system that, when receiving data input from a user, uses an emotion engine to recognize the user's emotions and generates optimal questions based on those emotions. This system creates questionnaires that take the user's emotional state into account, allowing for deeper insights.

[0775] The server uses an emotion engine to analyze emotional elements based on the text data received from the user. This emotion engine combines natural language processing technology and machine learning models to identify the emotional nuances contained in the sentences entered by the user.

[0776] Using the analyzed sentiment data, an artificial intelligence module on the server activates to generate an optimal set of questions that correspond to the user's emotional state. The generated questions are designed to encourage the user to respond more sincerely, taking into account how the questions relate to the user's current emotions.

[0777] After generating the questions, the server formats them into an electronic questionnaire. The questionnaire is designed to be intuitive and easy for respondents to answer. The questionnaire is then distributed to respondents through a designated medium.

[0778] Users answer the survey using their devices. The server collects the responses in real time and performs detailed statistical analysis, including sentiment analysis. The analyzed results are compiled into a report that reflects the user's emotional state and delivered to the information provider.

[0779] For example, if a user is dissatisfied with remote work, the emotion engine analyzes that dissatisfaction and generates questions about stress and fatigue. The data collected in this way can be used not only to improve the work environment but also to implement measures that take into account the psychological support of employees.

[0780] Thus, by incorporating emotion recognition, the present invention enhances the added value of the survey system and enables more reliable data collection.

[0781] The following describes the processing flow.

[0782] Step 1:

[0783] Users use their devices to input data, including the purpose of the survey and the information they want to know. The entered data is then sent to the server.

[0784] Step 2:

[0785] The server inputs the received data into an emotion engine, which uses natural language processing technology to analyze the emotional state of the text entered by the user. In this process, emotional nuances and keywords contained in the text are identified.

[0786] Step 3:

[0787] The server accesses the company's internal information storage and searches for past survey data and internal resources related to the extracted emotions. This integrates the results of the emotion analysis with the historical data.

[0788] Step 4:

[0789] An artificial intelligence module within the server generates a list of questions best suited to the user's emotional state based on this integrated data. This generation process reflects past success stories and relevant theories, selecting effective questions that align with the user's emotions.

[0790] Step 5:

[0791] The server formats the generated questions into an electronic questionnaire and optimizes the user interface. The questionnaire is designed to be intuitive and easy for respondents to answer.

[0792] Step 6:

[0793] The server handles the process of distributing questionnaires to the target individuals, which are then provided via email or the company's internal portal.

[0794] Step 7:

[0795] Users access the distributed survey using their device and enter their answers to the generated questions. The answers are immediately sent to the server.

[0796] Step 8:

[0797] The server aggregates responses in real time and performs detailed statistical analysis, including sentiment analysis results. In this process, the collected data is trended and patterns are identified.

[0798] Step 9:

[0799] The server generates a report based on the analysis results and provides it to the user. This report includes data insights linked to the user's emotional state, which can be used to develop practical strategies.

[0800] (Example 2)

[0801] 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".

[0802] Conventional data collection systems have struggled to generate flexible questions that take into account the emotional state of users, making it difficult to improve the accuracy and reliability of the data. Furthermore, there was a need for a mechanism that could generate questions appropriate to the emotions of the target audience and gain deeper insights.

[0803] 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.

[0804] In this invention, the server includes means for receiving information from the user and analyzing the natural state, means for generating optimal inquiries using generative artificial intelligence, and means for formatting the generated inquiries and creating an electronic questionnaire. This enables the generation of questions based on the user's emotional state and the collection of highly accurate data.

[0805] A "user" is an individual or legal entity that operates the system and provides or receives information.

[0806] "Information" refers to the text and data entered into a system, and analysis and processing are performed based on their content.

[0807] "Natural state" refers to the emotional or psychological nuances contained in the text data entered by the user.

[0808] "Emotional information" refers to data that indicates the user's emotions and psychological state, identified through natural language processing.

[0809] "Generative artificial intelligence" is a technology that uses machine learning models to generate optimal inquiries and creative content based on input information.

[0810] An "inquiry" refers to a question or command that is generated based on the user's emotions or state of mind.

[0811] An "electronic questionnaire" is a set of questions formatted in a digital format, used to conduct surveys with recipients.

[0812] "Statistical analysis" is a method for quantitatively analyzing collected data to identify trends and patterns.

[0813] This invention provides a system for generating questions based on the user's emotional state. First, the server receives information transmitted from the user via a terminal. This information includes feedback and comments. The received information is analyzed using natural language processing technology to identify the user's natural state, i.e., emotional or psychological nuances. Specifically, a machine learning model is used as the emotion engine to tokenize text and calculate an emotion score.

[0814] Based on the analyzed emotional information, the generative artificial intelligence on the server generates the most appropriate inquiry. In this process, a generative AI model is used to create prompts that match the user's emotional state, and then the question is designed based on these prompts. For example, if a user inputs "I am feeling stressed about remote work," the emotional engine can analyze that emotion and generate a question such as, "What kind of support do you think would be effective in alleviating the stress you feel while working remotely?"

[0815] The generated inquiries are formatted by the server and provided to the user as an electronic questionnaire. This questionnaire is designed to be easy for respondents to understand and answer. The questionnaire is distributed via email or a dedicated app, and users answer it using their devices.

[0816] The collected responses are aggregated on a server and statistically analyzed. In particular, by integrating sentiment analysis, it is possible to understand the changes and trends in users' emotions in detail. Based on this, the analysis results are created as a report and sent to the information provider. The analysis results are visualized in graphs and charts, providing information that accurately represents the user's emotional state, such as "stress tendencies in remote work."

[0817] An example of a prompt message is, "Analyze the user's sentiment from their input text and generate appropriate survey questions." In this way, flexible and highly accurate data collection tailored to the user's emotions is achieved.

[0818] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0819] Step 1:

[0820] The server receives information sent from the user via the terminal. This information includes user feedback and comments in text format. The server then temporarily stores the received data for analysis in the next step.

[0821] Step 2:

[0822] The server begins analyzing the received text data using natural language processing techniques. Specifically, it tokenizes the text and performs data calculations to identify emotional nuances using an emotion engine. The output of this analysis is data with an emotion score assigned to each word.

[0823] Step 3:

[0824] The server uses generative artificial intelligence to generate optimal questions, taking the emotional information obtained from the analysis as input. Here, the generative AI model operates, constructing prompt sentences based on the user's natural state, and designing a set of questions based on those prompts. The output of this step is the specific set of questions to be presented to the user.

[0825] Step 4:

[0826] The server formats the generated set of questions and creates an electronic questionnaire in a user-friendly format. Specifically, it adjusts the layout of the questionnaire and designs an interface that allows users to intuitively input their answers. The output is a distributable digital questionnaire.

[0827] Step 5:

[0828] The server distributes electronic questionnaires to users via email or app. The terminal opens the received questionnaire and provides functionality to enable users to enter their answers. The output in this step is the questionnaire in a state accessible to the user.

[0829] Step 6:

[0830] The user answers a questionnaire and sends it to the server via their device. The server receives the response data as input in real time and performs aggregation. It also performs sentiment analysis again and processes the data based on the aggregation results. The output of this step is aggregated data that includes the response data and the analysis results.

[0831] Step 7:

[0832] The server performs detailed statistical analysis based on the aggregated data and creates a report of the analysis results. Specifically, it generates graphs and charts to visually represent the user's emotional state and response trends. This report is then distributed to the information provider.

[0833] (Application Example 2)

[0834] 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".

[0835] When collecting customer feedback in physical stores, traditional surveys often fail to consider customer emotions, making it difficult to grasp true needs and problems. Furthermore, delays in addressing customer dissatisfaction can lead to decreased customer satisfaction.

[0836] 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.

[0837] In this invention, the server includes means for receiving data input from a user, means for recognizing the user's emotions using an emotion engine based on the data input, and means for generating optimal questions using artificial intelligence based on the recognized emotions. This makes it possible to quickly generate detailed and accurate questions based on customer emotions and improve the quality of surveys.

[0838] "Users" refer to end users who use this system and provide data.

[0839] "Data entry" refers to the information and feedback that users provide to the system.

[0840] An "emotion engine" is a processing device used to analyze the emotional elements contained in the user's data input.

[0841] "Recognizing emotions" refers to the process of identifying a user's emotional state from the input data.

[0842] Artificial intelligence is a technology that uses machine learning models to mimic human intellectual work.

[0843] "Generating questions" is the process of constructing appropriate questions based on user input data.

[0844] A "questionnaire" is a collection of questions presented to a user.

[0845] "Emotional analysis" is a technique that analyzes user response data to identify emotional tendencies.

[0846] The system implementing this invention understands the emotions of users when they provide feedback in a physical store and generates appropriate questions. The central components of this system include a server, a terminal, and an emotion engine.

[0847] The server accepts data input through terminals available in the store and through users' mobile devices. This data input includes free-form text and specific feedback from users, and the server receives this information in real time.

[0848] Next, the server uses an emotion engine to analyze the input text data and recognize the user's emotional state. This emotion engine utilizes technologies such as the Google Cloud Natural Language API or similar natural language processing (NLP) techniques to extract emotional characteristics such as positive, negative, and neutral from the user's statements.

[0849] After the emotional state is identified, an artificial intelligence module on the server activates and generates individually optimized questions using a generative AI model. This question generation process utilizes OpenAI's GPT-3 and other similar natural language generation models. The AI ​​module appropriately formats questions according to the user's emotional state and presents them immediately to the user's device, improving the user experience.

[0850] As a concrete example of this system, if a user enters dissatisfaction with a service delay, the emotion engine identifies the negative emotion and instantly generates and presents a question to the user such as, "We apologize for the delay. Specifically, which service improvements would you like to see?"

[0851] An example of a prompt for the generative AI model is: "Analyze the customer's sentiment from the following text and generate the most appropriate question based on that sentiment. Text: {customer input text}".

[0852] In this way, we aim to create a system that enhances the emotional basis of user interaction, contributing to improved store services and increased customer satisfaction.

[0853] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0854] Step 1:

[0855] The server accepts data input from the user's terminal. This data input consists of text information provided by the user. The server temporarily stores the received input data and prepares it for subsequent processing.

[0856] Step 2:

[0857] The server analyzes the input text data using an emotion engine. This emotion engine processes the input data using natural language processing techniques and classifies the user's emotional state as positive, negative, or neutral. Based on the analysis, it outputs tags and scores corresponding to the user's emotions.

[0858] Step 3:

[0859] An artificial intelligence module on the server uses a generative AI model to generate optimal questions based on the user's emotions. An example of a prompt is: "Analyze the customer's emotions from the following text and generate the optimal question based on those emotions. Text: {User input text}". This prompt is input to the AI ​​model, which then outputs an appropriate question.

[0860] Step 4:

[0861] The server formats the generated questions and converts them into a format that can be displayed on the user's device. By presenting questions in a format that is most relevant to the user's emotions, it enhances user engagement.

[0862] Step 5:

[0863] The terminal presents the user with a formatted question. The user answers the question, and the answer is sent back to the server. The server collects the user's answers in real time and stores them for further sentiment analysis.

[0864] Step 6:

[0865] The server performs statistical analysis, including sentiment analysis, based on the collected data. Based on the results of this analysis, it generates reports to improve the service quality of physical stores and provides them to managers and relevant parties.

[0866] 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.

[0867] 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.

[0868] 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.

[0869] 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.

[0870] 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.

[0871] 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.

[0872] 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.

[0873] 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.

[0874] 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."

[0875] 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.

[0876] 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.

[0877] 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.

[0878] 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.

[0879] 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.

[0880] 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.

[0881] 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.

[0882] 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.

[0883] 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.

[0884] 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.

[0885] 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.

[0886] 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.

[0887] The following is further disclosed regarding the embodiments described above.

[0888] (Claim 1)

[0889] The primary means of receiving data input from users,

[0890] A second means for obtaining related information from information storage based on the data input,

[0891] A third means that uses the acquired information to generate the optimal question using artificial intelligence,

[0892] A fourth means for formatting the generated questions and creating an electronic questionnaire,

[0893] A fifth method for distributing the questionnaire to the target persons,

[0894] A sixth method involves collecting and analyzing responses from the target individuals after distribution.

[0895] A system that includes this.

[0896] (Claim 2)

[0897] The system according to claim 1, wherein the first means analyzes data input using natural language processing.

[0898] (Claim 3)

[0899] The system according to claim 1, wherein the third means generates questions by referring to relevant theories and past research results.

[0900] "Example 1"

[0901] (Claim 1)

[0902] A processing means for receiving information input from users,

[0903] Based on the input of the information, an acquisition means for acquiring related knowledge from the storage area,

[0904] A generation means that uses the acquired knowledge to generate an optimal query using a data processing device,

[0905] A means for formatting the generated inquiry and creating an electronic investigation document,

[0906] A means of distributing the said survey documents to the patients,

[0907] An analytical means for collecting and analyzing responses from patients after distribution,

[0908] A system that includes this.

[0909] (Claim 2)

[0910] The system according to claim 1, wherein the processing means analyzes information input using natural language processing.

[0911] (Claim 3)

[0912] The system according to claim 1, wherein the generation means generates queries by referring to relevant theories and past research results.

[0913] "Application Example 1"

[0914] (Claim 1)

[0915] The primary means of receiving data input from users,

[0916] A second means for obtaining related information from an information storage device based on the data input,

[0917] A third means that uses the acquired information to generate optimal questions using machine learning technology,

[0918] A fourth means for formatting the generated questions and creating an electronic survey form,

[0919] A fifth means of distributing the survey form to the target individuals,

[0920] A sixth method involves collecting and evaluating responses from the target individuals after distribution,

[0921] A seventh method involves a robot presenting a survey form to a target individual and collecting responses.

[0922] An eighth means for detecting areas for improvement in the on-site environment based on the collected responses,

[0923] A system that includes this.

[0924] (Claim 2)

[0925] The system according to claim 1, wherein the first means analyzes data input using natural language processing.

[0926] (Claim 3)

[0927] The system according to claim 1, wherein the third means generates questions by referring to relevant theories and past research results.

[0928] "Example 2 of combining an emotion engine"

[0929] (Claim 1)

[0930] A means of receiving information from users and analyzing the natural state,

[0931] A means for generating the optimal inquiry using generative artificial intelligence based on the analyzed emotional information,

[0932] A means for formatting the generated inquiry and creating an electronic questionnaire,

[0933] Means for distributing the questionnaire to recipients,

[0934] A means for collecting responses from recipients after distribution and performing detailed statistical analysis, including sentiment analysis,

[0935] A system that includes this.

[0936] (Claim 2)

[0937] The system according to claim 1, wherein the means for analyzing the natural state is natural language processing technology.

[0938] (Claim 3)

[0939] The system according to claim 1, wherein the means for generating using the artificial intelligence for generation creates an input command sentence based on emotional information and designs a question based on that.

[0940] "Application example 2 when combining with an emotional engine"

[0941] (Claim 1)

[0942] The primary means of receiving data input from users,

[0943] A second means of recognizing the user's emotions using an emotion engine based on the data input,

[0944] A third means of generating the optimal question using artificial intelligence based on the recognized emotion,

[0945] A fourth means for reshaping the generated question to match the user's emotional state,

[0946] A fifth method for creating electronic questionnaires,

[0947] The sixth method involves distributing the questionnaire to the target individuals,

[0948] A seventh method involves collecting responses from the target individuals after distribution and conducting a detailed analysis, including sentiment analysis.

[0949] A system that includes this.

[0950] (Claim 2)

[0951] The system according to claim 1, wherein the first means analyzes data input using natural language processing.

[0952] (Claim 3)

[0953] The system according to claim 1, wherein the third means generates questions using a generating AI model based on the user's emotional state. [Explanation of Symbols]

[0954] 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. The primary means of receiving data input from users, A second means for obtaining related information from information storage based on the data input, A third means that uses the acquired information to generate the optimal question using artificial intelligence, A fourth means for formatting the generated questions and creating an electronic questionnaire, A fifth method for distributing the questionnaire to the target persons, A sixth method involves collecting and analyzing responses from the target individuals after distribution. A system that includes this.

2. The system according to claim 1, wherein the first means analyzes data input using natural language processing.

3. The system according to claim 1, wherein the third means generates questions by referring to relevant theories and past research results.

Images