system

Abstract

Provide a system. 【Solution means】 Means for displaying an initial question generated by an information processing device; Means for receiving and analyzing a user's answer to the initial question; Means for dynamically generating a follow-up question based on the analysis result; Means for presenting the follow-up question to the user; Means for collecting a user's re-answer and storing it in a database; Means for analyzing the stored data and extracting insights regarding the user's needs and feelings; Means for generating and outputting the insights as a report; A system including the above.

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, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance that responds 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 conventional questionnaire system, the questions are fixed, and it is difficult to perform dynamic follow-up based on the answers of users. Therefore, it is impossible to accurately grasp the essential needs, feelings, and intentions of respondents, and there are limitations in the accuracy and quality of market research. It is required to overcome such problems and draw out multi-faceted insights of users.

Means for Solving the Problems

[0005] This invention provides a means for dynamically generating appropriate follow-up questions based on the results of an analysis of the user's initial input, utilizing a generative AI model. The invention presents the user with an initial question generated using an information processing device, collects the user's responses, and analyzes their content. Based on these results, follow-up questions are generated and presented to the user, thereby accumulating and analyzing response data to extract deeper insights into the user's needs and emotions. This allows for the acquisition of higher-quality market research data and improved accuracy.

[0006] An "information processing device" is a device that receives, analyzes, processes, and stores data, and is a system that includes hardware such as computers and servers.

[0007] An "initial question" is the first question presented to the user at the start of a survey, and it is designed to gather general information.

[0008] A "user" is an individual or group that uses the survey system to enter their answers to the questions.

[0009] "Analysis" refers to the process of analyzing user response data and interpreting its content, including the identification of keywords and emotions.

[0010] "Follow-up questions" are additional questions generated based on the user's initial responses, with the aim of eliciting more detailed information.

[0011] A "database" is a digital storage medium or system used to structure and accumulate collected response data.

[0012] "Insight" refers to a deep understanding of user needs and emotions, extracted based on collected data.

[0013] A "report" is a document or digital file that summarizes and records analysis results and insights and provides them to stakeholders. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This 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] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] 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.

[0018] 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.

[0019] 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, etc.

[0020] 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).

[0021] 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."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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".

[0035] In implementing this invention, a server functioning as an information processing device plays a central role. First, the server identifies the user who initiated the survey and generates initial questions for that user. The initial questions are automatically created by a generation AI model according to the purpose and target audience of the survey and are presented to the user via a terminal.

[0036] The user enters answers to questions displayed on the interface. The terminal sends this user input to the server in real time. The server launches a program to analyze the received answers and identifies the user's possible intentions and emotions based on the analysis results. This analysis includes utilizing natural language processing techniques to grasp the meaning and tone of the answers.

[0037] Next, the server generates follow-up questions based on the analysis results to extract more detailed information. These follow-up questions are also dynamically generated by the generation AI model, allowing for flexible adaptation to the user's existing answers. The generated questions are then presented to the user again via the terminal, and the user continues to answer them.

[0038] The response data collected in this repeated manner is stored in a database on the server. This data is further analyzed to gain insights into user needs and emotions. The insights gained are automatically compiled into an analysis report by the server and provided to stakeholders in digital format.

[0039] For example, in market research, this system can be used to discover that a specific group of users is giving positive feedback on a new product. Follow-up questions can then be used to investigate specific functions or features in more detail, providing important insights for product development. Thus, this invention enables flexible and detailed questionnaire surveys, achieving the collection of high-quality data that cannot be obtained through conventional methods.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The server detects the start of a survey and generates initial questions to present to the user. Using a generation AI, it creates questions for basic information gathering and sends them to the device.

[0043] Step 2:

[0044] The terminal displays the initial questions received from the server to the user on the screen. The interface is adjusted to make it easier for the user to answer the questions.

[0045] Step 3:

[0046] The user enters their answers to the presented questions. The device sends the entered answers to the server in real time.

[0047] Step 4:

[0048] The server analyzes the user's responses. Using natural language processing techniques, it analyzes the content and emotional tone of the responses to estimate the respondent's intentions and needs.

[0049] Step 5:

[0050] The server generates follow-up questions based on the analysis results. It utilizes a generation AI to create dynamic questions that further explore the user's responses.

[0051] Step 6:

[0052] The server sends the generated follow-up questions to the terminal. The terminal displays them on the user's screen.

[0053] Step 7:

[0054] The user continues to answer follow-up questions. The device sends the user's responses back to the server, and this process is repeated until sufficient data has been collected.

[0055] Step 8:

[0056] The server stores all user response data in a database. This stored data is used for subsequent analysis.

[0057] Step 9:

[0058] The server conducts detailed analysis based on accumulated data to gain insights into user needs and emotions. From the analysis results, it generates reports useful for marketing and product development.

[0059] Step 10:

[0060] The server provides the generated reports to the relevant parties in digital format. This information is used according to the purpose of the investigation.

[0061] (Example 1)

[0062] 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."

[0063] Traditional survey methods have faced challenges in flexibly and quickly understanding respondents' intentions and emotions while generating questions, and in utilizing the collected data to gain highly accurate insights. Therefore, there is a need to provide a system that can automatically generate a sequence of questions that accurately reflect respondents' needs, and that enables the collection and analysis of high-quality data.

[0064] 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.

[0065] In this invention, the server includes means for identifying the caller using an information processing device and displaying an initial question that is generated; means for receiving the user's response to the initial question and analyzing it using natural language processing technology; and means for dynamically generating and adjusting follow-up questions using a generation AI model based on the analysis results. This makes it possible to more accurately grasp the user's intentions and emotions and flexibly generate questions accordingly, thereby enabling highly accurate data collection and the acquisition of insights.

[0066] An "information processing device" refers to a computer system that has the functions of inputting, processing, and outputting data.

[0067] "Initiator" refers to the user who starts a survey or questionnaire and enters their responses.

[0068] An "initial question" is the first question provided at the start of a survey, and it forms the basis for generating subsequent questions.

[0069] "Natural language processing technology" is a type of technology that enables computers to understand, interpret, and manipulate human language.

[0070] A "generative AI model" refers to a model that uses artificial intelligence to automatically generate questions and information.

[0071] "Follow-up questions" are additional questions generated based on the answers to the initial or previous questions, and their role is to elicit more detailed information from the user.

[0072] "User" refers to an individual who operates the survey system and provides answers to the questions.

[0073] A "data warehouse" is a system that centrally stores and manages large amounts of collected data for subsequent analysis.

[0074] "Insight" refers to a deep understanding of users' needs and emotions obtained through data analysis.

[0075] A "report" is a document that summarizes the results of an analysis and serves as a means of communicating the insights gained to relevant parties.

[0076] "Machine learning technology" is a type of technology that uses learning algorithms that allow computers to gain experience based on data and automatically improve their performance.

[0077] This system operates around a server that functions as an information processing device. The server utilizes advanced generative AI models to automatically generate dynamic questions based on user responses. Specifically, when a user starts a survey, the server identifies the user and creates initial questions using the generative AI model. These questions are then provided to the user via a terminal.

[0078] The user answers questions presented on the device, and the device sends these answers to the server in real time. The server analyzes the received answers using natural language processing technology. In doing so, it understands the meaning and emotional tone of the answers and generates more detailed and accurate follow-up questions.

[0079] For example, market research can use prompts such as "Please tell us your thoughts on this product" to collect specific feedback from users. In response to this feedback, the server can generate follow-up questions such as "What features do you particularly like?" to obtain even more valuable information.

[0080] The collected data is stored in a server-based data warehouse and analyzed using machine learning techniques. This provides deep insights into user needs and preferences, and reports based on this analysis are automatically generated. This system enables the collection and analysis of high-quality data, providing advanced information processing technology to support business decision-making.

[0081] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0082] Step 1:

[0083] When the server receives a request to start a survey, it identifies the sender. It receives user ID and session data as input, and as output, it generates initial questions using a generative AI model based on this information and sends them to the terminal. Specifically, the server generates questions such as "Please tell us about your area of ​​residence" based on the user's location.

[0084] Step 2:

[0085] The user enters their answers to the initial questions displayed on the terminal. The terminal formats this input data and sends the answer data to the server in real time as output. Specifically, the terminal sends the user's answer "Tokyo" to the server as a data packet.

[0086] Step 3:

[0087] The server receives responses from the terminal as input and analyzes them using natural language processing techniques. It evaluates the meaning and emotional tone of the data and identifies the interpreted intentions and emotions as output. Specifically, from the input "Tokyo," the server concludes that the user lives in a Japanese city.

[0088] Step 4:

[0089] Based on the analysis results, the server uses a generative AI model to generate follow-up questions. Using the analyzed intentions and emotions as input, it creates appropriate follow-up questions as output and sends them to the user via the terminal. For example, the server generates the follow-up question, "What is your favorite place in Tokyo?"

[0090] Step 5:

[0091] The user answers the follow-up questions again. The terminal receives the user's answers as input and sends them back to the server as output. The terminal then sends a specific answer such as "Ueno Park".

[0092] Step 6:

[0093] The server stores the response data and analyzes it again using natural language processing techniques. It receives the user's overall responses to multiple questions as input and outputs detailed insights into user needs and emotions. Specifically, the server extracts the insight that "users living in Tokyo prefer places with lots of nature."

[0094] Step 7:

[0095] The server compiles the analysis results into a report and provides it to relevant parties in digital format. It uses the analyzed data as input and generates and sends reports in PDF or email format as output. Specifically, the server creates a report including the insight that "women in their 20s in Tokyo prefer nature" and sends it to the relevant departments.

[0096] (Application Example 1)

[0097] 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."

[0098] In modern online sales, efficient and effective feedback collection is essential to improve user satisfaction after purchase and to facilitate product improvement. However, traditional surveys often present uniform questions, failing to fully grasp user intentions and emotions, and potentially missing valuable insights. Furthermore, the standardization of follow-up questions makes it difficult to elicit opinions based on specific user experiences. Therefore, there is a need for technology that maximizes user experience and collects high-quality data that contributes to product improvement.

[0099] 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.

[0100] In this invention, the server includes means for displaying initial questions generated by an information processing device, means for analyzing the user's answers to the initial questions, means for dynamically generating follow-up questions based on the analysis results, and means for collecting feedback on the user's post-purchase experience and outputting it as information that contributes to product improvement. This enables dynamic question development tailored to the user's individual emotions and intentions, making it possible to obtain highly accurate insights that contribute to product improvement.

[0101] An "information processing device" is a device used for collecting, analyzing, storing, and outputting data, and includes servers and computer systems.

[0102] An "initial question" is a question presented to a user at the beginning of a survey or feedback collection, forming the basis for the survey.

[0103] A "follow-up question" is an additional question that is generated after analyzing the user's response to the initial question and is presented to the user to obtain more detailed information.

[0104] "User emotional tone" refers to the nuances and atmosphere of emotions that can be gleaned from a user's responses and actions, and is an element used to personalize questions and results.

[0105] "Data storage" refers to a system or medium that systematically stores collected data and maintains it in a format that can be used for later analysis and report creation.

[0106] "Insight" refers to a deep understanding and perspective on user behavior and attitudes derived from collected and analyzed data.

[0107] A "report" is a document that organizes analyzed data and insights and provides them to stakeholders, and can be produced digitally or on paper.

[0108] "Post-purchase experience" refers to the user's impressions and opinions gained while actually using a product after purchase, and forms the basis of feedback.

[0109] To implement this invention, a server acting as an information processing device plays a central role. The server uses a generative AI model to create initial questions to present to the user. These questions are displayed on the user's terminal and form the basis for surveys and feedback.

[0110] When a user answers an initial question, that input is sent to the server in real time. The server uses natural language processing technology to analyze the user's response and extract its meaning and emotional tone. Based on this analysis, the server uses a generative AI model to dynamically generate follow-up questions. These follow-up questions change based on the user's answers, enabling the collection of more detailed information.

[0111] The data collected through these question-and-answer exchanges is stored in data storage. The server periodically analyzes this data to extract insights into user needs. The extracted insights are generated as reports to help improve products and are provided to stakeholders.

[0112] As a concrete example, consider a scenario where a user provides feedback on a product purchased from an online shopping site. If the initial question is "Are you satisfied with the product?" and the user responds "Yes, I particularly like the color," the server will generate a follow-up question such as "What aspects of the color did you particularly like?" This allows for question development based on the user's specific experience.

[0113] An example of a prompt is, "Based on the user's response, generate the following follow-up question. Response: I like the color." By inputting this prompt into the AI ​​model, follow-up questions tailored to the user's post-purchase experience can be effectively generated.

[0114] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0115] Step 1:

[0116] The server generates initial questions using a generative AI model. It uses the survey's purpose and user attribute data as input and sends the generated questions to the terminal. The output is the initial questions presented to the user. This process ensures that the user is shown appropriate questions tailored to their target audience.

[0117] Step 2:

[0118] The user enters their answers to initial questions displayed on the device. The device then sends this input data to the server. The input is the user's answer, and the output is the data transferred to the server. This process ensures that the server receives the user's answers, including their intentions and emotions.

[0119] Step 3:

[0120] The server analyzes the received user responses using natural language processing techniques. The input is user response data, and through semantic analysis and emotional tone extraction, the server outputs the user's intentions and emotions. The analysis results serve as foundational information for generating the next question. This process allows for a deeper understanding of the user's thoughts.

[0121] Step 4:

[0122] The server dynamically generates follow-up questions using an AI model based on the analysis results. The analysis results are used as input, and the output is the follow-up questions sent to the terminal. This process generates questions that appropriately provide detailed information based on the user's answers.

[0123] Step 5:

[0124] The user answers follow-up questions and resends the results to the server via the terminal. The input is the user's re-answer, and the output is the response data resent to the server. This process allows for the collection of further user feedback.

[0125] Step 6:

[0126] The server stores the collected user response data in data storage and performs periodic analysis. The input is the stored data, and the output is insights into user needs. This process provides information that is useful for long-term customer understanding and product improvement.

[0127] Step 7:

[0128] The server generates a report based on the insights gained and provides it to the relevant parties. The input is analytical data, and the output is a digital report. This process facilitates the sharing of information that can be used for marketing and product development strategies.

[0129] 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.

[0130] This invention provides an information processing system incorporating an emotion engine to analyze the user's emotional tone and gain in-depth insights through questionnaires. This system operates with a server at its core, coordinating with terminals and the emotion engine.

[0131] First, at the start of the survey, the server uses a generation AI to generate initial questions for the user. These questions are designed to elicit basic information relevant to the survey's purpose. The initial questions are displayed to the user via their device, and the user answers them. The device then sends the user's responses to the server in real time.

[0132] The server is equipped with an emotion engine that analyzes user responses, evaluating not only the content of the response but also the emotional tone. This evaluation identifies the emotions and intentions contained in the user's response, which helps in generating subsequent follow-up questions. Specifically, if the user shows positive emotions, it generates questions that delve deeper into those positive aspects, and if negative emotions are detected, it generates questions that explore the points of dissatisfaction the user is experiencing.

[0133] Data where emotional tone is recognized by the emotion engine is stored in the database just like regular response data. The server later analyzes this collected data in detail to gain insights into users' emotional tendencies. These insights are then compiled into reports useful for marketing and product development and provided to stakeholders.

[0134] For example, when surveying user feedback on a new product, this system can be used to reveal through sentiment analysis that certain users have a strong sense of satisfaction with the new features. At the same time, points of dissatisfaction with the features are also detected, allowing the development team to obtain specific feedback that can be used for improvement. In this way, the system of the present invention can respond to user needs more accurately than conventional survey methods.

[0135] The following describes the processing flow.

[0136] Step 1:

[0137] The server detects the start of the survey and generates initial questions using a generation AI. These questions collect basic information relevant to the survey's purpose and are presented to the user via the device.

[0138] Step 2:

[0139] The terminal displays the initial question received from the server to the user. The user reviews the displayed question and enters their answer.

[0140] Step 3:

[0141] The user enters their answers to an initial question, and the device sends this answer data to the server in real time.

[0142] Step 4:

[0143] The server uses an emotion engine to analyze the user's responses. It not only analyzes the content of the responses but also evaluates the emotional tone within the text to determine whether the response is positive, negative, neutral, or otherwise positive.

[0144] Step 5:

[0145] Based on the analysis results, the server generates follow-up questions. It dynamically constructs questions tailored to the user's response, taking into account emotional tone. For example, if the emotion is positive, it generates questions about related details.

[0146] Step 6:

[0147] The server sends the generated follow-up questions to the terminal. The terminal displays the new questions to the user and prompts them for the next answer.

[0148] Step 7:

[0149] The user continues to answer follow-up questions. The device sends the answers to the server, and this answering process is repeated until a predetermined condition or amount of data to be collected is reached.

[0150] Step 8:

[0151] The server stores all response data, along with corresponding sentiment data, in a database. This data forms the basis for subsequent analysis.

[0152] Step 9:

[0153] The server analyzes user needs and emotional trends based on accumulated data. Based on this analysis, it generates detailed reports to support marketing and product development decision-making.

[0154] Step 10:

[0155] The server provides the generated reports to stakeholders in digital format. The reports are customized to their specific purposes and designed to maximize user feedback.

[0156] (Example 2)

[0157] 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".

[0158] Traditional survey systems have difficulty capturing users' emotions and failing to fully understand their true needs. Furthermore, the fixed nature of follow-up questions makes it difficult to respond to individual user responses, resulting in reduced accuracy in data collection and analysis.

[0159] 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.

[0160] In this invention, the server includes means for presenting an initial question created by an information processing means, means for receiving and analyzing the user's response, and means for dynamically creating follow-up questions based on the analysis results. This makes it possible to present questions tailored to each user and to obtain deeper emotional insights based on them.

[0161] "Information processing means" refers to devices and software for inputting, analyzing, managing, and outputting information.

[0162] An "initial question" is a basic question presented to the user at the start of a survey, intended to collect initial information.

[0163] "Users" refer to individuals or groups who respond to the survey and are subject to evaluation by the system.

[0164] "Response" refers to the answer or reply that a user provides in response to a question presented to them.

[0165] "Follow-up questions" are additional questions generated based on the response to the initial question, and are intended to explore the user's emotions and intentions in more depth.

[0166] A "data storage device" refers to a physical or virtual recording medium used to store collected information.

[0167] "Emotional analysis" refers to the process of evaluating the emotional aspects contained in a user's response and analyzing their tone and intent.

[0168] A "report" refers to a document that organizes collected data and analysis results and is provided in visual or written form.

[0169] This invention provides a method for analyzing a user's emotional tone using an information processing system that integrates an emotion analysis engine, and for obtaining deeper insights through questionnaires. Specific embodiments for carrying out this invention are described below.

[0170] The server uses a generative AI model to create initial questions for users. This process utilizes past user data and information relevant to the survey's objectives. The generated questions form the foundation of the survey and are intended for initial information gathering. Specifically, the server generates questions such as, "What do you think of the new product?" These questions are designed to understand user opinions.

[0171] The terminal displays an initial question sent from the server to the user. The user responds, and the terminal sends the answer to the server in real time. At the same time, the response time and device information are also sent.

[0172] The sentiment analysis engine installed on the server analyzes the received response. The sentiment analysis engine uses language processing technology to analyze and evaluate the user's emotional tone from word choice and context. For example, if a user responds with "very satisfied," the sentiment analysis engine analyzes this as a positive emotion.

[0173] Based on the analysis results, the server generates follow-up questions. For positive responses, the server creates questions that delve deeper into the reasons, and for negative responses, it creates questions that explore the causes. For example, a follow-up question such as "In what ways are you satisfied with the new product?" is automatically generated.

[0174] Data containing users' emotional tones is stored in data storage devices, just like regular response data. The server analyzes the accumulated data to extract insights into users' emotional tendencies and needs. These insights are then provided as reports to aid in decision-making within relevant departments.

[0175] An example of a prompt message would be, "Please tell us how satisfied you are with the features of the new product. If you have any specific anecdotes, please share them." In this way, it is possible to gain a deep understanding of user emotions and needs throughout the entire system, which can contribute to improving products and services.

[0176] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0177] Step 1:

[0178] The server uses a generative AI model to generate initial questions according to the purpose of the survey. The input includes pre-configured survey objectives and target audience profiles. Based on this information, the generative AI model generates text and creates specific questions. The output is the initial questions to be presented to the user.

[0179] Specifically, the server retrieves past survey data from the database and creates the question, "What do you think about the new product?"

[0180] Step 2:

[0181] The terminal displays an initial question sent from the server to the user. The input is the initial question data from the server. By presenting this question to the user, the terminal prepares to receive the user's answer. The output is the question displayed to the user.

[0182] Specifically, a pop-up appears on the device, presenting the user with a question such as, "What do you think of the new product?"

[0183] Step 3:

[0184] The user enters their answers to questions displayed on the device. The input is text data containing the user's opinions and feelings. The user's answers are temporarily held on the device at this stage because they are sent to the server. The output is the user's response data.

[0185] Specifically, the user enters "Very satisfied" as their response, and the device temporarily records that response.

[0186] Step 4:

[0187] The terminal sends the user's responses to the server in real time. The input is the user response data obtained in step 3. The data is encrypted and sent to the server using secure communication. The output is the user's response data that reaches the server.

[0188] Specifically, the device encrypts the response "very satisfied" and sends it to the server.

[0189] Step 5:

[0190] The server analyzes user responses using an emotion analysis engine. The input is user response data sent from the terminal. Here, natural language processing techniques are used to evaluate the emotional tone from the responses. The output is data indicating the user's emotional tone.

[0191] Specifically, the server extracts the keyword "satisfied" and evaluates it as a positive emotion.

[0192] Step 6:

[0193] The server generates follow-up questions based on the analyzed sentiment tone data. The input is the user's sentiment tone information based on the sentiment analysis results. A generative AI model is used to create individually tailored follow-up questions. The output is the newly generated follow-up questions.

[0194] As a concrete action, it generates specific follow-up questions such as, "In what ways are you satisfied with the new product?"

[0195] Step 7:

[0196] The server presents the follow-up question to the user again via the terminal and waits for the user's response. The input is the generated follow-up question. The output is the new question presented to the user.

[0197] Specifically, a pop-up will reappear on the device, asking the question, "What aspects of the new product do you find appealing?"

[0198] Step 8:

[0199] The server stores all collected data in a data storage device, preparing it for later analysis. Inputs include user response data and sentiment tone data. Outputs are the information stored in the database.

[0200] In terms of specific actions, the server evaluates the accumulated data and prepares to analyze user opinions and emotional tendencies.

[0201] (Application Example 2)

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

[0203] Conventional user feedback collection systems have difficulty adequately analyzing users' emotions and intentions, and the feedback they provide has often remained superficial. As a result, companies may miss important insights for improving their products and services. This invention aims to solve these problems by analyzing users' emotional tones and gaining deeper insights.

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

[0205] In this invention, the server includes means for displaying basic questions generated by information processing means, means for analyzing the user's response to the basic questions, and means for generating supplementary questions based on the analysis results and emotional tone, and adjusting them based on the emotional evaluation. This makes it possible to collect and analyze detailed feedback on the user's emotions after purchase.

[0206] "Information processing means" refers to a device or system that has the function of receiving data, analyzing it, and generating and displaying necessary information.

[0207] "Basic questions" are the initial questions posed to elicit fundamental information and opinions from users.

[0208] "User responses" refer to the answers that users provide to basic questions and supplementary questions.

[0209] "Analysis results" refer to the results of an analysis obtained by an information processing device based on the user's response.

[0210] "Supplementary questions" are additional questions generated based on the analysis results and emotional tone.

[0211] "Emotional tone" refers to the emotional tendencies and nuances that can be gleaned from a user's response.

[0212] "Emotional assessment" refers to the analysis of a user's emotional tone and the identification and classification of the resulting emotions.

[0213] "Adjustment" means changing or modifying something to an appropriate state according to the circumstances and conditions.

[0214] "Feedback" refers to the collection of opinions and impressions from users.

[0215] This invention constructs an information processing system for collecting and analyzing user feedback. A specific embodiment is described below.

[0216] This system includes a server, terminals, and an emotion analysis engine. The terminals function as devices connected to the user, such as smartphones and computers, and have programs installed for information processing. The server functions as a central device for data analysis and storage. The emotion analysis engine can utilize emotion recognition software such as Microsoft® Azure® Emotion API. For generative AI, OpenAI® GPT models can be applied.

[0217] First, the device displays basic questions to the user. When the user responds to these basic questions, that information is sent to the server in real time. The server analyzes the received response data using an emotion analysis engine to evaluate the user's emotional tone. Then, based on the analysis results, it uses a generative AI to generate follow-up questions.

[0218] The generated follow-up questions are presented to the user immediately, and the responses are sent back to the server. The server stores the collected data on a recording medium and performs data analysis later. This process provides detailed insights into the user's requests and feelings, which are then generated as a report.

[0219] For example, this system can be useful when collecting feedback on a user's experience and performance after they purchase a new electronic device. If the user responds that they are "very satisfied," the generating AI can create follow-up questions such as, "Which features are you particularly satisfied with?"

[0220] An example of a prompt is: "Understand the emotional tone after product purchase and generate follow-up questions based on positive or negative feedback." This prompt allows the generating AI to automatically generate appropriate follow-up questions.

[0221] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0222] Step 1:

[0223] The terminal displays a basic question to the user. The input is the basic question sent from the server to the terminal. The terminal displays this question on the screen and waits for a response from the user. The output is the user's response in text format.

[0224] Step 2:

[0225] The user responds to a basic question. The input is the user's answer to the basic question. The user enters the answer through the terminal's input interface. The output is the user's response data, which is sent to the server in the next step.

[0226] Step 3:

[0227] The terminal sends user responses to the server in real time. The input is the response data entered by the user on the terminal. This data is securely transmitted to the server. The output is the user response data stored on the server.

[0228] Step 4:

[0229] The server analyzes the received response data using an emotion analysis engine. The input is the user's response data sent from the terminal. The server uses an emotion analysis engine (e.g., Microsoft Azure Emotion API) to evaluate the emotional tone underlying the response. The output is the result of the emotional tone analysis.

[0230] Step 5:

[0231] The server generates supplementary questions using a generative AI model based on the analysis results of the emotional tone. The input is the analysis results of the emotional tone. The server uses generative AI (e.g., OpenAI GPT model) and prompt sentences to generate appropriate supplementary questions. The output is the generated supplementary questions.

[0232] Step 6:

[0233] The server sends the generated supplementary questions to the terminal. The input is the generated supplementary questions. The server sends the data to the terminal in the appropriate format. The output is the supplementary questions displayed on the terminal.

[0234] Step 7:

[0235] The terminal presents the user with a generated supplementary question. The input is the supplementary question received from the server. The terminal displays this question on the screen and waits for a response from the user. The output is the user's response data.

[0236] Step 8:

[0237] The user responds to supplementary questions, and the terminal resends those answers to the server. The input is the user's responses to the supplementary questions. The data is securely transmitted to the server. The output is the user's re-responses, stored in the database.

[0238] Step 9:

[0239] The server performs a detailed analysis of user needs and emotions using accumulated response data. The input is all user response data stored in the database. The server extracts precise insights using data analysis tools. The output is the insights regarding user needs and emotions.

[0240] Step 10:

[0241] The server outputs a report based on the insights obtained. The input is the insights obtained through analysis. The server compiles the results in a report format and provides it to the necessary stakeholders. The output is a report useful for marketing and product development from various perspectives.

[0242] 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.

[0243] 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.

[0244] 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.

[0245] [Second Embodiment]

[0246] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0247] 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.

[0248] 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).

[0249] 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.

[0250] 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.

[0251] 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).

[0252] 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.

[0253] 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.

[0254] 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.

[0255] 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.

[0256] 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.

[0257] 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".

[0258] In implementing this invention, a server functioning as an information processing device plays a central role. First, the server identifies the user who initiated the survey and generates initial questions for that user. The initial questions are automatically created by a generation AI model according to the purpose and target audience of the survey and are presented to the user via a terminal.

[0259] The user enters answers to questions displayed on the interface. The terminal sends this user input to the server in real time. The server launches a program to analyze the received answers and identifies the user's possible intentions and emotions based on the analysis results. This analysis includes utilizing natural language processing techniques to grasp the meaning and tone of the answers.

[0260] Next, the server generates follow-up questions based on the analysis results to extract more detailed information. These follow-up questions are also dynamically generated by the generation AI model, allowing for flexible adaptation to the user's existing answers. The generated questions are then presented to the user again via the terminal, and the user continues to answer them.

[0261] The response data collected in this repeated manner is stored in a database on the server. This data is further analyzed to gain insights into user needs and emotions. The insights gained are automatically compiled into an analysis report by the server and provided to stakeholders in digital format.

[0262] For example, in market research, this system can be used to discover that a specific group of users is giving positive feedback on a new product. Follow-up questions can then be used to investigate specific functions or features in more detail, providing important insights for product development. Thus, this invention enables flexible and detailed questionnaire surveys, achieving the collection of high-quality data that cannot be obtained through conventional methods.

[0263] The following describes the processing flow.

[0264] Step 1:

[0265] The server detects the start of a survey and generates initial questions to present to the user. Using a generation AI, it creates questions for basic information gathering and sends them to the device.

[0266] Step 2:

[0267] The terminal displays the initial questions received from the server to the user on the screen. The interface is adjusted to make it easier for the user to answer the questions.

[0268] Step 3:

[0269] The user enters their answers to the presented questions. The device sends the entered answers to the server in real time.

[0270] Step 4:

[0271] The server analyzes the user's responses. Using natural language processing techniques, it analyzes the content and emotional tone of the responses to estimate the respondent's intentions and needs.

[0272] Step 5:

[0273] The server generates follow-up questions based on the analysis results. It utilizes a generation AI to create dynamic questions that further explore the user's responses.

[0274] Step 6:

[0275] The server sends the generated follow-up questions to the terminal. The terminal displays them on the user's screen.

[0276] Step 7:

[0277] The user continues to answer follow-up questions. The device sends the user's responses back to the server, and this process is repeated until sufficient data has been collected.

[0278] Step 8:

[0279] The server stores all user response data in a database. This stored data is used for subsequent analysis.

[0280] Step 9:

[0281] Based on the accumulated data, the server performs a detailed analysis to gain insights into the user's needs and emotions. Reports useful for marketing and product development are created from the analysis results.

[0282] Step 10:

[0283] The server provides the created report to the relevant parties in digital format. This information is utilized according to the purpose of the investigation.

[0284] (Example 1)

[0285] Next, Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0286] In the conventional questionnaire survey method, there is a problem that it is difficult to generate questions while flexibly and quickly grasping the intentions and emotions of the respondents and obtain accurate insights by utilizing the collected data. Therefore, it is necessary to provide a system that can automatically generate a chain of questions that accurately reflect the needs of the respondents and collect and analyze high-quality data.

[0287] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0288] In this invention, the server includes means for identifying the sender by an information processing device and displaying the generated initial questions, means for receiving the user's answers to the initial questions and analyzing them using natural language processing technology, and means for dynamically generating and adjusting follow-up questions by an AI model based on the analysis results. Thereby, it becomes possible to more accurately grasp the intentions and emotions of the user and flexibly generate corresponding questions, enabling the collection of high-precision data and the acquisition of insights.

[0289] An "information processing device" refers to a computer system that has the functions of inputting, processing, and outputting data.

[0290] "Initiator" refers to the user who starts a survey or questionnaire and enters their responses.

[0291] An "initial question" is the first question provided at the start of a survey, and it forms the basis for generating subsequent questions.

[0292] "Natural language processing technology" is a type of technology that enables computers to understand, interpret, and manipulate human language.

[0293] A "generative AI model" refers to a model that uses artificial intelligence to automatically generate questions and information.

[0294] "Follow-up questions" are additional questions generated based on the answers to the initial or previous questions, and their role is to elicit more detailed information from the user.

[0295] "User" refers to an individual who operates the survey system and provides answers to the questions.

[0296] A "data warehouse" is a system that centrally stores and manages large amounts of collected data for subsequent analysis.

[0297] "Insight" refers to a deep understanding of users' needs and emotions obtained through data analysis.

[0298] A "report" is a document that summarizes the results of an analysis and serves as a means of communicating the insights gained to relevant parties.

[0299] "Machine learning technology" is a type of technology that uses learning algorithms that allow computers to gain experience based on data and automatically improve their performance.

[0300] This system operates around a server that functions as an information processing device. The server utilizes advanced generative AI models to automatically generate dynamic questions based on user responses. Specifically, when a user starts a survey, the server identifies the user and creates initial questions using the generative AI model. These questions are then provided to the user via a terminal.

[0301] The user answers questions presented on the device, and the device sends these answers to the server in real time. The server analyzes the received answers using natural language processing technology. In doing so, it understands the meaning and emotional tone of the answers and generates more detailed and accurate follow-up questions.

[0302] For example, market research can use prompts such as "Please tell us your thoughts on this product" to collect specific feedback from users. In response to this feedback, the server can generate follow-up questions such as "What features do you particularly like?" to obtain even more valuable information.

[0303] The collected data is stored in a server-based data warehouse and analyzed using machine learning techniques. This provides deep insights into user needs and preferences, and reports based on this analysis are automatically generated. This system enables the collection and analysis of high-quality data, providing advanced information processing technology to support business decision-making.

[0304] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0305] Step 1:

[0306] When the server receives a request to start a survey, it identifies the sender. It receives user ID and session data as input, and as output, it generates initial questions using a generative AI model based on this information and sends them to the terminal. Specifically, the server generates questions such as "Please tell us about your area of ​​residence" based on the user's location.

[0307] Step 2:

[0308] The user inputs an answer to the initial question displayed on the terminal. The terminal formats this input data and sends the answer data to the server in real time as output. Specifically, the terminal sends the user's answer "Tokyo" to the server as a data packet.

[0309] Step 3:

[0310] The server obtains the answer received from the terminal as input and analyzes it using natural language processing technology. It evaluates the meaning and sentiment tone of the data and identifies the interpreted intent and sentiment as output. As a specific operation, the server concludes from the input "Tokyo" that the user lives in a city in Japan.

[0311] Step 4:

[0312] Based on the analysis results, the server utilizes the generative AI model to generate follow-up questions. Using the analyzed intent and sentiment as input, it creates appropriate follow-up questions as output and sends them to the user via the terminal. As a specific example, the server generates a follow-up question "What is your favorite place in Tokyo?"

[0313] Step 5:

[0314] The user answers the follow-up question again. The terminal receives the user's answer as input and sends it to the server again as output. An operation is performed where the terminal sends a specific answer such as "Ueno Park".

[0315] Step 6:

[0316] The server stores the response data and analyzes it again using natural language processing techniques. It receives the user's overall responses to multiple questions as input and outputs detailed insights into user needs and emotions. Specifically, the server extracts the insight that "users living in Tokyo prefer places with lots of nature."

[0317] Step 7:

[0318] The server compiles the analysis results into a report and provides it to relevant parties in digital format. It uses the analyzed data as input and generates and sends reports in PDF or email format as output. Specifically, the server creates a report including the insight that "women in their 20s in Tokyo prefer nature" and sends it to the relevant departments.

[0319] (Application Example 1)

[0320] 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."

[0321] In modern online sales, efficient and effective feedback collection is essential to improve user satisfaction after purchase and to facilitate product improvement. However, traditional surveys often present uniform questions, failing to fully grasp user intentions and emotions, and potentially missing valuable insights. Furthermore, the standardization of follow-up questions makes it difficult to elicit opinions based on specific user experiences. Therefore, there is a need for technology that maximizes user experience and collects high-quality data that contributes to product improvement.

[0322] 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.

[0323] In this invention, the server includes means for displaying initial questions generated by an information processing device, means for analyzing the user's answers to the initial questions, means for dynamically generating follow-up questions based on the analysis results, and means for collecting feedback on the user's post-purchase experience and outputting it as information that contributes to product improvement. This enables dynamic question development tailored to the user's individual emotions and intentions, making it possible to obtain highly accurate insights that contribute to product improvement.

[0324] An "information processing device" is a device used for collecting, analyzing, storing, and outputting data, and includes servers and computer systems.

[0325] An "initial question" is a question presented to a user at the beginning of a survey or feedback collection, forming the basis for the survey.

[0326] A "follow-up question" is an additional question that is generated after analyzing the user's response to the initial question and is presented to the user to obtain more detailed information.

[0327] "User emotional tone" refers to the nuances and atmosphere of emotions that can be gleaned from a user's responses and actions, and is an element used to personalize questions and results.

[0328] "Data storage" refers to a system or medium that systematically stores collected data and maintains it in a format that can be used for later analysis and report creation.

[0329] "Insight" refers to a deep understanding and perspective on user behavior and attitudes derived from collected and analyzed data.

[0330] A "report" is a document that organizes analyzed data and insights and provides them to stakeholders, and can be produced digitally or on paper.

[0331] "Post-purchase experience" refers to the user's impressions and opinions gained while actually using a product after purchase, and forms the basis of feedback.

[0332] To implement this invention, a server acting as an information processing device plays a central role. The server uses a generative AI model to create initial questions to present to the user. These questions are displayed on the user's terminal and form the basis for surveys and feedback.

[0333] When a user answers an initial question, that input is sent to the server in real time. The server uses natural language processing technology to analyze the user's response and extract its meaning and emotional tone. Based on this analysis, the server uses a generative AI model to dynamically generate follow-up questions. These follow-up questions change based on the user's answers, enabling the collection of more detailed information.

[0334] The data collected through these question-and-answer exchanges is stored in data storage. The server periodically analyzes this data to extract insights into user needs. The extracted insights are generated as reports to help improve products and are provided to stakeholders.

[0335] As a concrete example, consider a scenario where a user provides feedback on a product purchased from an online shopping site. If the initial question is "Are you satisfied with the product?" and the user responds "Yes, I particularly like the color," the server will generate a follow-up question such as "What aspects of the color did you particularly like?" This allows for question development based on the user's specific experience.

[0336] An example of a prompt is, "Based on the user's response, generate the following follow-up question. Response: I like the color." By inputting this prompt into the AI ​​model, follow-up questions tailored to the user's post-purchase experience can be effectively generated.

[0337] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0338] Step 1:

[0339] The server generates initial questions using a generative AI model. It uses the survey's purpose and user attribute data as input and sends the generated questions to the terminal. The output is the initial questions presented to the user. This process ensures that the user is shown appropriate questions tailored to their target audience.

[0340] Step 2:

[0341] The user enters their answers to initial questions displayed on the device. The device then sends this input data to the server. The input is the user's answer, and the output is the data transferred to the server. This process ensures that the server receives the user's answers, including their intentions and emotions.

[0342] Step 3:

[0343] The server analyzes the received user responses using natural language processing techniques. The input is user response data, and through semantic analysis and emotional tone extraction, the server outputs the user's intentions and emotions. The analysis results serve as foundational information for generating the next question. This process allows for a deeper understanding of the user's thoughts.

[0344] Step 4:

[0345] The server dynamically generates follow-up questions using an AI model based on the analysis results. The analysis results are used as input, and the output is the follow-up questions sent to the terminal. This process generates questions that appropriately provide detailed information based on the user's answers.

[0346] Step 5:

[0347] The user answers follow-up questions and resends the results to the server via the terminal. The input is the user's re-answer, and the output is the response data resent to the server. This process allows for the collection of further user feedback.

[0348] Step 6:

[0349] The server stores the collected user response data in data storage and performs periodic analysis. The input is the stored data, and the output is insights into user needs. This process provides information that is useful for long-term customer understanding and product improvement.

[0350] Step 7:

[0351] The server generates a report based on the insights gained and provides it to the relevant parties. The input is analytical data, and the output is a digital report. This process facilitates the sharing of information that can be used for marketing and product development strategies.

[0352] 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.

[0353] This invention provides an information processing system incorporating an emotion engine to analyze the user's emotional tone and gain in-depth insights through questionnaires. This system operates with a server at its core, coordinating with terminals and the emotion engine.

[0354] First, at the start of the survey, the server uses a generation AI to generate initial questions for the user. These questions are designed to elicit basic information relevant to the survey's purpose. The initial questions are displayed to the user via their device, and the user answers them. The device then sends the user's responses to the server in real time.

[0355] The server is equipped with an emotion engine that analyzes user responses, evaluating not only the content of the response but also the emotional tone. This evaluation identifies the emotions and intentions contained in the user's response, which helps in generating subsequent follow-up questions. Specifically, if the user shows positive emotions, it generates questions that delve deeper into those positive aspects, and if negative emotions are detected, it generates questions that explore the points of dissatisfaction the user is experiencing.

[0356] Data where emotional tone is recognized by the emotion engine is stored in the database just like regular response data. The server later analyzes this collected data in detail to gain insights into users' emotional tendencies. These insights are then compiled into reports useful for marketing and product development and provided to stakeholders.

[0357] For example, when surveying user feedback on a new product, this system can be used to reveal through sentiment analysis that certain users have a strong sense of satisfaction with the new features. At the same time, points of dissatisfaction with the features are also detected, allowing the development team to obtain specific feedback that can be used for improvement. In this way, the system of the present invention can respond to user needs more accurately than conventional survey methods.

[0358] The following describes the processing flow.

[0359] Step 1:

[0360] The server detects the start of the survey and generates initial questions using a generation AI. These questions collect basic information relevant to the survey's purpose and are presented to the user via the device.

[0361] Step 2:

[0362] The terminal displays the initial question received from the server to the user. The user reviews the displayed question and enters their answer.

[0363] Step 3:

[0364] The user enters their answers to an initial question, and the device sends this answer data to the server in real time.

[0365] Step 4:

[0366] The server uses an emotion engine to analyze the user's responses. It not only analyzes the content of the responses but also evaluates the emotional tone within the text to determine whether the response is positive, negative, neutral, or otherwise positive.

[0367] Step 5:

[0368] Based on the analysis results, the server generates follow-up questions. It dynamically constructs questions tailored to the user's response, taking into account emotional tone. For example, if the emotion is positive, it generates questions about related details.

[0369] Step 6:

[0370] The server sends the generated follow-up questions to the terminal. The terminal displays the new questions to the user and prompts them for the next answer.

[0371] Step 7:

[0372] The user continues to answer follow-up questions. The device sends the answers to the server, and this answering process is repeated until a predetermined condition or amount of data to be collected is reached.

[0373] Step 8:

[0374] The server stores all response data, along with corresponding sentiment data, in a database. This data forms the basis for subsequent analysis.

[0375] Step 9:

[0376] The server analyzes user needs and emotional trends based on accumulated data. Based on this analysis, it generates detailed reports to support marketing and product development decision-making.

[0377] Step 10:

[0378] The server provides the generated reports to stakeholders in digital format. The reports are customized to their specific purposes and designed to maximize user feedback.

[0379] (Example 2)

[0380] 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".

[0381] Traditional survey systems have difficulty capturing users' emotions and failing to fully understand their true needs. Furthermore, the fixed nature of follow-up questions makes it difficult to respond to individual user responses, resulting in reduced accuracy in data collection and analysis.

[0382] 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.

[0383] In this invention, the server includes means for presenting an initial question created by an information processing means, means for receiving and analyzing the user's response, and means for dynamically creating follow-up questions based on the analysis results. This makes it possible to present questions tailored to each user and to obtain deeper emotional insights based on them.

[0384] "Information processing means" refers to devices and software for inputting, analyzing, managing, and outputting information.

[0385] An "initial question" is a basic question presented to the user at the start of a survey, intended to collect initial information.

[0386] "Users" refer to individuals or groups who respond to the survey and are subject to evaluation by the system.

[0387] "Response" refers to the answer or reply that a user provides in response to a question presented to them.

[0388] "Follow-up questions" are additional questions generated based on the response to the initial question, and are intended to explore the user's emotions and intentions in more depth.

[0389] A "data storage device" refers to a physical or virtual recording medium used to store collected information.

[0390] "Emotional analysis" refers to the process of evaluating the emotional aspects contained in a user's response and analyzing their tone and intent.

[0391] A "report" refers to a document that organizes collected data and analysis results and is provided in visual or written form.

[0392] This invention provides a method for analyzing a user's emotional tone using an information processing system that integrates an emotion analysis engine, and for obtaining deeper insights through questionnaires. Specific embodiments for carrying out this invention are described below.

[0393] The server uses a generative AI model to create initial questions for users. This process utilizes past user data and information relevant to the survey's objectives. The generated questions form the foundation of the survey and are intended for initial information gathering. Specifically, the server generates questions such as, "What do you think of the new product?" These questions are designed to understand user opinions.

[0394] The terminal displays an initial question sent from the server to the user. The user responds, and the terminal sends the answer to the server in real time. At the same time, the response time and device information are also sent.

[0395] The sentiment analysis engine installed on the server analyzes the received response. The sentiment analysis engine uses language processing technology to analyze and evaluate the user's emotional tone from word choice and context. For example, if a user responds with "very satisfied," the sentiment analysis engine analyzes this as a positive emotion.

[0396] Based on the analysis results, the server generates follow-up questions. For positive responses, the server creates questions that delve deeper into the reasons, and for negative responses, it creates questions that explore the causes. For example, a follow-up question such as "In what ways are you satisfied with the new product?" is automatically generated.

[0397] Data containing users' emotional tones is stored in data storage devices, just like regular response data. The server analyzes the accumulated data to extract insights into users' emotional tendencies and needs. These insights are then provided as reports to aid in decision-making within relevant departments.

[0398] An example of a prompt message would be, "Please tell us how satisfied you are with the features of the new product. If you have any specific anecdotes, please share them." In this way, it is possible to gain a deep understanding of user emotions and needs throughout the entire system, which can contribute to improving products and services.

[0399] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0400] Step 1:

[0401] The server uses a generative AI model to generate initial questions according to the purpose of the survey. The input includes pre-configured survey objectives and target audience profiles. Based on this information, the generative AI model generates text and creates specific questions. The output is the initial questions to be presented to the user.

[0402] Specifically, the server retrieves past survey data from the database and creates the question, "What do you think about the new product?"

[0403] Step 2:

[0404] The terminal displays an initial question sent from the server to the user. The input is the initial question data from the server. By presenting this question to the user, the terminal prepares to receive the user's answer. The output is the question displayed to the user.

[0405] Specifically, a pop-up appears on the device, presenting the user with a question such as, "What do you think of the new product?"

[0406] Step 3:

[0407] The user enters their answers to questions displayed on the device. The input is text data containing the user's opinions and feelings. The user's answers are temporarily held on the device at this stage because they are sent to the server. The output is the user's response data.

[0408] Specifically, the user enters "Very satisfied" as their response, and the device temporarily records that response.

[0409] Step 4:

[0410] The terminal sends the user's responses to the server in real time. The input is the user response data obtained in step 3. The data is encrypted and sent to the server using secure communication. The output is the user's response data that reaches the server.

[0411] Specifically, the device encrypts the response "very satisfied" and sends it to the server.

[0412] Step 5:

[0413] The server analyzes user responses using an emotion analysis engine. The input is user response data sent from the terminal. Here, natural language processing techniques are used to evaluate the emotional tone from the responses. The output is data indicating the user's emotional tone.

[0414] Specifically, the server extracts the keyword "satisfied" and evaluates it as a positive emotion.

[0415] Step 6:

[0416] The server generates follow-up questions based on the analyzed sentiment tone data. The input is the user's sentiment tone information based on the sentiment analysis results. A generative AI model is used to create individually tailored follow-up questions. The output is the newly generated follow-up questions.

[0417] As a concrete action, it generates specific follow-up questions such as, "In what ways are you satisfied with the new product?"

[0418] Step 7:

[0419] The server presents the follow-up question to the user again via the terminal and waits for the user's response. The input is the generated follow-up question. The output is the new question presented to the user.

[0420] Specifically, a pop-up will reappear on the device, asking the question, "What aspects of the new product do you find appealing?"

[0421] Step 8:

[0422] The server stores all collected data in a data storage device, preparing it for later analysis. Inputs include user response data and sentiment tone data. Outputs are the information stored in the database.

[0423] In terms of specific actions, the server evaluates the accumulated data and prepares to analyze user opinions and emotional tendencies.

[0424] (Application Example 2)

[0425] 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."

[0426] Conventional user feedback collection systems have difficulty adequately analyzing users' emotions and intentions, and the feedback they provide has often remained superficial. As a result, companies may miss important insights for improving their products and services. This invention aims to solve these problems by analyzing users' emotional tones and gaining deeper insights.

[0427] 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.

[0428] In this invention, the server includes means for displaying basic questions generated by information processing means, means for analyzing the user's response to the basic questions, and means for generating supplementary questions based on the analysis results and emotional tone, and adjusting them based on the emotional evaluation. This makes it possible to collect and analyze detailed feedback on the user's emotions after purchase.

[0429] "Information processing means" refers to a device or system that has the function of receiving data, analyzing it, and generating and displaying necessary information.

[0430] "Basic questions" are the initial questions posed to elicit fundamental information and opinions from users.

[0431] "User responses" refer to the answers that users provide to basic questions and supplementary questions.

[0432] "Analysis results" refer to the results of an analysis obtained by an information processing device based on the user's response.

[0433] "Supplementary questions" are additional questions generated based on the analysis results and emotional tone.

[0434] "Emotional tone" refers to the emotional tendencies and nuances that can be gleaned from a user's response.

[0435] "Emotional assessment" refers to the analysis of a user's emotional tone and the identification and classification of the resulting emotions.

[0436] "Adjustment" means changing or modifying something to an appropriate state according to the circumstances and conditions.

[0437] "Feedback" refers to the collection of opinions and impressions from users.

[0438] This invention constructs an information processing system for collecting and analyzing user feedback. A specific embodiment is described below.

[0439] This system includes a server, terminals, and an emotion analysis engine. The terminals function as devices connected to users, such as smartphones and computers, and have programs installed for information processing. The server functions as a central device for data analysis and storage. The emotion analysis engine can utilize emotion recognition software such as the Microsoft Azure Emotion API. For generative AI, OpenAI GPT models and others can be applied.

[0440] First, the device displays basic questions to the user. When the user responds to these basic questions, that information is sent to the server in real time. The server analyzes the received response data using an emotion analysis engine to evaluate the user's emotional tone. Then, based on the analysis results, it uses a generative AI to generate follow-up questions.

[0441] The generated follow-up questions are presented to the user immediately, and the responses are sent back to the server. The server stores the collected data on a recording medium and performs data analysis later. This process provides detailed insights into the user's requests and feelings, which are then generated as a report.

[0442] For example, this system can be useful when collecting feedback on a user's experience and performance after they purchase a new electronic device. If the user responds that they are "very satisfied," the generating AI can create follow-up questions such as, "Which features are you particularly satisfied with?"

[0443] An example of a prompt is: "Understand the emotional tone after product purchase and generate follow-up questions based on positive or negative feedback." This prompt allows the generating AI to automatically generate appropriate follow-up questions.

[0444] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0445] Step 1:

[0446] The terminal displays a basic question to the user. The input is the basic question sent from the server to the terminal. The terminal displays this question on the screen and waits for a response from the user. The output is the user's response in text format.

[0447] Step 2:

[0448] The user responds to a basic question. The input is the user's answer to the basic question. The user enters the answer through the terminal's input interface. The output is the user's response data, which is sent to the server in the next step.

[0449] Step 3:

[0450] The terminal sends user responses to the server in real time. The input is the response data entered by the user on the terminal. This data is securely transmitted to the server. The output is the user response data stored on the server.

[0451] Step 4:

[0452] The server analyzes the received response data using an emotion analysis engine. The input is the user's response data sent from the terminal. The server uses an emotion analysis engine (e.g., Microsoft Azure Emotion API) to evaluate the emotional tone underlying the response. The output is the result of the emotional tone analysis.

[0453] Step 5:

[0454] The server generates supplementary questions using a generative AI model based on the analysis results of the emotional tone. The input is the analysis results of the emotional tone. The server uses generative AI (e.g., OpenAI GPT model) and prompt sentences to generate appropriate supplementary questions. The output is the generated supplementary questions.

[0455] Step 6:

[0456] The server sends the generated supplementary questions to the terminal. The input is the generated supplementary questions. The server sends the data to the terminal in the appropriate format. The output is the supplementary questions displayed on the terminal.

[0457] Step 7:

[0458] The terminal presents the user with a generated supplementary question. The input is the supplementary question received from the server. The terminal displays this question on the screen and waits for a response from the user. The output is the user's response data.

[0459] Step 8:

[0460] The user responds to supplementary questions, and the terminal resends those answers to the server. The input is the user's responses to the supplementary questions. The data is securely transmitted to the server. The output is the user's re-responses, stored in the database.

[0461] Step 9:

[0462] The server performs a detailed analysis of user needs and emotions using accumulated response data. The input is all user response data stored in the database. The server extracts precise insights using data analysis tools. The output is the insights regarding user needs and emotions.

[0463] Step 10:

[0464] The server outputs a report based on the insights obtained. The input is the insights obtained through analysis. The server compiles the results in a report format and provides it to the necessary stakeholders. The output is a report useful for marketing and product development from various perspectives.

[0465] 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.

[0466] 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.

[0467] 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.

[0468] [Third Embodiment]

[0469] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0470] 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.

[0471] 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).

[0472] 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.

[0473] 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.

[0474] 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).

[0475] 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.

[0476] 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.

[0477] 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.

[0478] 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.

[0479] 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.

[0480] 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".

[0481] In implementing this invention, a server functioning as an information processing device plays a central role. First, the server identifies the user who initiated the survey and generates initial questions for that user. The initial questions are automatically created by a generation AI model according to the purpose and target audience of the survey and are presented to the user via a terminal.

[0482] The user enters answers to questions displayed on the interface. The terminal sends this user input to the server in real time. The server launches a program to analyze the received answers and identifies the user's possible intentions and emotions based on the analysis results. This analysis includes utilizing natural language processing techniques to grasp the meaning and tone of the answers.

[0483] Next, the server generates follow-up questions based on the analysis results to extract more detailed information. These follow-up questions are also dynamically generated by the generation AI model, allowing for flexible adaptation to the user's existing answers. The generated questions are then presented to the user again via the terminal, and the user continues to answer them.

[0484] The response data collected in this repeated manner is stored in a database on the server. This data is further analyzed to gain insights into user needs and emotions. The insights gained are automatically compiled into an analysis report by the server and provided to stakeholders in digital format.

[0485] For example, in market research, this system can be used to discover that a specific group of users is giving positive feedback on a new product. Follow-up questions can then be used to investigate specific functions or features in more detail, providing important insights for product development. Thus, this invention enables flexible and detailed questionnaire surveys, achieving the collection of high-quality data that cannot be obtained through conventional methods.

[0486] The following describes the processing flow.

[0487] Step 1:

[0488] The server detects the start of a survey and generates initial questions to present to the user. Using a generation AI, it creates questions for basic information gathering and sends them to the device.

[0489] Step 2:

[0490] The terminal displays the initial questions received from the server to the user on the screen. The interface is adjusted to make it easier for the user to answer the questions.

[0491] Step 3:

[0492] The user enters their answers to the presented questions. The device sends the entered answers to the server in real time.

[0493] Step 4:

[0494] The server analyzes the user's responses. Using natural language processing techniques, it analyzes the content and emotional tone of the responses to estimate the respondent's intentions and needs.

[0495] Step 5:

[0496] The server generates follow-up questions based on the analysis results. It utilizes a generation AI to create dynamic questions that further explore the user's responses.

[0497] Step 6:

[0498] The server sends the generated follow-up questions to the terminal. The terminal displays them on the user's screen.

[0499] Step 7:

[0500] The user continues to answer follow-up questions. The device sends the user's responses back to the server, and this process is repeated until sufficient data has been collected.

[0501] Step 8:

[0502] The server stores all user response data in a database. This stored data is used for subsequent analysis.

[0503] Step 9:

[0504] The server conducts detailed analysis based on accumulated data to gain insights into user needs and emotions. From the analysis results, it generates reports useful for marketing and product development.

[0505] Step 10:

[0506] The server provides the generated reports to the relevant parties in digital format. This information is used according to the purpose of the investigation.

[0507] (Example 1)

[0508] 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."

[0509] Traditional survey methods have faced challenges in flexibly and quickly understanding respondents' intentions and emotions while generating questions, and in utilizing the collected data to gain highly accurate insights. Therefore, there is a need to provide a system that can automatically generate a sequence of questions that accurately reflect respondents' needs, and that enables the collection and analysis of high-quality data.

[0510] 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.

[0511] In this invention, the server includes means for identifying the caller using an information processing device and displaying an initial question that is generated; means for receiving the user's response to the initial question and analyzing it using natural language processing technology; and means for dynamically generating and adjusting follow-up questions using a generation AI model based on the analysis results. This makes it possible to more accurately grasp the user's intentions and emotions and flexibly generate questions accordingly, thereby enabling highly accurate data collection and the acquisition of insights.

[0512] An "information processing device" refers to a computer system that has the functions of inputting, processing, and outputting data.

[0513] "Initiator" refers to the user who starts a survey or questionnaire and enters their responses.

[0514] An "initial question" is the first question provided at the start of a survey, and it forms the basis for generating subsequent questions.

[0515] "Natural language processing technology" is a type of technology that enables computers to understand, interpret, and manipulate human language.

[0516] A "generative AI model" refers to a model that uses artificial intelligence to automatically generate questions and information.

[0517] "Follow-up questions" are additional questions generated based on the answers to the initial or previous questions, and their role is to elicit more detailed information from the user.

[0518] "User" refers to an individual who operates the survey system and provides answers to the questions.

[0519] A "data warehouse" is a system that centrally stores and manages large amounts of collected data for subsequent analysis.

[0520] "Insight" refers to a deep understanding of users' needs and emotions obtained through data analysis.

[0521] A "report" is a document that summarizes the results of an analysis and serves as a means of communicating the insights gained to relevant parties.

[0522] "Machine learning technology" is a type of technology that uses learning algorithms that allow computers to gain experience based on data and automatically improve their performance.

[0523] This system operates around a server that functions as an information processing device. The server utilizes advanced generative AI models to automatically generate dynamic questions based on user responses. Specifically, when a user starts a survey, the server identifies the user and creates initial questions using the generative AI model. These questions are then provided to the user via a terminal.

[0524] The user answers questions presented on the device, and the device sends these answers to the server in real time. The server analyzes the received answers using natural language processing technology. In doing so, it understands the meaning and emotional tone of the answers and generates more detailed and accurate follow-up questions.

[0525] For example, market research can use prompts such as "Please tell us your thoughts on this product" to collect specific feedback from users. In response to this feedback, the server can generate follow-up questions such as "What features do you particularly like?" to obtain even more valuable information.

[0526] The collected data is stored in a server-based data warehouse and analyzed using machine learning techniques. This provides deep insights into user needs and preferences, and reports based on this analysis are automatically generated. This system enables the collection and analysis of high-quality data, providing advanced information processing technology to support business decision-making.

[0527] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0528] Step 1:

[0529] When the server receives a request to start a survey, it identifies the sender. It receives user ID and session data as input, and as output, it generates initial questions using a generative AI model based on this information and sends them to the terminal. Specifically, the server generates questions such as "Please tell us about your area of ​​residence" based on the user's location.

[0530] Step 2:

[0531] The user enters their answers to the initial questions displayed on the terminal. The terminal formats this input data and sends the answer data to the server in real time as output. Specifically, the terminal sends the user's answer "Tokyo" to the server as a data packet.

[0532] Step 3:

[0533] The server receives responses from the terminal as input and analyzes them using natural language processing techniques. It evaluates the meaning and emotional tone of the data and identifies the interpreted intentions and emotions as output. Specifically, from the input "Tokyo," the server concludes that the user lives in a Japanese city.

[0534] Step 4:

[0535] Based on the analysis results, the server uses a generative AI model to generate follow-up questions. Using the analyzed intentions and emotions as input, it creates appropriate follow-up questions as output and sends them to the user via the terminal. For example, the server generates the follow-up question, "What is your favorite place in Tokyo?"

[0536] Step 5:

[0537] The user answers the follow-up questions again. The terminal receives the user's answers as input and sends them back to the server as output. The terminal then sends a specific answer such as "Ueno Park".

[0538] Step 6:

[0539] The server stores the response data and analyzes it again using natural language processing techniques. It receives the user's overall responses to multiple questions as input and outputs detailed insights into user needs and emotions. Specifically, the server extracts the insight that "users living in Tokyo prefer places with lots of nature."

[0540] Step 7:

[0541] The server compiles the analysis results into a report and provides it to relevant parties in digital format. It uses the analyzed data as input and generates and sends reports in PDF or email format as output. Specifically, the server creates a report including the insight that "women in their 20s in Tokyo prefer nature" and sends it to the relevant departments.

[0542] (Application Example 1)

[0543] 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."

[0544] In modern online sales, efficient and effective feedback collection is essential to improve user satisfaction after purchase and to facilitate product improvement. However, traditional surveys often present uniform questions, failing to fully grasp user intentions and emotions, and potentially missing valuable insights. Furthermore, the standardization of follow-up questions makes it difficult to elicit opinions based on specific user experiences. Therefore, there is a need for technology that maximizes user experience and collects high-quality data that contributes to product improvement.

[0545] 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.

[0546] In this invention, the server includes means for displaying initial questions generated by an information processing device, means for analyzing the user's answers to the initial questions, means for dynamically generating follow-up questions based on the analysis results, and means for collecting feedback on the user's post-purchase experience and outputting it as information that contributes to product improvement. This enables dynamic question development tailored to the user's individual emotions and intentions, making it possible to obtain highly accurate insights that contribute to product improvement.

[0547] An "information processing device" is a device used for collecting, analyzing, storing, and outputting data, and includes servers and computer systems.

[0548] An "initial question" is a question presented to a user at the beginning of a survey or feedback collection, forming the basis for the survey.

[0549] A "follow-up question" is an additional question that is generated after analyzing the user's response to the initial question and is presented to the user to obtain more detailed information.

[0550] "User emotional tone" refers to the nuances and atmosphere of emotions that can be gleaned from a user's responses and actions, and is an element used to personalize questions and results.

[0551] "Data storage" refers to a system or medium that systematically stores collected data and maintains it in a format that can be used for later analysis and report creation.

[0552] "Insight" refers to a deep understanding and perspective on user behavior and attitudes derived from collected and analyzed data.

[0553] A "report" is a document that organizes analyzed data and insights and provides them to stakeholders, and can be produced digitally or on paper.

[0554] "Post-purchase experience" refers to the user's impressions and opinions gained while actually using a product after purchase, and forms the basis of feedback.

[0555] To implement this invention, a server acting as an information processing device plays a central role. The server uses a generative AI model to create initial questions to present to the user. These questions are displayed on the user's terminal and form the basis for surveys and feedback.

[0556] When a user answers an initial question, that input is sent to the server in real time. The server uses natural language processing technology to analyze the user's response and extract its meaning and emotional tone. Based on this analysis, the server uses a generative AI model to dynamically generate follow-up questions. These follow-up questions change based on the user's answers, enabling the collection of more detailed information.

[0557] The data collected through these question-and-answer exchanges is stored in data storage. The server periodically analyzes this data to extract insights into user needs. The extracted insights are generated as reports to help improve products and are provided to stakeholders.

[0558] As a concrete example, consider a scenario where a user provides feedback on a product purchased from an online shopping site. If the initial question is "Are you satisfied with the product?" and the user responds "Yes, I particularly like the color," the server will generate a follow-up question such as "What aspects of the color did you particularly like?" This allows for question development based on the user's specific experience.

[0559] An example of a prompt is, "Based on the user's response, generate the following follow-up question. Response: I like the color." By inputting this prompt into the AI ​​model, follow-up questions tailored to the user's post-purchase experience can be effectively generated.

[0560] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0561] Step 1:

[0562] The server generates initial questions using a generative AI model. It uses the survey's purpose and user attribute data as input and sends the generated questions to the terminal. The output is the initial questions presented to the user. This process ensures that the user is shown appropriate questions tailored to their target audience.

[0563] Step 2:

[0564] The user enters their answers to initial questions displayed on the device. The device then sends this input data to the server. The input is the user's answer, and the output is the data transferred to the server. This process ensures that the server receives the user's answers, including their intentions and emotions.

[0565] Step 3:

[0566] The server analyzes the received user responses using natural language processing techniques. The input is user response data, and through semantic analysis and emotional tone extraction, the server outputs the user's intentions and emotions. The analysis results serve as foundational information for generating the next question. This process allows for a deeper understanding of the user's thoughts.

[0567] Step 4:

[0568] The server dynamically generates follow-up questions using an AI model based on the analysis results. The analysis results are used as input, and the output is the follow-up questions sent to the terminal. This process generates questions that appropriately provide detailed information based on the user's answers.

[0569] Step 5:

[0570] The user answers follow-up questions and resends the results to the server via the terminal. The input is the user's re-answer, and the output is the response data resent to the server. This process allows for the collection of further user feedback.

[0571] Step 6:

[0572] The server stores the collected user response data in data storage and performs periodic analysis. The input is the stored data, and the output is insights into user needs. This process provides information that is useful for long-term customer understanding and product improvement.

[0573] Step 7:

[0574] The server generates a report based on the insights gained and provides it to the relevant parties. The input is analytical data, and the output is a digital report. This process facilitates the sharing of information that can be used for marketing and product development strategies.

[0575] 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.

[0576] This invention provides an information processing system incorporating an emotion engine to analyze the user's emotional tone and gain in-depth insights through questionnaires. This system operates with a server at its core, coordinating with terminals and the emotion engine.

[0577] First, at the start of the survey, the server uses a generation AI to generate initial questions for the user. These questions are designed to elicit basic information relevant to the survey's purpose. The initial questions are displayed to the user via their device, and the user answers them. The device then sends the user's responses to the server in real time.

[0578] The server is equipped with an emotion engine that analyzes user responses, evaluating not only the content of the response but also the emotional tone. This evaluation identifies the emotions and intentions contained in the user's response, which helps in generating subsequent follow-up questions. Specifically, if the user shows positive emotions, it generates questions that delve deeper into those positive aspects, and if negative emotions are detected, it generates questions that explore the points of dissatisfaction the user is experiencing.

[0579] Data where emotional tone is recognized by the emotion engine is stored in the database just like regular response data. The server later analyzes this collected data in detail to gain insights into users' emotional tendencies. These insights are then compiled into reports useful for marketing and product development and provided to stakeholders.

[0580] For example, when surveying user feedback on a new product, this system can be used to reveal through sentiment analysis that certain users have a strong sense of satisfaction with the new features. At the same time, points of dissatisfaction with the features are also detected, allowing the development team to obtain specific feedback that can be used for improvement. In this way, the system of the present invention can respond to user needs more accurately than conventional survey methods.

[0581] The following describes the processing flow.

[0582] Step 1:

[0583] The server detects the start of the survey and generates initial questions using a generation AI. These questions collect basic information relevant to the survey's purpose and are presented to the user via the device.

[0584] Step 2:

[0585] The terminal displays the initial question received from the server to the user. The user reviews the displayed question and enters their answer.

[0586] Step 3:

[0587] The user enters their answers to an initial question, and the device sends this answer data to the server in real time.

[0588] Step 4:

[0589] The server uses an emotion engine to analyze the user's responses. It not only analyzes the content of the responses but also evaluates the emotional tone within the text to determine whether the response is positive, negative, neutral, or otherwise positive.

[0590] Step 5:

[0591] Based on the analysis results, the server generates follow-up questions. It dynamically constructs questions tailored to the user's response, taking into account emotional tone. For example, if the emotion is positive, it generates questions about related details.

[0592] Step 6:

[0593] The server sends the generated follow-up questions to the terminal. The terminal displays the new questions to the user and prompts them for the next answer.

[0594] Step 7:

[0595] The user continues to answer follow-up questions. The device sends the answers to the server, and this answering process is repeated until a predetermined condition or amount of data to be collected is reached.

[0596] Step 8:

[0597] The server stores all response data, along with corresponding sentiment data, in a database. This data forms the basis for subsequent analysis.

[0598] Step 9:

[0599] The server analyzes user needs and emotional trends based on accumulated data. Based on this analysis, it generates detailed reports to support marketing and product development decision-making.

[0600] Step 10:

[0601] The server provides the generated reports to stakeholders in digital format. The reports are customized to their specific purposes and designed to maximize user feedback.

[0602] (Example 2)

[0603] 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."

[0604] Traditional survey systems have difficulty capturing users' emotions and failing to fully understand their true needs. Furthermore, the fixed nature of follow-up questions makes it difficult to respond to individual user responses, resulting in reduced accuracy in data collection and analysis.

[0605] 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.

[0606] In this invention, the server includes means for presenting an initial question created by an information processing means, means for receiving and analyzing the user's response, and means for dynamically creating follow-up questions based on the analysis results. This makes it possible to present questions tailored to each user and to obtain deeper emotional insights based on them.

[0607] "Information processing means" refers to devices and software for inputting, analyzing, managing, and outputting information.

[0608] An "initial question" is a basic question presented to the user at the start of a survey, intended to collect initial information.

[0609] "Users" refer to individuals or groups who respond to the survey and are subject to evaluation by the system.

[0610] "Response" refers to the answer or reply that a user provides in response to a question presented to them.

[0611] "Follow-up questions" are additional questions generated based on the response to the initial question, and are intended to explore the user's emotions and intentions in more depth.

[0612] A "data storage device" refers to a physical or virtual recording medium used to store collected information.

[0613] "Emotional analysis" refers to the process of evaluating the emotional aspects contained in a user's response and analyzing their tone and intent.

[0614] A "report" refers to a document that organizes collected data and analysis results and is provided in visual or written form.

[0615] This invention provides a method for analyzing a user's emotional tone using an information processing system that integrates an emotion analysis engine, and for obtaining deeper insights through questionnaires. Specific embodiments for carrying out this invention are described below.

[0616] The server uses a generative AI model to create initial questions for users. This process utilizes past user data and information relevant to the survey's objectives. The generated questions form the foundation of the survey and are intended for initial information gathering. Specifically, the server generates questions such as, "What do you think of the new product?" These questions are designed to understand user opinions.

[0617] The terminal displays an initial question sent from the server to the user. The user responds, and the terminal sends the answer to the server in real time. At the same time, the response time and device information are also sent.

[0618] The sentiment analysis engine installed on the server analyzes the received response. The sentiment analysis engine uses language processing technology to analyze and evaluate the user's emotional tone from word choice and context. For example, if a user responds with "very satisfied," the sentiment analysis engine analyzes this as a positive emotion.

[0619] Based on the analysis results, the server generates follow-up questions. For positive responses, the server creates questions that delve deeper into the reasons, and for negative responses, it creates questions that explore the causes. For example, a follow-up question such as "In what ways are you satisfied with the new product?" is automatically generated.

[0620] Data containing users' emotional tones is stored in data storage devices, just like regular response data. The server analyzes the accumulated data to extract insights into users' emotional tendencies and needs. These insights are then provided as reports to aid in decision-making within relevant departments.

[0621] An example of a prompt message would be, "Please tell us how satisfied you are with the features of the new product. If you have any specific anecdotes, please share them." In this way, it is possible to gain a deep understanding of user emotions and needs throughout the entire system, which can contribute to improving products and services.

[0622] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0623] Step 1:

[0624] The server uses a generative AI model to generate initial questions according to the purpose of the survey. The input includes pre-configured survey objectives and target audience profiles. Based on this information, the generative AI model generates text and creates specific questions. The output is the initial questions to be presented to the user.

[0625] Specifically, the server retrieves past survey data from the database and creates the question, "What do you think about the new product?"

[0626] Step 2:

[0627] The terminal displays an initial question sent from the server to the user. The input is the initial question data from the server. By presenting this question to the user, the terminal prepares to receive the user's answer. The output is the question displayed to the user.

[0628] Specifically, a pop-up appears on the device, presenting the user with a question such as, "What do you think of the new product?"

[0629] Step 3:

[0630] The user enters their answers to questions displayed on the device. The input is text data containing the user's opinions and feelings. The user's answers are temporarily held on the device at this stage because they are sent to the server. The output is the user's response data.

[0631] Specifically, the user enters "Very satisfied" as their response, and the device temporarily records that response.

[0632] Step 4:

[0633] The terminal sends the user's responses to the server in real time. The input is the user response data obtained in step 3. The data is encrypted and sent to the server using secure communication. The output is the user's response data that reaches the server.

[0634] Specifically, the device encrypts the response "very satisfied" and sends it to the server.

[0635] Step 5:

[0636] The server analyzes user responses using an emotion analysis engine. The input is user response data sent from the terminal. Here, natural language processing techniques are used to evaluate the emotional tone from the responses. The output is data indicating the user's emotional tone.

[0637] Specifically, the server extracts the keyword "satisfied" and evaluates it as a positive emotion.

[0638] Step 6:

[0639] The server generates follow-up questions based on the analyzed sentiment tone data. The input is the user's sentiment tone information based on the sentiment analysis results. A generative AI model is used to create individually tailored follow-up questions. The output is the newly generated follow-up questions.

[0640] As a concrete action, it generates specific follow-up questions such as, "In what ways are you satisfied with the new product?"

[0641] Step 7:

[0642] The server presents the follow-up question to the user again via the terminal and waits for the user's response. The input is the generated follow-up question. The output is the new question presented to the user.

[0643] Specifically, a pop-up will reappear on the device, asking the question, "What aspects of the new product do you find appealing?"

[0644] Step 8:

[0645] The server stores all collected data in a data storage device, preparing it for later analysis. Inputs include user response data and sentiment tone data. Outputs are the information stored in the database.

[0646] In terms of specific actions, the server evaluates the accumulated data and prepares to analyze user opinions and emotional tendencies.

[0647] (Application Example 2)

[0648] 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."

[0649] Conventional user feedback collection systems have difficulty adequately analyzing users' emotions and intentions, and the feedback they provide has often remained superficial. As a result, companies may miss important insights for improving their products and services. This invention aims to solve these problems by analyzing users' emotional tones and gaining deeper insights.

[0650] 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.

[0651] In this invention, the server includes means for displaying basic questions generated by information processing means, means for analyzing the user's response to the basic questions, and means for generating supplementary questions based on the analysis results and emotional tone, and adjusting them based on the emotional evaluation. This makes it possible to collect and analyze detailed feedback on the user's emotions after purchase.

[0652] "Information processing means" refers to a device or system that has the function of receiving data, analyzing it, and generating and displaying necessary information.

[0653] "Basic questions" are the initial questions posed to elicit fundamental information and opinions from users.

[0654] "User responses" refer to the answers that users provide to basic questions and supplementary questions.

[0655] "Analysis results" refer to the results of an analysis obtained by an information processing device based on the user's response.

[0656] "Supplementary questions" are additional questions generated based on the analysis results and emotional tone.

[0657] "Emotional tone" refers to the emotional tendencies and nuances that can be gleaned from a user's response.

[0658] "Emotional assessment" refers to the analysis of a user's emotional tone and the identification and classification of the resulting emotions.

[0659] "Adjustment" means changing or modifying something to an appropriate state according to the circumstances and conditions.

[0660] "Feedback" refers to the collection of opinions and impressions from users.

[0661] This invention constructs an information processing system for collecting and analyzing user feedback. A specific embodiment is described below.

[0662] This system includes a server, terminals, and an emotion analysis engine. The terminals function as devices connected to users, such as smartphones and computers, and have programs installed for information processing. The server functions as a central device for data analysis and storage. The emotion analysis engine can utilize emotion recognition software such as the Microsoft Azure Emotion API. For generative AI, OpenAI GPT models and others can be applied.

[0663] First, the device displays basic questions to the user. When the user responds to these basic questions, that information is sent to the server in real time. The server analyzes the received response data using an emotion analysis engine to evaluate the user's emotional tone. Then, based on the analysis results, it uses a generative AI to generate follow-up questions.

[0664] The generated follow-up questions are presented to the user immediately, and the responses are sent back to the server. The server stores the collected data on a recording medium and performs data analysis later. This process provides detailed insights into the user's requests and feelings, which are then generated as a report.

[0665] For example, this system can be useful when collecting feedback on a user's experience and performance after they purchase a new electronic device. If the user responds that they are "very satisfied," the generating AI can create follow-up questions such as, "Which features are you particularly satisfied with?"

[0666] An example of a prompt is: "Understand the emotional tone after product purchase and generate follow-up questions based on positive or negative feedback." This prompt allows the generating AI to automatically generate appropriate follow-up questions.

[0667] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0668] Step 1:

[0669] The terminal displays a basic question to the user. The input is the basic question sent from the server to the terminal. The terminal displays this question on the screen and waits for a response from the user. The output is the user's response in text format.

[0670] Step 2:

[0671] The user responds to a basic question. The input is the user's answer to the basic question. The user enters the answer through the terminal's input interface. The output is the user's response data, which is sent to the server in the next step.

[0672] Step 3:

[0673] The terminal sends user responses to the server in real time. The input is the response data entered by the user on the terminal. This data is securely transmitted to the server. The output is the user response data stored on the server.

[0674] Step 4:

[0675] The server analyzes the received response data using an emotion analysis engine. The input is the user's response data sent from the terminal. The server uses an emotion analysis engine (e.g., Microsoft Azure Emotion API) to evaluate the emotional tone underlying the response. The output is the result of the emotional tone analysis.

[0676] Step 5:

[0677] The server generates supplementary questions using a generative AI model based on the analysis results of the emotional tone. The input is the analysis results of the emotional tone. The server uses generative AI (e.g., OpenAI GPT model) and prompt sentences to generate appropriate supplementary questions. The output is the generated supplementary questions.

[0678] Step 6:

[0679] The server sends the generated supplementary questions to the terminal. The input is the generated supplementary questions. The server sends the data to the terminal in the appropriate format. The output is the supplementary questions displayed on the terminal.

[0680] Step 7:

[0681] The terminal presents the user with a generated supplementary question. The input is the supplementary question received from the server. The terminal displays this question on the screen and waits for a response from the user. The output is the user's response data.

[0682] Step 8:

[0683] The user responds to supplementary questions, and the terminal resends those answers to the server. The input is the user's responses to the supplementary questions. The data is securely transmitted to the server. The output is the user's re-responses, stored in the database.

[0684] Step 9:

[0685] The server performs a detailed analysis of user needs and emotions using accumulated response data. The input is all user response data stored in the database. The server extracts precise insights using data analysis tools. The output is the insights regarding user needs and emotions.

[0686] Step 10:

[0687] The server outputs a report based on the insights obtained. The input is the insights obtained through analysis. The server compiles the results in a report format and provides it to the necessary stakeholders. The output is a report useful for marketing and product development from various perspectives.

[0688] 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.

[0689] 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.

[0690] 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.

[0691] [Fourth Embodiment]

[0692] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0693] 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.

[0694] 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).

[0695] 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.

[0696] 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.

[0697] 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).

[0698] 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.

[0699] 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.

[0700] 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.

[0701] 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.

[0702] 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.

[0703] 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.

[0704] 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".

[0705] In implementing this invention, a server functioning as an information processing device plays a central role. First, the server identifies the user who initiated the survey and generates initial questions for that user. The initial questions are automatically created by a generation AI model according to the purpose and target audience of the survey and are presented to the user via a terminal.

[0706] The user enters answers to questions displayed on the interface. The terminal sends this user input to the server in real time. The server launches a program to analyze the received answers and identifies the user's possible intentions and emotions based on the analysis results. This analysis includes utilizing natural language processing techniques to grasp the meaning and tone of the answers.

[0707] Next, the server generates follow-up questions based on the analysis results to extract more detailed information. These follow-up questions are also dynamically generated by the generation AI model, allowing for flexible adaptation to the user's existing answers. The generated questions are then presented to the user again via the terminal, and the user continues to answer them.

[0708] The response data collected in this repeated manner is stored in a database on the server. This data is further analyzed to gain insights into user needs and emotions. The insights gained are automatically compiled into an analysis report by the server and provided to stakeholders in digital format.

[0709] For example, in market research, this system can be used to discover that a specific group of users is giving positive feedback on a new product. Follow-up questions can then be used to investigate specific functions or features in more detail, providing important insights for product development. Thus, this invention enables flexible and detailed questionnaire surveys, achieving the collection of high-quality data that cannot be obtained through conventional methods.

[0710] The following describes the processing flow.

[0711] Step 1:

[0712] The server detects the start of a survey and generates initial questions to present to the user. Using a generation AI, it creates questions for basic information gathering and sends them to the device.

[0713] Step 2:

[0714] The terminal displays the initial questions received from the server to the user on the screen. The interface is adjusted to make it easier for the user to answer the questions.

[0715] Step 3:

[0716] The user enters their answers to the presented questions. The device sends the entered answers to the server in real time.

[0717] Step 4:

[0718] The server analyzes the user's responses. Using natural language processing techniques, it analyzes the content and emotional tone of the responses to estimate the respondent's intentions and needs.

[0719] Step 5:

[0720] The server generates follow-up questions based on the analysis results. It utilizes a generation AI to create dynamic questions that further explore the user's responses.

[0721] Step 6:

[0722] The server sends the generated follow-up questions to the terminal. The terminal displays them on the user's screen.

[0723] Step 7:

[0724] The user continues to answer follow-up questions. The device sends the user's responses back to the server, and this process is repeated until sufficient data has been collected.

[0725] Step 8:

[0726] The server stores all user response data in a database. This stored data is used for subsequent analysis.

[0727] Step 9:

[0728] The server conducts detailed analysis based on accumulated data to gain insights into user needs and emotions. From the analysis results, it generates reports useful for marketing and product development.

[0729] Step 10:

[0730] The server provides the generated reports to the relevant parties in digital format. This information is used according to the purpose of the investigation.

[0731] (Example 1)

[0732] 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".

[0733] Traditional survey methods have faced challenges in flexibly and quickly understanding respondents' intentions and emotions while generating questions, and in utilizing the collected data to gain highly accurate insights. Therefore, there is a need to provide a system that can automatically generate a sequence of questions that accurately reflect respondents' needs, and that enables the collection and analysis of high-quality data.

[0734] 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.

[0735] In this invention, the server includes means for identifying the caller using an information processing device and displaying an initial question that is generated; means for receiving the user's response to the initial question and analyzing it using natural language processing technology; and means for dynamically generating and adjusting follow-up questions using a generation AI model based on the analysis results. This makes it possible to more accurately grasp the user's intentions and emotions and flexibly generate questions accordingly, thereby enabling highly accurate data collection and the acquisition of insights.

[0736] An "information processing device" refers to a computer system that has the functions of inputting, processing, and outputting data.

[0737] "Initiator" refers to the user who starts a survey or questionnaire and enters their responses.

[0738] An "initial question" is the first question provided at the start of a survey, and it forms the basis for generating subsequent questions.

[0739] "Natural language processing technology" is a type of technology that enables computers to understand, interpret, and manipulate human language.

[0740] A "generative AI model" refers to a model that uses artificial intelligence to automatically generate questions and information.

[0741] "Follow-up questions" are additional questions generated based on the answers to the initial or previous questions, and their role is to elicit more detailed information from the user.

[0742] "User" refers to an individual who operates the survey system and provides answers to the questions.

[0743] A "data warehouse" is a system that centrally stores and manages large amounts of collected data for subsequent analysis.

[0744] "Insight" refers to a deep understanding of users' needs and emotions obtained through data analysis.

[0745] A "report" is a document that summarizes the results of an analysis and serves as a means of communicating the insights gained to relevant parties.

[0746] "Machine learning technology" is a type of technology that uses learning algorithms that allow computers to gain experience based on data and automatically improve their performance.

[0747] This system operates around a server that functions as an information processing device. The server utilizes advanced generative AI models to automatically generate dynamic questions based on user responses. Specifically, when a user starts a survey, the server identifies the user and creates initial questions using the generative AI model. These questions are then provided to the user via a terminal.

[0748] The user answers questions presented on the device, and the device sends these answers to the server in real time. The server analyzes the received answers using natural language processing technology. In doing so, it understands the meaning and emotional tone of the answers and generates more detailed and accurate follow-up questions.

[0749] For example, market research can use prompts such as "Please tell us your thoughts on this product" to collect specific feedback from users. In response to this feedback, the server can generate follow-up questions such as "What features do you particularly like?" to obtain even more valuable information.

[0750] The collected data is stored in a server-based data warehouse and analyzed using machine learning techniques. This provides deep insights into user needs and preferences, and reports based on this analysis are automatically generated. This system enables the collection and analysis of high-quality data, providing advanced information processing technology to support business decision-making.

[0751] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0752] Step 1:

[0753] When the server receives a request to start a survey, it identifies the sender. It receives user ID and session data as input, and as output, it generates initial questions using a generative AI model based on this information and sends them to the terminal. Specifically, the server generates questions such as "Please tell us about your area of ​​residence" based on the user's location.

[0754] Step 2:

[0755] The user enters their answers to the initial questions displayed on the terminal. The terminal formats this input data and sends the answer data to the server in real time as output. Specifically, the terminal sends the user's answer "Tokyo" to the server as a data packet.

[0756] Step 3:

[0757] The server receives responses from the terminal as input and analyzes them using natural language processing techniques. It evaluates the meaning and emotional tone of the data and identifies the interpreted intentions and emotions as output. Specifically, from the input "Tokyo," the server concludes that the user lives in a Japanese city.

[0758] Step 4:

[0759] Based on the analysis results, the server uses a generative AI model to generate follow-up questions. Using the analyzed intentions and emotions as input, it creates appropriate follow-up questions as output and sends them to the user via the terminal. For example, the server generates the follow-up question, "What is your favorite place in Tokyo?"

[0760] Step 5:

[0761] The user answers the follow-up questions again. The terminal receives the user's answers as input and sends them back to the server as output. The terminal then sends a specific answer such as "Ueno Park".

[0762] Step 6:

[0763] The server stores the response data and analyzes it again using natural language processing techniques. It receives the user's overall responses to multiple questions as input and outputs detailed insights into user needs and emotions. Specifically, the server extracts the insight that "users living in Tokyo prefer places with lots of nature."

[0764] Step 7:

[0765] The server compiles the analysis results into a report and provides it to relevant parties in digital format. It uses the analyzed data as input and generates and sends reports in PDF or email format as output. Specifically, the server creates a report including the insight that "women in their 20s in Tokyo prefer nature" and sends it to the relevant departments.

[0766] (Application Example 1)

[0767] 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".

[0768] In modern online sales, efficient and effective feedback collection is essential to improve user satisfaction after purchase and to facilitate product improvement. However, traditional surveys often present uniform questions, failing to fully grasp user intentions and emotions, and potentially missing valuable insights. Furthermore, the standardization of follow-up questions makes it difficult to elicit opinions based on specific user experiences. Therefore, there is a need for technology that maximizes user experience and collects high-quality data that contributes to product improvement.

[0769] 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.

[0770] In this invention, the server includes means for displaying initial questions generated by an information processing device, means for analyzing the user's answers to the initial questions, means for dynamically generating follow-up questions based on the analysis results, and means for collecting feedback on the user's post-purchase experience and outputting it as information that contributes to product improvement. This enables dynamic question development tailored to the user's individual emotions and intentions, making it possible to obtain highly accurate insights that contribute to product improvement.

[0771] An "information processing device" is a device used for collecting, analyzing, storing, and outputting data, and includes servers and computer systems.

[0772] An "initial question" is a question presented to a user at the beginning of a survey or feedback collection, forming the basis for the survey.

[0773] A "follow-up question" is an additional question that is generated after analyzing the user's response to the initial question and is presented to the user to obtain more detailed information.

[0774] "User emotional tone" refers to the nuances and atmosphere of emotions that can be gleaned from a user's responses and actions, and is an element used to personalize questions and results.

[0775] "Data storage" refers to a system or medium that systematically stores collected data and maintains it in a format that can be used for later analysis and report creation.

[0776] "Insight" refers to a deep understanding and perspective on user behavior and attitudes derived from collected and analyzed data.

[0777] A "report" is a document that organizes analyzed data and insights and provides them to stakeholders, and can be produced digitally or on paper.

[0778] "Post-purchase experience" refers to the user's impressions and opinions gained while actually using a product after purchase, and forms the basis of feedback.

[0779] To implement this invention, a server acting as an information processing device plays a central role. The server uses a generative AI model to create initial questions to present to the user. These questions are displayed on the user's terminal and form the basis for surveys and feedback.

[0780] When a user answers an initial question, that input is sent to the server in real time. The server uses natural language processing technology to analyze the user's response and extract its meaning and emotional tone. Based on this analysis, the server uses a generative AI model to dynamically generate follow-up questions. These follow-up questions change based on the user's answers, enabling the collection of more detailed information.

[0781] The data collected through these question-and-answer exchanges is stored in data storage. The server periodically analyzes this data to extract insights into user needs. The extracted insights are generated as reports to help improve products and are provided to stakeholders.

[0782] As a concrete example, consider a scenario where a user provides feedback on a product purchased from an online shopping site. If the initial question is "Are you satisfied with the product?" and the user responds "Yes, I particularly like the color," the server will generate a follow-up question such as "What aspects of the color did you particularly like?" This allows for question development based on the user's specific experience.

[0783] An example of a prompt is, "Based on the user's response, generate the following follow-up question. Response: I like the color." By inputting this prompt into the AI ​​model, follow-up questions tailored to the user's post-purchase experience can be effectively generated.

[0784] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0785] Step 1:

[0786] The server generates initial questions using a generative AI model. It uses the survey's purpose and user attribute data as input and sends the generated questions to the terminal. The output is the initial questions presented to the user. This process ensures that the user is shown appropriate questions tailored to their target audience.

[0787] Step 2:

[0788] The user enters their answers to initial questions displayed on the device. The device then sends this input data to the server. The input is the user's answer, and the output is the data transferred to the server. This process ensures that the server receives the user's answers, including their intentions and emotions.

[0789] Step 3:

[0790] The server analyzes the received user responses using natural language processing techniques. The input is user response data, and through semantic analysis and emotional tone extraction, the server outputs the user's intentions and emotions. The analysis results serve as foundational information for generating the next question. This process allows for a deeper understanding of the user's thoughts.

[0791] Step 4:

[0792] The server dynamically generates follow-up questions using an AI model based on the analysis results. The analysis results are used as input, and the output is the follow-up questions sent to the terminal. This process generates questions that appropriately provide detailed information based on the user's answers.

[0793] Step 5:

[0794] The user answers follow-up questions and resends the results to the server via the terminal. The input is the user's re-answer, and the output is the response data resent to the server. This process allows for the collection of further user feedback.

[0795] Step 6:

[0796] The server stores the collected user response data in data storage and performs periodic analysis. The input is the stored data, and the output is insights into user needs. This process provides information that is useful for long-term customer understanding and product improvement.

[0797] Step 7:

[0798] The server generates a report based on the insights gained and provides it to the relevant parties. The input is analytical data, and the output is a digital report. This process facilitates the sharing of information that can be used for marketing and product development strategies.

[0799] 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.

[0800] This invention provides an information processing system incorporating an emotion engine to analyze the user's emotional tone and gain in-depth insights through questionnaires. This system operates with a server at its core, coordinating with terminals and the emotion engine.

[0801] First, at the start of the survey, the server uses a generation AI to generate initial questions for the user. These questions are designed to elicit basic information relevant to the survey's purpose. The initial questions are displayed to the user via their device, and the user answers them. The device then sends the user's responses to the server in real time.

[0802] The server is equipped with an emotion engine that analyzes user responses, evaluating not only the content of the response but also the emotional tone. This evaluation identifies the emotions and intentions contained in the user's response, which helps in generating subsequent follow-up questions. Specifically, if the user shows positive emotions, it generates questions that delve deeper into those positive aspects, and if negative emotions are detected, it generates questions that explore the points of dissatisfaction the user is experiencing.

[0803] Data where emotional tone is recognized by the emotion engine is stored in the database just like regular response data. The server later analyzes this collected data in detail to gain insights into users' emotional tendencies. These insights are then compiled into reports useful for marketing and product development and provided to stakeholders.

[0804] For example, when surveying user feedback on a new product, this system can be used to reveal through sentiment analysis that certain users have a strong sense of satisfaction with the new features. At the same time, points of dissatisfaction with the features are also detected, allowing the development team to obtain specific feedback that can be used for improvement. In this way, the system of the present invention can respond to user needs more accurately than conventional survey methods.

[0805] The following describes the processing flow.

[0806] Step 1:

[0807] The server detects the start of the survey and generates initial questions using a generation AI. These questions collect basic information relevant to the survey's purpose and are presented to the user via the device.

[0808] Step 2:

[0809] The terminal displays the initial question received from the server to the user. The user reviews the displayed question and enters their answer.

[0810] Step 3:

[0811] The user enters their answers to an initial question, and the device sends this answer data to the server in real time.

[0812] Step 4:

[0813] The server uses an emotion engine to analyze the user's responses. It not only analyzes the content of the responses but also evaluates the emotional tone within the text to determine whether the response is positive, negative, neutral, or otherwise positive.

[0814] Step 5:

[0815] Based on the analysis results, the server generates follow-up questions. It dynamically constructs questions tailored to the user's response, taking into account emotional tone. For example, if the emotion is positive, it generates questions about related details.

[0816] Step 6:

[0817] The server sends the generated follow-up questions to the terminal. The terminal displays the new questions to the user and prompts them for the next answer.

[0818] Step 7:

[0819] The user continues to answer follow-up questions. The device sends the answers to the server, and this answering process is repeated until a predetermined condition or amount of data to be collected is reached.

[0820] Step 8:

[0821] The server stores all response data, along with corresponding sentiment data, in a database. This data forms the basis for subsequent analysis.

[0822] Step 9:

[0823] The server analyzes user needs and emotional trends based on accumulated data. Based on this analysis, it generates detailed reports to support marketing and product development decision-making.

[0824] Step 10:

[0825] The server provides the generated reports to stakeholders in digital format. The reports are customized to their specific purposes and designed to maximize user feedback.

[0826] (Example 2)

[0827] 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".

[0828] Traditional survey systems have difficulty capturing users' emotions and failing to fully understand their true needs. Furthermore, the fixed nature of follow-up questions makes it difficult to respond to individual user responses, resulting in reduced accuracy in data collection and analysis.

[0829] 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.

[0830] In this invention, the server includes means for presenting an initial question created by an information processing means, means for receiving and analyzing the user's response, and means for dynamically creating follow-up questions based on the analysis results. This makes it possible to present questions tailored to each user and to obtain deeper emotional insights based on them.

[0831] "Information processing means" refers to devices and software for inputting, analyzing, managing, and outputting information.

[0832] An "initial question" is a basic question presented to the user at the start of a survey, intended to collect initial information.

[0833] "Users" refer to individuals or groups who respond to the survey and are subject to evaluation by the system.

[0834] "Response" refers to the answer or reply that a user provides in response to a question presented to them.

[0835] "Follow-up questions" are additional questions generated based on the response to the initial question, and are intended to explore the user's emotions and intentions in more depth.

[0836] A "data storage device" refers to a physical or virtual recording medium used to store collected information.

[0837] "Emotional analysis" refers to the process of evaluating the emotional aspects contained in a user's response and analyzing their tone and intent.

[0838] A "report" refers to a document that organizes collected data and analysis results and is provided in visual or written form.

[0839] This invention provides a method for analyzing a user's emotional tone using an information processing system that integrates an emotion analysis engine, and for obtaining deeper insights through questionnaires. Specific embodiments for carrying out this invention are described below.

[0840] The server uses a generative AI model to create initial questions for users. This process utilizes past user data and information relevant to the survey's objectives. The generated questions form the foundation of the survey and are intended for initial information gathering. Specifically, the server generates questions such as, "What do you think of the new product?" These questions are designed to understand user opinions.

[0841] The terminal displays an initial question sent from the server to the user. The user responds, and the terminal sends the answer to the server in real time. At the same time, the response time and device information are also sent.

[0842] The sentiment analysis engine installed on the server analyzes the received response. The sentiment analysis engine uses language processing technology to analyze and evaluate the user's emotional tone from word choice and context. For example, if a user responds with "very satisfied," the sentiment analysis engine analyzes this as a positive emotion.

[0843] Based on the analysis results, the server generates follow-up questions. For positive responses, the server creates questions that delve deeper into the reasons, and for negative responses, it creates questions that explore the causes. For example, a follow-up question such as "In what ways are you satisfied with the new product?" is automatically generated.

[0844] Data containing users' emotional tones is stored in data storage devices, just like regular response data. The server analyzes the accumulated data to extract insights into users' emotional tendencies and needs. These insights are then provided as reports to aid in decision-making within relevant departments.

[0845] An example of a prompt message would be, "Please tell us how satisfied you are with the features of the new product. If you have any specific anecdotes, please share them." In this way, it is possible to gain a deep understanding of user emotions and needs throughout the entire system, which can contribute to improving products and services.

[0846] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0847] Step 1:

[0848] The server uses a generative AI model to generate initial questions according to the purpose of the survey. The input includes pre-configured survey objectives and target audience profiles. Based on this information, the generative AI model generates text and creates specific questions. The output is the initial questions to be presented to the user.

[0849] Specifically, the server retrieves past survey data from the database and creates the question, "What do you think about the new product?"

[0850] Step 2:

[0851] The terminal displays an initial question sent from the server to the user. The input is the initial question data from the server. By presenting this question to the user, the terminal prepares to receive the user's answer. The output is the question displayed to the user.

[0852] Specifically, a pop-up appears on the device, presenting the user with a question such as, "What do you think of the new product?"

[0853] Step 3:

[0854] The user enters their answers to questions displayed on the device. The input is text data containing the user's opinions and feelings. The user's answers are temporarily held on the device at this stage because they are sent to the server. The output is the user's response data.

[0855] Specifically, the user enters "Very satisfied" as their response, and the device temporarily records that response.

[0856] Step 4:

[0857] The terminal sends the user's responses to the server in real time. The input is the user response data obtained in step 3. The data is encrypted and sent to the server using secure communication. The output is the user's response data that reaches the server.

[0858] Specifically, the device encrypts the response "very satisfied" and sends it to the server.

[0859] Step 5:

[0860] The server analyzes user responses using an emotion analysis engine. The input is user response data sent from the terminal. Here, natural language processing techniques are used to evaluate the emotional tone from the responses. The output is data indicating the user's emotional tone.

[0861] Specifically, the server extracts the keyword "satisfied" and evaluates it as a positive emotion.

[0862] Step 6:

[0863] The server generates follow-up questions based on the analyzed sentiment tone data. The input is the user's sentiment tone information based on the sentiment analysis results. A generative AI model is used to create individually tailored follow-up questions. The output is the newly generated follow-up questions.

[0864] As a concrete action, it generates specific follow-up questions such as, "In what ways are you satisfied with the new product?"

[0865] Step 7:

[0866] The server presents the follow-up question to the user again via the terminal and waits for the user's response. The input is the generated follow-up question. The output is the new question presented to the user.

[0867] Specifically, a pop-up will reappear on the device, asking the question, "What aspects of the new product do you find appealing?"

[0868] Step 8:

[0869] The server stores all collected data in a data storage device, preparing it for later analysis. Inputs include user response data and sentiment tone data. Outputs are the information stored in the database.

[0870] In terms of specific actions, the server evaluates the accumulated data and prepares to analyze user opinions and emotional tendencies.

[0871] (Application Example 2)

[0872] 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".

[0873] Conventional user feedback collection systems have difficulty adequately analyzing users' emotions and intentions, and the feedback they provide has often remained superficial. As a result, companies may miss important insights for improving their products and services. This invention aims to solve these problems by analyzing users' emotional tones and gaining deeper insights.

[0874] 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.

[0875] In this invention, the server includes means for displaying basic questions generated by information processing means, means for analyzing the user's response to the basic questions, and means for generating supplementary questions based on the analysis results and emotional tone, and adjusting them based on the emotional evaluation. This makes it possible to collect and analyze detailed feedback on the user's emotions after purchase.

[0876] "Information processing means" refers to a device or system that has the function of receiving data, analyzing it, and generating and displaying necessary information.

[0877] "Basic questions" are the initial questions posed to elicit fundamental information and opinions from users.

[0878] "User responses" refer to the answers that users provide to basic questions and supplementary questions.

[0879] "Analysis results" refer to the results of an analysis obtained by an information processing device based on the user's response.

[0880] "Supplementary questions" are additional questions generated based on the analysis results and emotional tone.

[0881] "Emotional tone" refers to the emotional tendencies and nuances that can be gleaned from a user's response.

[0882] "Emotional assessment" refers to the analysis of a user's emotional tone and the identification and classification of the resulting emotions.

[0883] "Adjustment" means changing or modifying something to an appropriate state according to the circumstances and conditions.

[0884] "Feedback" refers to the collection of opinions and impressions from users.

[0885] This invention constructs an information processing system for collecting and analyzing user feedback. A specific embodiment is described below.

[0886] This system includes a server, terminals, and an emotion analysis engine. The terminals function as devices connected to users, such as smartphones and computers, and have programs installed for information processing. The server functions as a central device for data analysis and storage. The emotion analysis engine can utilize emotion recognition software such as the Microsoft Azure Emotion API. For generative AI, OpenAI GPT models and others can be applied.

[0887] First, the device displays basic questions to the user. When the user responds to these basic questions, that information is sent to the server in real time. The server analyzes the received response data using an emotion analysis engine to evaluate the user's emotional tone. Then, based on the analysis results, it uses a generative AI to generate follow-up questions.

[0888] The generated follow-up questions are presented to the user immediately, and the responses are sent back to the server. The server stores the collected data on a recording medium and performs data analysis later. This process provides detailed insights into the user's requests and feelings, which are then generated as a report.

[0889] For example, this system can be useful when collecting feedback on a user's experience and performance after they purchase a new electronic device. If the user responds that they are "very satisfied," the generating AI can create follow-up questions such as, "Which features are you particularly satisfied with?"

[0890] An example of a prompt is: "Understand the emotional tone after product purchase and generate follow-up questions based on positive or negative feedback." This prompt allows the generating AI to automatically generate appropriate follow-up questions.

[0891] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0892] Step 1:

[0893] The terminal displays a basic question to the user. The input is the basic question sent from the server to the terminal. The terminal displays this question on the screen and waits for a response from the user. The output is the user's response in text format.

[0894] Step 2:

[0895] The user responds to a basic question. The input is the user's answer to the basic question. The user enters the answer through the terminal's input interface. The output is the user's response data, which is sent to the server in the next step.

[0896] Step 3:

[0897] The terminal sends user responses to the server in real time. The input is the response data entered by the user on the terminal. This data is securely transmitted to the server. The output is the user response data stored on the server.

[0898] Step 4:

[0899] The server analyzes the received response data using an emotion analysis engine. The input is the user's response data sent from the terminal. The server uses an emotion analysis engine (e.g., Microsoft Azure Emotion API) to evaluate the emotional tone underlying the response. The output is the result of the emotional tone analysis.

[0900] Step 5:

[0901] The server generates supplementary questions using a generative AI model based on the analysis results of the emotional tone. The input is the analysis results of the emotional tone. The server uses generative AI (e.g., OpenAI GPT model) and prompt sentences to generate appropriate supplementary questions. The output is the generated supplementary questions.

[0902] Step 6:

[0903] The server sends the generated supplementary questions to the terminal. The input is the generated supplementary questions. The server sends the data to the terminal in the appropriate format. The output is the supplementary questions displayed on the terminal.

[0904] Step 7:

[0905] The terminal presents the user with a generated supplementary question. The input is the supplementary question received from the server. The terminal displays this question on the screen and waits for a response from the user. The output is the user's response data.

[0906] Step 8:

[0907] The user responds to supplementary questions, and the terminal resends those answers to the server. The input is the user's responses to the supplementary questions. The data is securely transmitted to the server. The output is the user's re-responses, stored in the database.

[0908] Step 9:

[0909] The server performs a detailed analysis of user needs and emotions using accumulated response data. The input is all user response data stored in the database. The server extracts precise insights using data analysis tools. The output is the insights regarding user needs and emotions.

[0910] Step 10:

[0911] The server outputs a report based on the insights obtained. The input is the insights obtained through analysis. The server compiles the results in a report format and provides it to the necessary stakeholders. The output is a report useful for marketing and product development from various perspectives.

[0912] 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.

[0913] 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.

[0914] 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 robot 414.

[0915] 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.

[0916] 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.

[0917] 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.

[0918] 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.

[0919] 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.

[0920] 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."

[0921] 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.

[0922] 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.

[0923] 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.

[0924] 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.

[0925] 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.

[0926] 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.

[0927] 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.

[0928] 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.

[0929] 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.

[0930] 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.

[0931] 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.

[0932] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0933] The following is further disclosed regarding the embodiments described above.

[0934] (Claim 1)

[0935] A means for displaying an initial question generated by an information processing device,

[0936] A means for receiving and analyzing the user's response to the aforementioned initial question,

[0937] A means for dynamically generating follow-up questions based on analysis results,

[0938] A means for presenting the aforementioned follow-up questions to the user,

[0939] A means of collecting and storing user responses in a database,

[0940] A means of analyzing accumulated data and extracting insights into user needs and emotions,

[0941] A means for generating and outputting the aforementioned insights as a report,

[0942] A system that includes this.

[0943] (Claim 2)

[0944] The system according to claim 1, comprising a technique for adjusting follow-up questions to take into account the user's emotional tone when generating them.

[0945] (Claim 3)

[0946] The system according to claim 1, comprising a machine learning means that learns from data collected from users and improves the accuracy of question generation in the future.

[0947] "Example 1"

[0948] (Claim 1)

[0949] A means for identifying the caller using an information processing device and displaying the generated initial question,

[0950] A means for receiving the user's response to the aforementioned initial question and analyzing it using natural language processing technology,

[0951] A means of dynamically generating and adjusting follow-up questions using an AI model based on the analysis results,

[0952] A means of presenting the aforementioned follow-up questions to the user,

[0953] A means of collecting and storing user responses in a data warehouse,

[0954] A means of analyzing accumulated information and extracting insights into users' needs and emotions,

[0955] A means for generating and outputting the aforementioned insights as a report,

[0956] A system that includes this.

[0957] (Claim 2)

[0958] The system according to claim 1, comprising a technique for adjusting follow-up questions to take into account the user's emotional tone when generating them.

[0959] (Claim 3)

[0960] The system according to claim 1, which has machine learning technology that learns from information collected from users and improves the accuracy of question generation in the future.

[0961] "Application Example 1"

[0962] (Claim 1)

[0963] A means for displaying an initial question generated by an information processing device,

[0964] A means for receiving and analyzing the user's response to the aforementioned initial question,

[0965] A means for dynamically generating follow-up questions based on analysis results,

[0966] A means for presenting the aforementioned follow-up questions to the user,

[0967] A means of collecting user responses and storing them in data storage,

[0968] A means of analyzing accumulated data and extracting insights into user needs and emotions,

[0969] A means for generating and outputting the aforementioned insights as a report,

[0970] A means of collecting user feedback on their post-purchase experience and outputting it as information that contributes to product improvement,

[0971] A system that includes this.

[0972] (Claim 2)

[0973] The system according to claim 1, comprising a technique for adjusting follow-up questions to take into account the user's emotional tone and purchase experience when generating them.

[0974] (Claim 3)

[0975] The system according to claim 1, which has a machine learning method that learns from data collected from users and improves the accuracy of question generation in the future, and also generates insights that contribute to product improvement with high accuracy.

[0976] "Example 2 of combining an emotion engine"

[0977] (Claim 1)

[0978] A means for presenting an initial question generated by an information processing means,

[0979] A means for receiving and analyzing the user's response to the aforementioned initial question,

[0980] A means for dynamically generating follow-up questions based on the analysis results,

[0981] A means of presenting the aforementioned follow-up questions to the user,

[0982] A means for collecting user responses and storing them in a data storage device,

[0983] A means of analyzing accumulated information and extracting insights into users' needs and emotions,

[0984] A means for creating and outputting the aforementioned insights as a report,

[0985] In data collection and analysis, means for analyzing user emotions,

[0986] A system that includes this.

[0987] (Claim 2)

[0988] The system according to claim 1, comprising a technique that uses an emotion analysis engine to adjust follow-up questions considering the user's emotional tone.

[0989] (Claim 3)

[0990] The system according to claim 1, comprising a machine learning means that learns from information collected from users and improves the accuracy of future question generation.

[0991] "Application example 2 of combining emotional engines"

[0992] (Claim 1)

[0993] A means for displaying basic questions generated by an information processing means,

[0994] A means for receiving and analyzing user responses to the aforementioned basic questions,

[0995] A means for dynamically generating supplementary questions based on the analysis results,

[0996] A means of presenting the aforementioned supplementary questions to the user,

[0997] A means for collecting and storing user responses on a recording medium,

[0998] A means of analyzing accumulated data and extracting insights into user needs and emotions,

[0999] A means for generating and outputting the aforementioned insights as a report,

[1000] A means for evaluating the emotional tone of users after product purchase through emotion analysis, and for adjusting the generated supplementary questions based on the emotional evaluation,

[1001] A system that includes this.

[1002] (Claim 2)

[1003] The system according to claim 1, comprising techniques for considering the user's emotional tone and extracting detailed feedback regarding the product experience when generating follow-up questions.

[1004] (Claim 3)

[1005] The system according to claim 1, comprising machine learning means that learns from data collected from users and improves the accuracy of question generation and sentiment evaluation in the future. [Explanation of Symbols]

[1006] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for displaying an initial question generated by an information processing device, A means for receiving and analyzing the user's response to the aforementioned initial question, A means for dynamically generating follow-up questions based on analysis results, A means for presenting the aforementioned follow-up questions to the user, A means of collecting and storing user responses in a database, A means of analyzing accumulated data and extracting insights into user needs and emotions, A means for generating and outputting the aforementioned insights as a report, A system that includes this.

2. The system according to claim 1, further comprising a technique for adjusting follow-up questions to take into account the user's emotional tone when generating them.

3. The system according to claim 1, comprising a machine learning means that learns from data collected from users and improves the accuracy of question generation in the future.

Images