system

Abstract

We provide the system. [Solution] An information processing device that receives authentication information from users, A server means that receives an authentication request based on the authentication information and generates authentication data including image data and product evaluation questions, A means for transmitting the authentication data to the information processing device and receiving the response data entered by the user, A means for creating model improvement data to improve the performance of the product based on the response data, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] A large amount of feedback from humans is indispensable for improving the performance of generative AI. However, conventional methods are costly, and it is difficult to stably and evenly aggregate a large number of feedbacks. Therefore, it is required to efficiently collect feedback by utilizing the daily authentication process and contribute to the improvement of generative AI.

Means for Solving the Problems

[0005] This invention provides a system for collecting feedback by presenting authentication data, including image data and product evaluation questions, during the authentication process used by users on a daily basis. In this system, a server generates authentication data and presents it to the user via an information processing device. The response data provided by the user is aggregated by the server and used as model improvement data for the generating AI. This makes it possible to efficiently utilize daily authentication work and collect high-quality, unbiased feedback at low cost.

[0006] An "information processing device" is a device that receives authentication information from users and communicates with a server.

[0007] A "server means" is a device that receives an authentication request based on authentication information and generates and transmits authentication data including image data and product evaluation questions.

[0008] "Authentication information" refers to information that a user enters to access a specific service or system, and typically includes a user ID and password.

[0009] "Image data" refers to information in image format presented to the user during the authentication process.

[0010] A "product evaluation question" refers to a question that asks the user to evaluate the results provided by the generating AI.

[0011] "Response data" refers to data that includes the user's response to the authentication data.

[0012] "Model improvement data" refers to a dataset used to improve the performance of the generating AI, based on collected user response data. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

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

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

[0016] In the following embodiments, 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.

[0017] 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.

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

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

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

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

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] The system for implementing this invention can efficiently collect feedback using the user login process and use it to improve the model of the generated AI. This system is built on the cooperation between the user's terminal, the authentication server, and the AI ​​improvement server.

[0035] First, to log in to a service, the user enters authentication information (such as a user ID and password) into their device. This information is then sent from the device to the server. The server receives the authentication information and generates a CAPTCHA containing image data and a generated evaluation question to verify the user's legitimacy.

[0036] The generated CAPTCHA is sent to the user's device, which then displays it to the user. The user reviews the image presented in the CAPTCHA and answers questions regarding their evaluation of the generated product. For example, they might select a specific object in the image or rate their satisfaction with the email summary provided by the generating AI.

[0037] The response data entered by the user is returned to the server via the terminal. This response data is stored in a database on the server. This data is used as model improvement data for the generated AI and is aggregated and analyzed on the AI ​​improvement server. The AI ​​model is retrained using this feedback data to improve its performance.

[0038] As a concrete example, consider a user logging into a shopping cart on an e-commerce platform. When the user attempts to log in, the system displays a CAPTCHA containing an image of an animal, along with the question, "Please rate your satisfaction with the AI-generated summary of this product description." The user responds based on the image, rating the AI ​​summary as "satisfied," "somewhat satisfied," etc. The data collected during this process contributes to improving subsequent AI models.

[0039] In this way, the system utilizes routine authentication processes to efficiently collect and aggregate feedback for improving generated AI. This system makes it possible to utilize a large amount of feedback without incurring high costs.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The user accesses the service's login page and enters their user ID and password. The device then sends these authentication details to the server.

[0043] Step 2:

[0044] The server analyzes the received authentication information to verify the user's legitimacy. In this process, the server generates a CAPTCHA that includes image data and a generated evaluation question.

[0045] Step 3:

[0046] The server sends the generated CAPTCHA to the user's device. The device displays the received CAPTCHA and presents a screen prompting the user for an answer.

[0047] Step 4:

[0048] Users select specified objects within an image based on the displayed CAPTCHA and answer the generated evaluation questions. For example, they might answer questions such as "Select all the cars in the image" or "Evaluate the AI-generated summary of this service."

[0049] Step 5:

[0050] The terminal returns the user's CAPTCHA response and the generated evaluation response data to the server.

[0051] Step 6:

[0052] The server stores the received response data in a database. Furthermore, it prepares to create data for improving the AI ​​model based on the accumulated feedback.

[0053] Step 7:

[0054] The server analyzes the collected data and retrains the AI ​​model. This improvement enhances the performance of the generative AI.

[0055] (Example 1)

[0056] 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."

[0057] Modern authentication processes require more than just user verification; they need to efficiently collect useful feedback to improve the performance of generative AI models. However, systems that perform authentication and feedback collection simultaneously are often complex and costly, making it a challenge to collect large amounts of feedback in a cost-effective way.

[0058] 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.

[0059] In this invention, the server includes terminal means for receiving information from users, server means for generating authentication information including various types of data and evaluation questions, and means for creating model improvement information to improve the performance of the data based on the answer data. This makes it possible to efficiently collect feedback necessary for improving the generated AI through the authentication process and improve the performance of the model while keeping costs down.

[0060] A "terminal device" is a device that receives information from users and displays data from a server.

[0061] A "server device" is a device that processes requests based on information received from users and generates authentication information.

[0062] "Authentication information" refers to information generated to authenticate a user's information, including various types of data and evaluation questions.

[0063] "Answer data" refers to data that includes the responses entered by users in response to evaluation questions.

[0064] "Model improvement information" refers to information generated based on the answer data and used to improve the performance of the data.

[0065] To implement this invention, a system is constructed primarily by combining terminal means, server means, database means, and AI-enhanced server means. The details are shown below.

[0066] The user enters login information using a terminal device equipped with an internet connection. This terminal device transmits authentication information to the server device using a security protocol.

[0067] The server system processes user authentication information using a central processing unit and, if necessary, an image processing library. Based on the received information, the server system generates a CAPTCHA using an image processing library such as OpenCV. This includes visual elements such as images of animals or nature, and evaluation questions related to AI. This CAPTCHA is sent to the terminal system and presented to the user.

[0068] The user responds appropriately based on the visual information contained in the displayed CAPTCHA and provides feedback such as "satisfied" or "dissatisfied" in response to evaluation questions. This response data is then sent back to the server via the terminal. The server stores the received data using PostgreSQL or a similar database.

[0069] The AI ​​improvement server analyzes the accumulated data using software such as TENSORFLOW® and PyTorch, and generates a new data structure as a model. This generated material provides important information for improving the performance of the generated AI model.

[0070] As a concrete example, this system can be applied when logging into a shopping cart on an e-commerce platform. When a user attempts to log in, the system will present a CAPTCHA containing an automatically generated animal image and a question asking, "Please rate your satisfaction with this AI-generated summary of the product description."

[0071] Examples of prompts include, "How can we proceed with collecting satisfaction ratings for AI-generated products based on user CAPTCHA response data on an e-commerce site?" and "What is the best way to collect data to improve the generated AI when users log in to a shopping platform?" In this way, a system conforming to the embodiment of the invention enables the collection of useful data for improving the generated AI model during the user authentication process.

[0072] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0073] Step 1:

[0074] The user accesses a specific service using their device and enters their login information (user ID and password). This input data is processed by the device as authentication information and sent to the server. The authentication information is then obtained as output data.

[0075] Step 2:

[0076] The server verifies the user's legitimacy based on the received authentication information. This verification uses a database query to search for information that matches the input, and as a result, the authentication status is output. This process also utilizes OpenCV and PIL to select image data for CAPTCHA generation.

[0077] Step 3:

[0078] The server generates a CAPTCHA after successful user authentication. The CAPTCHA consists of randomly selected image data and questions. Using an image template and a list of questions as input, the generated CAPTCHA is sent to the device as output data.

[0079] Step 4:

[0080] The device displays the received CAPTCHA on the user interface. When displaying it, HTML and JavaScript (registered trademark) are used to show the CAPTCHA image and text question to the user. This results in the CAPTCHA display being obtained as output data.

[0081] Step 5:

[0082] The user enters a response based on a CAPTCHA displayed on their device. Specifically, they select content related to the image and rate their satisfaction with the summary generated by the AI. This response is then taken into the device as new input data.

[0083] Step 6:

[0084] The terminal sends user response data to the server and provides the response data as output data. Secure protocols such as HTTPS are used for transmission.

[0085] Step 7:

[0086] The server saves the received response data to the database. It takes the response data as input data, performs the process of saving it to the database, and generates a status indicating that saving is complete as output data.

[0087] Step 8:

[0088] The AI ​​improvement server analyzes the response data stored in the database. Here, TensorFlow and PyTorch are used to treat the data as model improvement information, and the AI ​​model is retrained. As a result, the improved AI model is obtained as output data.

[0089] Step 9:

[0090] The improved AI model can be used for new predictions and processing and is ready for use on the server. The optimized AI model is obtained as output data.

[0091] (Application Example 1)

[0092] 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."

[0093] A challenge is efficiently collecting the feedback data necessary to improve generative AI models. In particular, in electronic payment services, it is essential to obtain this feedback naturally through the user authentication process. Existing methods make it difficult to collect data frequently and accurately without disrupting the user experience, and therefore, improvement is necessary.

[0094] 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.

[0095] In this invention, the server includes an information processing device that receives authentication information from a user, a data processing device that receives an authentication request based on the authentication information and generates authentication data including visual information and a product evaluation question, and means for presenting a product evaluation question including transaction information in an electronic payment service and collecting the user's evaluation. This makes it possible to improve the performance of a generative AI model using feedback that is naturally collected in the daily authentication process.

[0096] An "information processing device" is an electronic system used to receive user authentication information.

[0097] "Visual information" refers to images and video data presented to the user.

[0098] "Product evaluation questions" are questions designed to allow users to evaluate the quality and content of the product.

[0099] A "data processing device" is an electronic system that generates authentication data based on authentication information and exchanges data with users.

[0100] "Response data" refers to the data entered by users in response to visual information and product evaluation questions.

[0101] "Model improvement data" refers to data used to improve the performance of the generated product.

[0102] An "electronic payment service" is a service that allows users to conduct monetary transactions via the internet.

[0103] "Transaction information" refers to data concerning the specific movement and handling of money in electronic payment services.

[0104] The system for implementing this invention is primarily a network configuration including an information processing device, a data processing device, and a server for AI improvement. The information processing device is responsible for receiving authentication information from the user, and this information is transmitted to the data processing device. Based on the received authentication information, the data processing device generates authentication data including visual information and product evaluation questions, and transmits it to the information processing device. By approving this authentication data, the user can answer product evaluation questions based on their transaction information.

[0105] On the server side, the response data entered by the user is analyzed, and model improvement data is generated. This allows the generated AI model to be continuously improved. Specifically, the AI ​​improvement server runs on a cloud platform such as Google Cloud and performs data analysis using image recognition libraries such as OpenCV.

[0106] For example, consider a scenario where a user uses an electronic payment service application and logs in regularly. When the user attempts to log in, the application displays an image of an animal as a CAPTCHA and presents an evaluation question: "Are you satisfied with the AI ​​summary of your recent payment history?" If the user answers "satisfied," this information is used as data necessary to improve the performance of the AI ​​model, contributing to the improvement of the quality of subsequent AI generation.

[0107] An example of a prompt message is: "Are you satisfied with the AI ​​summary of your recent payment history? Please provide your rating for each item."

[0108] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0109] Step 1:

[0110] The terminal receives authentication information (such as username and password) from the user as input and sends it to the data processing unit. The entered authentication information is then generated as data to be transmitted.

[0111] Step 2:

[0112] The server uses the authentication information received from the terminal as input to initiate an authentication request. This generates authentication data that includes visual information and product evaluation questions. For the visual information, OpenCV is used to select an appropriate image, and the product evaluation questions are automatically generated by AI based on past transaction data.

[0113] Step 3:

[0114] The terminal receives visual information and product evaluation questions sent from the server and presents them to the user. The user then reviews this presented data and prepares to enter their response.

[0115] Step 4:

[0116] The user selects a specific object based on the displayed visual information and enters an evaluation in response to a product evaluation question. This input data is compiled into response data on the terminal.

[0117] Step 5:

[0118] The terminal sends user response data to the server. This transmitted data is used on the server to generate AI improvement data.

[0119] Step 6:

[0120] The server takes the received response data as input, stores it in a database, and generates model improvement data for AI enhancement. This allows the generated AI model to reflect new feedback from the prompt messages, enabling more accurate output.

[0121] 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.

[0122] This invention is a feedback collection system that can recognize a user's emotional state and contribute to improving the model of a generative AI in a way that takes that state into account. This system enhances the value of the collected data by incorporating emotion recognition into the authentication process that is normally performed when a user logs in.

[0123] First, the user enters authentication information on their device when accessing the service. The device sends this information to the server, which then begins a process to verify the user's legitimacy using the authentication information. At this point, the server generates a CAPTCHA that includes image data and a product evaluation question, and sends it to the user's device.

[0124] The device not only displays a CAPTCHA to the user, but also uses an emotion engine to recognize the user's emotions from their facial expressions and tone of voice. This emotion analysis utilizes machine learning algorithms to identify the user's emotional state (e.g., relaxed, stressed, dissatisfied).

[0125] The user solves a CAPTCHA, answers evaluation questions about the generated product, and the sentiment data analyzed by the sentiment engine is sent from the device to the server. The server stores this response data and sentiment data in a database and creates a dataset necessary for improving the generative AI model. In model improvement, the sentiment data is used as important information to complement the subtle nuances behind the user's feedback.

[0126] As a concrete example, when a user logs into a video streaming service, they are presented with a CAPTCHA that requires them to evaluate a specific video clip. During this process, the user's face is scanned with a camera to recognize emotions such as smiles or confusion. This information is used as data to evaluate the emotional impact the video content has on the user, and is used to personalize the generative AI and improve recommendation algorithms.

[0127] Thus, the present invention is a system that can effectively collect rich, emotion-based feedback through the user's daily authentication operations, thereby improving the accuracy of the generated AI and the user experience.

[0128] The following describes the processing flow.

[0129] Step 1:

[0130] The user accesses the service's login screen and enters their user ID and password. The device then sends this authentication information to the server.

[0131] Step 2:

[0132] The server verifies the user's legitimacy based on the received authentication information. Simultaneously, it generates a CAPTCHA containing image data and a product evaluation question.

[0133] Step 3:

[0134] The server sends the generated CAPTCHA to the device. The device displays it to the user and activates the sentiment engine.

[0135] Step 4:

[0136] The user reviews the CAPTCHA, selects a specified object in the image, and answers a generated evaluation question. During this time, the device's emotion engine analyzes the user's facial expressions and tone of voice through the camera and microphone to estimate their current emotional state.

[0137] Step 5:

[0138] Once the user has finished answering the CAPTCHA, the device sends the CAPTCHA answers along with the emotion data recognized by the emotion engine to the server.

[0139] Step 6:

[0140] The server stores the received response data and sentiment data in a database. This data is then incorporated into the dataset for improving the generative AI model.

[0141] Step 7:

[0142] The server analyzes the accumulated data and retrains the AI ​​model based on user feedback. At this stage, emotional data provides in-depth insights into the quality of the feedback, which is expected to improve the AI's performance.

[0143] (Example 2)

[0144] 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".

[0145] Conventional authentication systems typically do not incorporate emotional states when collecting user feedback, and therefore fail to fully utilize the emotional nuances behind the feedback. Furthermore, it was difficult to effectively use the collected feedback to improve the generating AI model. As a result, the performance of the generated products sometimes failed to fully meet user expectations.

[0146] 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.

[0147] In this invention, the server includes means for analyzing the user's emotional state, means for storing and aggregating response data and emotional data, and means for presenting product evaluation questions and evaluating satisfaction. This makes it possible to collect detailed and rich feedback that takes emotions into account.

[0148] A "data input device" is a device that receives authentication information from users and transmits that information to the server.

[0149] A "processing unit" is a device that processes authentication information and generates authentication data, including image data and product evaluation questions.

[0150] "Device" refers to hardware or software that has the function of transmitting authentication data to a data input device and receiving response data.

[0151] "Model improvement data" refers to a dataset used to improve the performance of the generated model by analyzing response data and the emotional state of the user.

[0152] An "information processing system" refers to the entire system used to perform a series of processes, from the authentication process to the evaluation of the resulting products.

[0153] "Emotional state" refers to data that indicates the psychological or emotional condition of a user, estimated from their facial expressions, tone of voice, and other physiological indicators.

[0154] "Product evaluation questions" are questions presented to users to evaluate their opinions and satisfaction with the generated content and services.

[0155] "Response data" refers to the information entered by the user in response to the product evaluation questions presented.

[0156] "Visual information" refers to information that can be seen with the eyes, such as images and videos.

[0157] This invention is an information processing system that collects user feedback that takes emotions into account and improves the performance of the generated AI model. The system mainly consists of a terminal, a server, and a data input device.

[0158] The user enters authentication information into the terminal via a data entry device. The terminal sends the entered information to the server. The server uses the received authentication information to verify the user's legitimacy. This verification step includes database matching using a processing unit.

[0159] The server generates authentication data for authenticated users, including image data and a product evaluation question, and sends it to the terminal. CAPTCHA generation algorithms and image processing software are used at this stage.

[0160] The device is equipped with the ability to recognize the user's emotional state in real time. A model trained with machine learning algorithms is used as the emotion engine, analyzing facial expressions and tone of voice. Specific software used for emotion recognition includes TensorFlow and PyTorch.

[0161] The user answers CAPTCHA and product evaluation questions on their device. In addition to this response data, the device sends sentiment data to the server. This data is processed on the server as model improvement data. The data is used to personalize the AI ​​model and improve recommendation algorithms.

[0162] As a concrete example, when a user logs into a music streaming service, they are presented with a CAPTCHA that requires them to rate a specific song. During this process, the user's face is scanned with a camera to recognize emotions such as joy and sadness. The emotional data obtained through this process will be used as parameters for future music recommendation algorithms.

[0163] Examples of prompts include, "Please describe how you felt when you listened to this song. Briefly explain why you smiled." In this way, this invention enhances the generative AI model by utilizing user feedback and emotional information.

[0164] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0165] Step 1:

[0166] The user enters authentication information on their device to access the service. This input includes basic information such as a user ID and password. The device receives this information, encrypts the data using TLS (Transport Layer Security), and sends it to the server.

[0167] Step 2:

[0168] The server verifies the user's legitimacy by comparing the authentication information received from the terminal with the database. This process involves querying whether the entered information matches the information in the pre-registered database. If the user is confirmed to be legitimate, the server proceeds to the next step.

[0169] Step 3:

[0170] The server generates a CAPTCHA containing image data and a product evaluation question for authenticated users. This CAPTCHA generation uses a CAPTCHA generation algorithm to test the user's attention and judgment. The generated CAPTCHA data is then sent to the device.

[0171] Step 4:

[0172] The device displays a CAPTCHA to the user. Simultaneously, the device senses the user's facial expressions and tone of voice via its built-in emotion engine and collects emotion data. GPU acceleration for image processing is used for emotion recognition. Specifically, machine learning algorithms using TensorFlow and PyTorch perform real-time analysis.

[0173] Step 5:

[0174] The user correctly answers the CAPTCHA and enters their thoughts and evaluations in response to the presented product evaluation questions. The device sends this user input, along with sentiment data, to the server. The data is packaged in JSON format and transmitted using a secure protocol.

[0175] Step 6:

[0176] The server stores response and sentiment data sent from the terminal in a database. This data is used as model improvement data to improve the generative AI model. The server applies aggregation and analysis algorithms to integrate user sentiment and feedback, and uses this to personalize the generated products and improve the recommendation algorithm.

[0177] This sequence of events allows the system to combine sentiment analysis with the user authentication process, collect more detailed and valuable feedback, and improve the performance of its generative AI models.

[0178] (Application Example 2)

[0179] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0180] Existing content delivery services lack personalized content recommendations that adequately consider users' emotional states, thus limiting improvements to the user experience. Therefore, there is a need for a system that recognizes user emotions in real time and provides content recommendations based on those emotions.

[0181] 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.

[0182] In this invention, the server includes an information processing device that receives authentication information and emotional state from a user; processing means that receives an authentication request based on the authentication information and emotional state and generates authentication data including image data, product evaluation questions, and emotional analysis results; means that transmit the authentication data to the information processing device and receive response data and emotional data entered by the user; and means that create model improvement data for improving the performance of products, including content recommendations, based on the response data and emotional data. This enables personalized content recommendations based on the user's emotions.

[0183] A "user" is a person who operates an information processing device and uses a service.

[0184] "Authentication information" refers to information necessary to verify the legitimacy of a user, and may include passwords and biometric authentication data.

[0185] "Emotional state" refers to a temporary psychological condition detected from the user's facial expressions, tone of voice, etc., and includes states such as relaxation and stress.

[0186] An "information processing device" is a terminal used by users to input authentication information and transmit emotional states, and includes smartphones and computers.

[0187] "Image data" refers to digital data containing visual information, and in this invention, it is used as part of the authentication process.

[0188] A "product evaluation question" is a question presented to a user to evaluate a specific product.

[0189] "Emotional analysis results" refer to data obtained by analyzing the user's emotional state, and represent information that demonstrates the success of emotional recognition.

[0190] "Authentication data" refers to a dataset that includes user authentication information, image data, product evaluation questions, and sentiment analysis results.

[0191] "Processing means" refers to a server or software program that performs specific functions such as data generation or receiving authentication requests.

[0192] "Response data" refers to the data entered by the user in response to the presented product evaluation questions.

[0193] "Model improvement data" refers to a dataset containing user response data and sentiment data used to improve generative AI.

[0194] "Content recommendation" is the act of suggesting appropriate digital content based on the user's preferences and emotional state.

[0195] The system for implementing this invention operates during the process of a user logging into a service through an information processing device. The information processing device includes terminals such as smartphones and personal computers. The user enters authentication information into the terminal, which then sends it to the server. Based on the received authentication information, the server initiates the authentication request process. Simultaneously, the server performs sentiment analysis to recognize the user's emotional state. For sentiment analysis, machine learning libraries such as OpenCV and TensorFlow are used to analyze the user's face and tone of voice.

[0196] The server generates authentication data consisting of authentication information, sentiment analysis results, image data, and product evaluation questions, and sends it to the terminal. Based on this authentication data, the user provides answers to the product evaluation questions, and the terminal sends this response data and sentiment analysis results to the server. The server stores this data as model improvement data and uses it to improve the generating AI model. This data processing makes it possible to improve the accuracy of products, including content recommendations.

[0197] A concrete example is using facial recognition technology to determine if a user is smiling while watching a video. If the emotional state is "joyful," similar videos are recommended to improve the user experience. An example of a prompt message would be: "Analyze what kind of content the user is watching when they are displaying certain facial expressions and tone of voice, and collect the most appropriate emotional feedback for that content. Then, based on that, recommend new content that is suitable for the user."

[0198] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0199] Step 1:

[0200] The user enters authentication information into the terminal. This input information includes data such as the user's ID and password. The terminal performs initial processing to send this authentication information to the server. The input is the authentication information from the user, and the output is the authentication request to the server.

[0201] Step 2:

[0202] The server verifies the user's legitimacy based on the authentication information received from the terminal. This verification process checks the consistency of user information by comparing it with the database. The input is the authentication information from the terminal, and the output is the result of user authentication.

[0203] Step 3:

[0204] The server begins processing to analyze the user's emotional state. Using video and audio data obtained from the terminal, it performs facial and vocal analysis using tools such as OpenCV and TensorFlow. The input is video and audio data from the terminal, and the output is the analyzed emotional state data.

[0205] Step 4:

[0206] The server generates authentication data, which includes analyzed emotional state data, image data, and a product evaluation question. This authentication data is prepared to be presented to the user in the next step. The input is emotional state data and additional image data, and the output is the configured authentication data.

[0207] Step 5:

[0208] The terminal displays authentication data received from the server to the user. The user answers the generated evaluation questions and inputs the responses into the terminal. The input is the authentication data from the server, and the output is the user's response to the evaluation questions.

[0209] Step 6:

[0210] The terminal sends user response data and emotional state data to the server. The server receives this data and uses it as a dataset to improve the generative AI model. The input is the response data and emotional state data from the terminal, and the output is the stored dataset.

[0211] Step 7:

[0212] The server uses accumulated data to provide content recommendations optimized for the user's emotions. This recommendation process executes a recommendation algorithm based on the emotion data. The input is emotion data and response data stored in the database, and the output is content recommendations for the user.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] [Second Embodiment]

[0217] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0218] 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.

[0219] 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).

[0220] 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.

[0221] 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.

[0222] 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).

[0223] 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.

[0224] 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.

[0225] 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.

[0226] 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.

[0227] 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.

[0228] 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".

[0229] The system for implementing this invention can efficiently collect feedback using the user login process and use it to improve the model of the generated AI. This system is built on the cooperation between the user's terminal, the authentication server, and the AI ​​improvement server.

[0230] First, to log in to a service, the user enters authentication information (such as a user ID and password) into their device. This information is then sent from the device to the server. The server receives the authentication information and generates a CAPTCHA containing image data and a generated evaluation question to verify the user's legitimacy.

[0231] The generated CAPTCHA is sent to the user's device, which then displays it to the user. The user reviews the image presented in the CAPTCHA and answers questions regarding their evaluation of the generated product. For example, they might select a specific object in the image or rate their satisfaction with the email summary provided by the generating AI.

[0232] The response data entered by the user is returned to the server via the terminal. This response data is stored in a database on the server. This data is used as model improvement data for the generated AI and is aggregated and analyzed on the AI ​​improvement server. The AI ​​model is retrained using this feedback data to improve its performance.

[0233] As a concrete example, consider a user logging into a shopping cart on an e-commerce platform. When the user attempts to log in, the system displays a CAPTCHA containing an image of an animal, along with the question, "Please rate your satisfaction with the AI-generated summary of this product description." The user responds based on the image, rating the AI ​​summary as "satisfied," "somewhat satisfied," etc. The data collected during this process contributes to improving subsequent AI models.

[0234] In this way, the system utilizes routine authentication processes to efficiently collect and aggregate feedback for improving generated AI. This system makes it possible to utilize a large amount of feedback without incurring high costs.

[0235] The following describes the processing flow.

[0236] Step 1:

[0237] The user accesses the service's login page and enters their user ID and password. The device then sends these authentication details to the server.

[0238] Step 2:

[0239] The server analyzes the received authentication information to verify the user's legitimacy. In this process, the server generates a CAPTCHA that includes image data and a generated evaluation question.

[0240] Step 3:

[0241] The server sends the generated CAPTCHA to the user's device. The device displays the received CAPTCHA and presents a screen prompting the user for an answer.

[0242] Step 4:

[0243] Users select specified objects within an image based on the displayed CAPTCHA and answer the generated evaluation questions. For example, they might answer questions such as "Select all the cars in the image" or "Evaluate the AI-generated summary of this service."

[0244] Step 5:

[0245] The terminal returns the user's CAPTCHA response and the generated evaluation response data to the server.

[0246] Step 6:

[0247] The server stores the received response data in a database. Furthermore, it prepares to create data for improving the AI ​​model based on the accumulated feedback.

[0248] Step 7:

[0249] The server analyzes the collected data and retrains the AI ​​model. This improvement enhances the performance of the generative AI.

[0250] (Example 1)

[0251] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0252] Modern authentication processes require more than just user verification; they need to efficiently collect useful feedback to improve the performance of generative AI models. However, systems that perform authentication and feedback collection simultaneously are often complex and costly, making it a challenge to collect large amounts of feedback in a cost-effective way.

[0253] 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.

[0254] In this invention, the server includes terminal means for receiving information from users, server means for generating authentication information including various types of data and evaluation questions, and means for creating model improvement information to improve the performance of the data based on the answer data. This makes it possible to efficiently collect feedback necessary for improving the generated AI through the authentication process and improve the performance of the model while keeping costs down.

[0255] A "terminal device" is a device that receives information from users and displays data from a server.

[0256] A "server device" is a device that processes requests based on information received from users and generates authentication information.

[0257] "Authentication information" refers to information generated to authenticate a user's information, including various types of data and evaluation questions.

[0258] "Answer data" refers to data that includes the responses entered by users in response to evaluation questions.

[0259] "Model improvement information" refers to information generated based on the answer data and used to improve the performance of the data.

[0260] To implement this invention, a system is constructed primarily by combining terminal means, server means, database means, and AI-enhanced server means. The details are shown below.

[0261] The user enters login information using a terminal device equipped with an internet connection. This terminal device transmits authentication information to the server device using a security protocol.

[0262] The server system processes user authentication information using a central processing unit and, if necessary, an image processing library. Based on the received information, the server system generates a CAPTCHA using an image processing library such as OpenCV. This includes visual elements such as images of animals or nature, and evaluation questions related to AI. This CAPTCHA is sent to the terminal system and presented to the user.

[0263] The user responds appropriately based on the visual information contained in the displayed CAPTCHA and provides feedback such as "satisfied" or "dissatisfied" in response to evaluation questions. This response data is then sent back to the server via the terminal. The server stores the received data using PostgreSQL or a similar database.

[0264] The AI ​​improvement server analyzes accumulated data using software such as TensorFlow and PyTorch, and generates a new data structure as a model. This generated data provides important information for improving the performance of the generated AI model.

[0265] As a concrete example, this system can be applied when logging into a shopping cart on an e-commerce platform. When a user attempts to log in, the system will present a CAPTCHA containing an automatically generated animal image and a question asking, "Please rate your satisfaction with this AI-generated summary of the product description."

[0266] Examples of prompts include, "How can we proceed with collecting satisfaction ratings for AI-generated products based on user CAPTCHA response data on an e-commerce site?" and "What is the best way to collect data to improve the generated AI when users log in to a shopping platform?" In this way, a system conforming to the embodiment of the invention enables the collection of useful data for improving the generated AI model during the user authentication process.

[0267] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0268] Step 1:

[0269] The user accesses a specific service using their device and enters their login information (user ID and password). This input data is processed by the device as authentication information and sent to the server. The authentication information is then obtained as output data.

[0270] Step 2:

[0271] The server verifies the user's legitimacy based on the received authentication information. This verification uses a database query to search for information that matches the input, and as a result, the authentication status is output. This process also utilizes OpenCV and PIL to select image data for CAPTCHA generation.

[0272] Step 3:

[0273] The server generates a CAPTCHA after successful user authentication. The CAPTCHA consists of randomly selected image data and questions. Using an image template and a list of questions as input, the generated CAPTCHA is sent to the device as output data.

[0274] Step 4:

[0275] The terminal displays the received CAPTCHA on the user interface. When displaying, HTML and JavaScript are used to show the CAPTCHA image and text question to the user. Thus, the CAPTCHA display is obtained as output data.

[0276] Step 5:

[0277] The user inputs a response based on the CAPTCHA displayed on the terminal. Specifically, the user selects content related to the image or evaluates the satisfaction of the summary by the generative AI. This response is taken into the terminal as new input data.

[0278] Step 6:

[0279] The terminal sends the user's response data to the server and provides the response data as output data. A secure protocol such as HTTPS is used for transmission.

[0280] [[ID= XIX]] Step 7:

[0281] The server saves the received response data in the database. The response data is taken in as input data, the saving process to the database is carried out, and the status of saving completion is generated as output data.

[0282] Step 8:

[0283] [[ID= XXIX]] The AI improvement server analyzes the response data accumulated in the database. Here, TensorFlow or PyTorch is used to handle the data as model improvement information and retrain the AI model. Thus, an improved AI model is obtained as output data.

[0284] [[ID= XXXII]] Step 9:

[0285] The improved AI model can be used for new predictions and processing, and it is ready for use on the server. An optimized AI model is obtained as output data.

[0286] (Application Example 1)

[0287] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0288] Efficiently collecting feedback data necessary for improving the generated AI model is an issue. In particular, in electronic payment services, it is required to naturally obtain such feedback through the user authentication process. With existing methods, it is difficult to collect data with high frequency and accuracy without disturbing the user experience, so there is a need to improve this.

[0289] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means respectively.

[0290] [[ID=?]]In this invention, the server includes an information processing device that receives authentication information from a user, a data processing device that receives an authentication request based on the authentication information and generates authentication data including visual information and a product evaluation question, and means for presenting a product evaluation question including transaction information in an electronic payment service and collecting the user's evaluation. Thereby, it becomes possible to improve the performance of the generated AI model using the feedback naturally collected in the daily authentication process.

[0291] The "information processing device" is an electronic system used to receive the user's authentication information.

[0292] The "visual information" is image or video data presented to the user.

[0293] The "product evaluation question" is a question for the user to evaluate the quality and content of the product.

[0294] The "data processing device" is an electronic system for generating authentication data based on authentication information and performing data exchange with the user.

[0295] Note: There seems to be an issue with the numbering in the original text. The "ID=?" in the translation of line 17 is a placeholder for the correct ID which should be "17" as per the original text's numbering sequence. "Response data" refers to the data entered by users in response to visual information and product evaluation questions.

[0296] "Model improvement data" refers to data used to improve the performance of the generated product.

[0297] An "electronic payment service" is a service that allows users to conduct monetary transactions via the internet.

[0298] "Transaction information" refers to data concerning the specific movement and handling of money in electronic payment services.

[0299] The system for implementing this invention is primarily a network configuration including an information processing device, a data processing device, and a server for AI improvement. The information processing device is responsible for receiving authentication information from the user, and this information is transmitted to the data processing device. Based on the received authentication information, the data processing device generates authentication data including visual information and product evaluation questions, and transmits it to the information processing device. By approving this authentication data, the user can answer product evaluation questions based on their transaction information.

[0300] On the server side, the response data entered by the user is analyzed, and model improvement data is generated. This allows the generated AI model to be continuously improved. Specifically, the AI ​​improvement server runs on a cloud platform such as Google Cloud and performs data analysis using image recognition libraries such as OpenCV.

[0301] For example, consider a scenario where a user uses an electronic payment service application and logs in regularly. When the user attempts to log in, the application displays an image of an animal as a CAPTCHA and presents an evaluation question: "Are you satisfied with the AI ​​summary of your recent payment history?" If the user answers "satisfied," this information is used as data necessary to improve the performance of the AI ​​model, contributing to the improvement of the quality of subsequent AI generation.

[0302] As an example of a prompt sentence, it is set like "Are you satisfied with the AI summary regarding the recent payment history? Please let us know each evaluation."

[0303] The flow of the specific process in Application Example 1 will be described with reference to FIG. 12.

[0304] Step 1:

[0305] The terminal receives authentication information (such as a username and password) from the user as input and transmits it to the data processing device. The input authentication information is generated as transmission data.

[0306] Step 2:

[0307] The server makes an authentication request using the authentication information received from the terminal as input. As a result, authentication data including visual information and a product evaluation question is generated. The visual information selects an appropriate image using OpenCV, and the product evaluation question is automatically generated by AI based on past transaction data.

[0308] Step 3:

[0309] The terminal receives the visual information and the product evaluation question transmitted from the server and presents them to the user. Looking at the presented data, the user prepares to input a response.

[0310] Step 4:

[0311] [[ID=�9]]The user selects a specific object based on the displayed visual information and inputs an evaluation for the product evaluation question. These input data are compiled as response data at the terminal.

[0312] Step 5:

[0313] The terminal sends user response data to the server. This transmitted data is used on the server to generate AI improvement data.

[0314] Step 6:

[0315] The server takes the received response data as input, stores it in a database, and generates model improvement data for AI enhancement. This allows the generated AI model to reflect new feedback from the prompt messages, enabling more accurate output.

[0316] 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.

[0317] This invention is a feedback collection system that can recognize a user's emotional state and contribute to improving the model of a generative AI in a way that takes that state into account. This system enhances the value of the collected data by incorporating emotion recognition into the authentication process that is normally performed when a user logs in.

[0318] First, the user enters authentication information on their device when accessing the service. The device sends this information to the server, which then begins a process to verify the user's legitimacy using the authentication information. At this point, the server generates a CAPTCHA that includes image data and a product evaluation question, and sends it to the user's device.

[0319] The device not only displays a CAPTCHA to the user, but also uses an emotion engine to recognize the user's emotions from their facial expressions and tone of voice. This emotion analysis utilizes machine learning algorithms to identify the user's emotional state (e.g., relaxed, stressed, dissatisfied).

[0320] The user solves a CAPTCHA, answers evaluation questions about the generated product, and the sentiment data analyzed by the sentiment engine is sent from the device to the server. The server stores this response data and sentiment data in a database and creates a dataset necessary for improving the generative AI model. In model improvement, the sentiment data is used as important information to complement the subtle nuances behind the user's feedback.

[0321] As a concrete example, when a user logs into a video streaming service, they are presented with a CAPTCHA that requires them to evaluate a specific video clip. During this process, the user's face is scanned with a camera to recognize emotions such as smiles or confusion. This information is used as data to evaluate the emotional impact the video content has on the user, and is used to personalize the generative AI and improve recommendation algorithms.

[0322] Thus, the present invention is a system that can effectively collect rich, emotion-based feedback through the user's daily authentication operations, thereby improving the accuracy of the generated AI and the user experience.

[0323] The following describes the processing flow.

[0324] Step 1:

[0325] The user accesses the service's login screen and enters their user ID and password. The device then sends this authentication information to the server.

[0326] Step 2:

[0327] The server verifies the user's legitimacy based on the received authentication information. Simultaneously, it generates a CAPTCHA containing image data and a product evaluation question.

[0328] Step 3:

[0329] The server sends the generated CAPTCHA to the device. The device displays it to the user and activates the sentiment engine.

[0330] Step 4:

[0331] The user reviews the CAPTCHA, selects a specified object in the image, and answers a generated evaluation question. During this time, the device's emotion engine analyzes the user's facial expressions and tone of voice through the camera and microphone to estimate their current emotional state.

[0332] Step 5:

[0333] Once the user has finished answering the CAPTCHA, the device sends the CAPTCHA answers along with the emotion data recognized by the emotion engine to the server.

[0334] Step 6:

[0335] The server stores the received response data and sentiment data in a database. This data is then incorporated into the dataset for improving the generative AI model.

[0336] Step 7:

[0337] The server analyzes the accumulated data and retrains the AI ​​model based on user feedback. At this stage, emotional data provides in-depth insights into the quality of the feedback, which is expected to improve the AI's performance.

[0338] (Example 2)

[0339] 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".

[0340] Conventional authentication systems typically do not incorporate emotional states when collecting user feedback, and therefore fail to fully utilize the emotional nuances behind the feedback. Furthermore, it was difficult to effectively use the collected feedback to improve the generating AI model. As a result, the performance of the generated products sometimes failed to fully meet user expectations.

[0341] 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.

[0342] In this invention, the server includes means for analyzing the user's emotional state, means for storing and aggregating response data and emotional data, and means for presenting product evaluation questions and evaluating satisfaction. This makes it possible to collect detailed and rich feedback that takes emotions into account.

[0343] A "data input device" is a device that receives authentication information from users and transmits that information to the server.

[0344] A "processing unit" is a device that processes authentication information and generates authentication data, including image data and product evaluation questions.

[0345] "Device" refers to hardware or software that has the function of transmitting authentication data to a data input device and receiving response data.

[0346] "Model improvement data" refers to a dataset used to improve the performance of the generated model by analyzing response data and the emotional state of the user.

[0347] An "information processing system" refers to the entire system used to perform a series of processes, from the authentication process to the evaluation of the resulting products.

[0348] "Emotional state" refers to data that indicates the psychological or emotional condition of a user, estimated from their facial expressions, tone of voice, and other physiological indicators.

[0349] "Product evaluation questions" are questions presented to users to evaluate their opinions and satisfaction with the generated content and services.

[0350] "Response data" refers to the information entered by the user in response to the product evaluation questions presented.

[0351] "Visual information" refers to information that can be seen with the eyes, such as images and videos.

[0352] This invention is an information processing system that collects user feedback that takes emotions into account and improves the performance of the generated AI model. The system mainly consists of a terminal, a server, and a data input device.

[0353] The user enters authentication information into the terminal via a data entry device. The terminal sends the entered information to the server. The server uses the received authentication information to verify the user's legitimacy. This verification step includes database matching using a processing unit.

[0354] The server generates authentication data for authenticated users, including image data and a product evaluation question, and sends it to the terminal. CAPTCHA generation algorithms and image processing software are used at this stage.

[0355] The device is equipped with the ability to recognize the user's emotional state in real time. A model trained with machine learning algorithms is used as the emotion engine, analyzing facial expressions and tone of voice. Specific software used for emotion recognition includes TensorFlow and PyTorch.

[0356] The user answers CAPTCHA and product evaluation questions on their device. In addition to this response data, the device sends sentiment data to the server. This data is processed on the server as model improvement data. The data is used to personalize the AI ​​model and improve recommendation algorithms.

[0357] As a concrete example, when a user logs into a music streaming service, they are presented with a CAPTCHA that requires them to rate a specific song. During this process, the user's face is scanned with a camera to recognize emotions such as joy and sadness. The emotional data obtained through this process will be used as parameters for future music recommendation algorithms.

[0358] Examples of prompts include, "Please describe how you felt when you listened to this song. Briefly explain why you smiled." In this way, this invention enhances the generative AI model by utilizing user feedback and emotional information.

[0359] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0360] Step 1:

[0361] The user enters authentication information on their device to access the service. This input includes basic information such as a user ID and password. The device receives this information, encrypts the data using TLS (Transport Layer Security), and sends it to the server.

[0362] Step 2:

[0363] The server verifies the user's legitimacy by comparing the authentication information received from the terminal with the database. This process involves querying whether the entered information matches the information in the pre-registered database. If the user is confirmed to be legitimate, the server proceeds to the next step.

[0364] Step 3:

[0365] The server generates a CAPTCHA containing image data and a product evaluation question for authenticated users. This CAPTCHA generation uses a CAPTCHA generation algorithm to test the user's attention and judgment. The generated CAPTCHA data is then sent to the device.

[0366] Step 4:

[0367] The device displays a CAPTCHA to the user. Simultaneously, the device senses the user's facial expressions and tone of voice via its built-in emotion engine and collects emotion data. GPU acceleration for image processing is used for emotion recognition. Specifically, machine learning algorithms using TensorFlow and PyTorch perform real-time analysis.

[0368] Step 5:

[0369] The user correctly answers the CAPTCHA and enters their thoughts and evaluations in response to the presented product evaluation questions. The device sends this user input, along with sentiment data, to the server. The data is packaged in JSON format and transmitted using a secure protocol.

[0370] Step 6:

[0371] The server stores response and sentiment data sent from the terminal in a database. This data is used as model improvement data to improve the generative AI model. The server applies aggregation and analysis algorithms to integrate user sentiment and feedback, and uses this to personalize the generated products and improve the recommendation algorithm.

[0372] This sequence of events allows the system to combine sentiment analysis with the user authentication process, collect more detailed and valuable feedback, and improve the performance of its generative AI models.

[0373] (Application Example 2)

[0374] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0375] Existing content delivery services lack personalized content recommendations that adequately consider users' emotional states, thus limiting improvements to the user experience. Therefore, there is a need for a system that recognizes user emotions in real time and provides content recommendations based on those emotions.

[0376] 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.

[0377] In this invention, the server includes an information processing device that receives authentication information and emotional state from a user; processing means that receives an authentication request based on the authentication information and emotional state and generates authentication data including image data, product evaluation questions, and emotional analysis results; means that transmit the authentication data to the information processing device and receive response data and emotional data entered by the user; and means that create model improvement data for improving the performance of products, including content recommendations, based on the response data and emotional data. This enables personalized content recommendations based on the user's emotions.

[0378] A "user" is a person who operates an information processing device and uses a service.

[0379] "Authentication information" refers to information necessary to verify the legitimacy of a user, and may include passwords and biometric authentication data.

[0380] "Emotional state" refers to a temporary psychological condition detected from the user's facial expressions, tone of voice, etc., and includes states such as relaxation and stress.

[0381] An "information processing device" is a terminal used by users to input authentication information and transmit emotional states, and includes smartphones and computers.

[0382] "Image data" refers to digital data containing visual information, and in this invention, it is used as part of the authentication process.

[0383] A "product evaluation question" is a question presented to a user to evaluate a specific product.

[0384] "Emotional analysis results" refer to data obtained by analyzing the user's emotional state, and represent information that demonstrates the success of emotional recognition.

[0385] "Authentication data" refers to a dataset that includes user authentication information, image data, product evaluation questions, and sentiment analysis results.

[0386] "Processing means" refers to a server or software program that performs specific functions such as data generation or receiving authentication requests.

[0387] "Response data" refers to the data entered by the user in response to the presented product evaluation questions.

[0388] "Model improvement data" refers to a dataset containing user response data and sentiment data used to improve generative AI.

[0389] "Content recommendation" is the act of suggesting appropriate digital content based on the user's preferences and emotional state.

[0390] The system for implementing this invention operates during the process of a user logging into a service through an information processing device. The information processing device includes terminals such as smartphones and personal computers. The user enters authentication information into the terminal, which then sends it to the server. Based on the received authentication information, the server initiates the authentication request process. Simultaneously, the server performs sentiment analysis to recognize the user's emotional state. For sentiment analysis, machine learning libraries such as OpenCV and TensorFlow are used to analyze the user's face and tone of voice.

[0391] The server generates authentication data consisting of authentication information, sentiment analysis results, image data, and product evaluation questions, and sends it to the terminal. Based on this authentication data, the user provides answers to the product evaluation questions, and the terminal sends this response data and sentiment analysis results to the server. The server stores this data as model improvement data and uses it to improve the generating AI model. This data processing makes it possible to improve the accuracy of products, including content recommendations.

[0392] A concrete example is using facial recognition technology to determine if a user is smiling while watching a video. If the emotional state is "joyful," similar videos are recommended to improve the user experience. An example of a prompt message would be: "Analyze what kind of content the user is watching when they are displaying certain facial expressions and tone of voice, and collect the most appropriate emotional feedback for that content. Then, based on that, recommend new content that is suitable for the user."

[0393] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0394] Step 1:

[0395] The user enters authentication information into the terminal. This input information includes data such as the user's ID and password. The terminal performs initial processing to send this authentication information to the server. The input is the authentication information from the user, and the output is the authentication request to the server.

[0396] Step 2:

[0397] The server verifies the user's legitimacy based on the authentication information received from the terminal. This verification process checks the consistency of user information by comparing it with the database. The input is the authentication information from the terminal, and the output is the result of user authentication.

[0398] Step 3:

[0399] The server begins processing to analyze the user's emotional state. Using video and audio data obtained from the terminal, it performs facial and vocal analysis using tools such as OpenCV and TensorFlow. The input is video and audio data from the terminal, and the output is the analyzed emotional state data.

[0400] Step 4:

[0401] The server generates authentication data, which includes analyzed emotional state data, image data, and a product evaluation question. This authentication data is prepared to be presented to the user in the next step. The input is emotional state data and additional image data, and the output is the configured authentication data.

[0402] Step 5:

[0403] The terminal displays authentication data received from the server to the user. The user answers the generated evaluation questions and inputs the responses into the terminal. The input is the authentication data from the server, and the output is the user's response to the evaluation questions.

[0404] Step 6:

[0405] The terminal sends user response data and emotional state data to the server. The server receives this data and uses it as a dataset to improve the generative AI model. The input is the response data and emotional state data from the terminal, and the output is the stored dataset.

[0406] Step 7:

[0407] The server uses accumulated data to provide content recommendations optimized for the user's emotions. This recommendation process executes a recommendation algorithm based on the emotion data. The input is emotion data and response data stored in the database, and the output is content recommendations for the user.

[0408] 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.

[0409] 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.

[0410] 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.

[0411] [Third Embodiment]

[0412] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0413] 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.

[0414] 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).

[0415] 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.

[0416] 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.

[0417] 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).

[0418] 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.

[0419] 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.

[0420] 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.

[0421] 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.

[0422] 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.

[0423] 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".

[0424] The system for implementing this invention can efficiently collect feedback using the user login process and use it to improve the model of the generated AI. This system is built on the cooperation between the user's terminal, the authentication server, and the AI ​​improvement server.

[0425] First, to log in to a service, the user enters authentication information (such as a user ID and password) into their device. This information is then sent from the device to the server. The server receives the authentication information and generates a CAPTCHA containing image data and a generated evaluation question to verify the user's legitimacy.

[0426] The generated CAPTCHA is sent to the user's device, which then displays it to the user. The user reviews the image presented in the CAPTCHA and answers questions regarding their evaluation of the generated product. For example, they might select a specific object in the image or rate their satisfaction with the email summary provided by the generating AI.

[0427] The response data entered by the user is returned to the server via the terminal. This response data is stored in a database on the server. This data is used as model improvement data for the generated AI and is aggregated and analyzed on the AI ​​improvement server. The AI ​​model is retrained using this feedback data to improve its performance.

[0428] As a concrete example, consider a user logging into a shopping cart on an e-commerce platform. When the user attempts to log in, the system displays a CAPTCHA containing an image of an animal, along with the question, "Please rate your satisfaction with the AI-generated summary of this product description." The user responds based on the image, rating the AI ​​summary as "satisfied," "somewhat satisfied," etc. The data collected during this process contributes to improving subsequent AI models.

[0429] In this way, the system utilizes routine authentication processes to efficiently collect and aggregate feedback for improving generated AI. This system makes it possible to utilize a large amount of feedback without incurring high costs.

[0430] The following describes the processing flow.

[0431] Step 1:

[0432] The user accesses the service's login page and enters their user ID and password. The device then sends these authentication details to the server.

[0433] Step 2:

[0434] The server analyzes the received authentication information to verify the user's legitimacy. In this process, the server generates a CAPTCHA that includes image data and a generated evaluation question.

[0435] Step 3:

[0436] The server sends the generated CAPTCHA to the user's device. The device displays the received CAPTCHA and presents a screen prompting the user for an answer.

[0437] Step 4:

[0438] Users select specified objects within an image based on the displayed CAPTCHA and answer the generated evaluation questions. For example, they might answer questions such as "Select all the cars in the image" or "Evaluate the AI-generated summary of this service."

[0439] Step 5:

[0440] The terminal returns the user's CAPTCHA response and the generated evaluation response data to the server.

[0441] Step 6:

[0442] The server stores the received response data in a database. Furthermore, it prepares to create data for improving the AI ​​model based on the accumulated feedback.

[0443] Step 7:

[0444] The server analyzes the collected data and retrains the AI ​​model. This improvement enhances the performance of the generative AI.

[0445] (Example 1)

[0446] 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."

[0447] Modern authentication processes require more than just user verification; they need to efficiently collect useful feedback to improve the performance of generative AI models. However, systems that perform authentication and feedback collection simultaneously are often complex and costly, making it a challenge to collect large amounts of feedback in a cost-effective way.

[0448] 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.

[0449] In this invention, the server includes terminal means for receiving information from users, server means for generating authentication information including various types of data and evaluation questions, and means for creating model improvement information to improve the performance of the data based on the answer data. This makes it possible to efficiently collect feedback necessary for improving the generated AI through the authentication process and improve the performance of the model while keeping costs down.

[0450] A "terminal device" is a device that receives information from users and displays data from a server.

[0451] A "server device" is a device that processes requests based on information received from users and generates authentication information.

[0452] "Authentication information" refers to information generated to authenticate a user's information, including various types of data and evaluation questions.

[0453] "Answer data" refers to data that includes the responses entered by users in response to evaluation questions.

[0454] "Model improvement information" refers to information generated based on the answer data and used to improve the performance of the data.

[0455] To implement this invention, a system is constructed primarily by combining terminal means, server means, database means, and AI-enhanced server means. The details are shown below.

[0456] The user enters login information using a terminal device equipped with an internet connection. This terminal device transmits authentication information to the server device using a security protocol.

[0457] The server system processes user authentication information using a central processing unit and, if necessary, an image processing library. Based on the received information, the server system generates a CAPTCHA using an image processing library such as OpenCV. This includes visual elements such as images of animals or nature, and evaluation questions related to AI. This CAPTCHA is sent to the terminal system and presented to the user.

[0458] The user responds appropriately based on the visual information contained in the displayed CAPTCHA and provides feedback such as "satisfied" or "dissatisfied" in response to evaluation questions. This response data is then sent back to the server via the terminal. The server stores the received data using PostgreSQL or a similar database.

[0459] The AI ​​improvement server analyzes accumulated data using software such as TensorFlow and PyTorch, and generates a new data structure as a model. This generated data provides important information for improving the performance of the generated AI model.

[0460] As a concrete example, this system can be applied when logging into a shopping cart on an e-commerce platform. When a user attempts to log in, the system will present a CAPTCHA containing an automatically generated animal image and a question asking, "Please rate your satisfaction with this AI-generated summary of the product description."

[0461] Examples of prompts include, "How can we proceed with collecting satisfaction ratings for AI-generated products based on user CAPTCHA response data on an e-commerce site?" and "What is the best way to collect data to improve the generated AI when users log in to a shopping platform?" In this way, a system conforming to the embodiment of the invention enables the collection of useful data for improving the generated AI model during the user authentication process.

[0462] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0463] Step 1:

[0464] The user accesses a specific service using their device and enters their login information (user ID and password). This input data is processed by the device as authentication information and sent to the server. The authentication information is then obtained as output data.

[0465] Step 2:

[0466] The server verifies the user's legitimacy based on the received authentication information. This verification uses a database query to search for information that matches the input, and as a result, the authentication status is output. This process also utilizes OpenCV and PIL to select image data for CAPTCHA generation.

[0467] Step 3:

[0468] The server generates a CAPTCHA after successful user authentication. The CAPTCHA consists of randomly selected image data and questions. Using an image template and a list of questions as input, the generated CAPTCHA is sent to the device as output data.

[0469] Step 4:

[0470] The device displays the received CAPTCHA on the user interface. When displaying it, HTML and JavaScript are used to show the CAPTCHA image and text question to the user. This results in the CAPTCHA display being obtained as output data.

[0471] Step 5:

[0472] The user enters a response based on a CAPTCHA displayed on their device. Specifically, they select content related to the image and rate their satisfaction with the summary generated by the AI. This response is then taken into the device as new input data.

[0473] Step 6:

[0474] The terminal sends user response data to the server and provides the response data as output data. Secure protocols such as HTTPS are used for transmission.

[0475] Step 7:

[0476] The server saves the received response data to the database. It takes the response data as input data, performs the process of saving it to the database, and generates a status indicating that saving is complete as output data.

[0477] Step 8:

[0478] The AI ​​improvement server analyzes the response data stored in the database. Here, TensorFlow and PyTorch are used to treat the data as model improvement information, and the AI ​​model is retrained. As a result, the improved AI model is obtained as output data.

[0479] Step 9:

[0480] The improved AI model can be used for new predictions and processing and is ready for use on the server. The optimized AI model is obtained as output data.

[0481] (Application Example 1)

[0482] 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."

[0483] A challenge is efficiently collecting the feedback data necessary to improve generative AI models. In particular, in electronic payment services, it is essential to obtain this feedback naturally through the user authentication process. Existing methods make it difficult to collect data frequently and accurately without disrupting the user experience, and therefore, improvement is necessary.

[0484] 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.

[0485] In this invention, the server includes an information processing device that receives authentication information from a user, a data processing device that receives an authentication request based on the authentication information and generates authentication data including visual information and a product evaluation question, and means for presenting a product evaluation question including transaction information in an electronic payment service and collecting the user's evaluation. This makes it possible to improve the performance of a generative AI model using feedback that is naturally collected in the daily authentication process.

[0486] An "information processing device" is an electronic system used to receive user authentication information.

[0487] "Visual information" refers to images and video data presented to the user.

[0488] "Product evaluation questions" are questions designed to allow users to evaluate the quality and content of the product.

[0489] A "data processing device" is an electronic system that generates authentication data based on authentication information and exchanges data with users.

[0490] "Response data" refers to the data entered by users in response to visual information and product evaluation questions.

[0491] "Model improvement data" refers to data used to improve the performance of the generated product.

[0492] An "electronic payment service" is a service that allows users to conduct monetary transactions via the internet.

[0493] "Transaction information" refers to data concerning the specific movement and handling of money in electronic payment services.

[0494] The system for implementing this invention is primarily a network configuration including an information processing device, a data processing device, and a server for AI improvement. The information processing device is responsible for receiving authentication information from the user, and this information is transmitted to the data processing device. Based on the received authentication information, the data processing device generates authentication data including visual information and product evaluation questions, and transmits it to the information processing device. By approving this authentication data, the user can answer product evaluation questions based on their transaction information.

[0495] On the server side, the response data entered by the user is analyzed, and model improvement data is generated. This allows the generated AI model to be continuously improved. Specifically, the AI ​​improvement server runs on a cloud platform such as Google Cloud and performs data analysis using image recognition libraries such as OpenCV.

[0496] For example, consider a scenario where a user uses an electronic payment service application and logs in regularly. When the user attempts to log in, the application displays an image of an animal as a CAPTCHA and presents an evaluation question: "Are you satisfied with the AI ​​summary of your recent payment history?" If the user answers "satisfied," this information is used as data necessary to improve the performance of the AI ​​model, contributing to the improvement of the quality of subsequent AI generation.

[0497] An example of a prompt message is: "Are you satisfied with the AI ​​summary of your recent payment history? Please provide your rating for each item."

[0498] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0499] Step 1:

[0500] The terminal receives authentication information (such as username and password) from the user as input and sends it to the data processing unit. The entered authentication information is then generated as data to be transmitted.

[0501] Step 2:

[0502] The server uses the authentication information received from the terminal as input to initiate an authentication request. This generates authentication data that includes visual information and product evaluation questions. For the visual information, OpenCV is used to select an appropriate image, and the product evaluation questions are automatically generated by AI based on past transaction data.

[0503] Step 3:

[0504] The terminal receives visual information and product evaluation questions sent from the server and presents them to the user. The user then reviews this presented data and prepares to enter their response.

[0505] Step 4:

[0506] The user selects a specific object based on the displayed visual information and enters an evaluation in response to a product evaluation question. This input data is compiled into response data on the terminal.

[0507] Step 5:

[0508] The terminal sends user response data to the server. This transmitted data is used on the server to generate AI improvement data.

[0509] Step 6:

[0510] The server takes the received response data as input, stores it in a database, and generates model improvement data for AI enhancement. This allows the generated AI model to reflect new feedback from the prompt messages, enabling more accurate output.

[0511] 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.

[0512] This invention is a feedback collection system that can recognize a user's emotional state and contribute to improving the model of a generative AI in a way that takes that state into account. This system enhances the value of the collected data by incorporating emotion recognition into the authentication process that is normally performed when a user logs in.

[0513] First, the user enters authentication information on their device when accessing the service. The device sends this information to the server, which then begins a process to verify the user's legitimacy using the authentication information. At this point, the server generates a CAPTCHA that includes image data and a product evaluation question, and sends it to the user's device.

[0514] The device not only displays a CAPTCHA to the user, but also uses an emotion engine to recognize the user's emotions from their facial expressions and tone of voice. This emotion analysis utilizes machine learning algorithms to identify the user's emotional state (e.g., relaxed, stressed, dissatisfied).

[0515] The user solves a CAPTCHA, answers evaluation questions about the generated product, and the sentiment data analyzed by the sentiment engine is sent from the device to the server. The server stores this response data and sentiment data in a database and creates a dataset necessary for improving the generative AI model. In model improvement, the sentiment data is used as important information to complement the subtle nuances behind the user's feedback.

[0516] As a concrete example, when a user logs into a video streaming service, they are presented with a CAPTCHA that requires them to evaluate a specific video clip. During this process, the user's face is scanned with a camera to recognize emotions such as smiles or confusion. This information is used as data to evaluate the emotional impact the video content has on the user, and is used to personalize the generative AI and improve recommendation algorithms.

[0517] Thus, the present invention is a system that can effectively collect rich, emotion-based feedback through the user's daily authentication operations, thereby improving the accuracy of the generated AI and the user experience.

[0518] The following describes the processing flow.

[0519] Step 1:

[0520] The user accesses the service's login screen and enters their user ID and password. The device then sends this authentication information to the server.

[0521] Step 2:

[0522] The server verifies the user's legitimacy based on the received authentication information. Simultaneously, it generates a CAPTCHA containing image data and a product evaluation question.

[0523] Step 3:

[0524] The server sends the generated CAPTCHA to the device. The device displays it to the user and activates the sentiment engine.

[0525] Step 4:

[0526] The user reviews the CAPTCHA, selects a specified object in the image, and answers a generated evaluation question. During this time, the device's emotion engine analyzes the user's facial expressions and tone of voice through the camera and microphone to estimate their current emotional state.

[0527] Step 5:

[0528] Once the user has finished answering the CAPTCHA, the device sends the CAPTCHA answers along with the emotion data recognized by the emotion engine to the server.

[0529] Step 6:

[0530] The server stores the received response data and sentiment data in a database. This data is then incorporated into the dataset for improving the generative AI model.

[0531] Step 7:

[0532] The server analyzes the accumulated data and retrains the AI ​​model based on user feedback. At this stage, emotional data provides in-depth insights into the quality of the feedback, which is expected to improve the AI's performance.

[0533] (Example 2)

[0534] 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."

[0535] Conventional authentication systems typically do not incorporate emotional states when collecting user feedback, and therefore fail to fully utilize the emotional nuances behind the feedback. Furthermore, it was difficult to effectively use the collected feedback to improve the generating AI model. As a result, the performance of the generated products sometimes failed to fully meet user expectations.

[0536] 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.

[0537] In this invention, the server includes means for analyzing the user's emotional state, means for storing and aggregating response data and emotional data, and means for presenting product evaluation questions and evaluating satisfaction. This makes it possible to collect detailed and rich feedback that takes emotions into account.

[0538] A "data input device" is a device that receives authentication information from users and transmits that information to the server.

[0539] A "processing unit" is a device that processes authentication information and generates authentication data, including image data and product evaluation questions.

[0540] "Device" refers to hardware or software that has the function of transmitting authentication data to a data input device and receiving response data.

[0541] "Model improvement data" refers to a dataset used to improve the performance of the generated model by analyzing response data and the emotional state of the user.

[0542] An "information processing system" refers to the entire system used to perform a series of processes, from the authentication process to the evaluation of the resulting products.

[0543] "Emotional state" refers to data that indicates the psychological or emotional condition of a user, estimated from their facial expressions, tone of voice, and other physiological indicators.

[0544] "Product evaluation questions" are questions presented to users to evaluate their opinions and satisfaction with the generated content and services.

[0545] "Response data" refers to the information entered by the user in response to the product evaluation questions presented.

[0546] "Visual information" refers to information that can be seen with the eyes, such as images and videos.

[0547] This invention is an information processing system that collects user feedback that takes emotions into account and improves the performance of the generated AI model. The system mainly consists of a terminal, a server, and a data input device.

[0548] The user enters authentication information into the terminal via a data entry device. The terminal sends the entered information to the server. The server uses the received authentication information to verify the user's legitimacy. This verification step includes database matching using a processing unit.

[0549] The server generates authentication data for authenticated users, including image data and a product evaluation question, and sends it to the terminal. CAPTCHA generation algorithms and image processing software are used at this stage.

[0550] The device is equipped with the ability to recognize the user's emotional state in real time. A model trained with machine learning algorithms is used as the emotion engine, analyzing facial expressions and tone of voice. Specific software used for emotion recognition includes TensorFlow and PyTorch.

[0551] The user answers CAPTCHA and product evaluation questions on their device. In addition to this response data, the device sends sentiment data to the server. This data is processed on the server as model improvement data. The data is used to personalize the AI ​​model and improve recommendation algorithms.

[0552] As a concrete example, when a user logs into a music streaming service, they are presented with a CAPTCHA that requires them to rate a specific song. During this process, the user's face is scanned with a camera to recognize emotions such as joy and sadness. The emotional data obtained through this process will be used as parameters for future music recommendation algorithms.

[0553] Examples of prompts include, "Please describe how you felt when you listened to this song. Briefly explain why you smiled." In this way, this invention enhances the generative AI model by utilizing user feedback and emotional information.

[0554] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0555] Step 1:

[0556] The user enters authentication information on their device to access the service. This input includes basic information such as a user ID and password. The device receives this information, encrypts the data using TLS (Transport Layer Security), and sends it to the server.

[0557] Step 2:

[0558] The server verifies the user's legitimacy by comparing the authentication information received from the terminal with the database. This process involves querying whether the entered information matches the information in the pre-registered database. If the user is confirmed to be legitimate, the server proceeds to the next step.

[0559] Step 3:

[0560] The server generates a CAPTCHA containing image data and a product evaluation question for authenticated users. This CAPTCHA generation uses a CAPTCHA generation algorithm to test the user's attention and judgment. The generated CAPTCHA data is then sent to the device.

[0561] Step 4:

[0562] The device displays a CAPTCHA to the user. Simultaneously, the device senses the user's facial expressions and tone of voice via its built-in emotion engine and collects emotion data. GPU acceleration for image processing is used for emotion recognition. Specifically, machine learning algorithms using TensorFlow and PyTorch perform real-time analysis.

[0563] Step 5:

[0564] The user correctly answers the CAPTCHA and enters their thoughts and evaluations in response to the presented product evaluation questions. The device sends this user input, along with sentiment data, to the server. The data is packaged in JSON format and transmitted using a secure protocol.

[0565] Step 6:

[0566] The server stores response and sentiment data sent from the terminal in a database. This data is used as model improvement data to improve the generative AI model. The server applies aggregation and analysis algorithms to integrate user sentiment and feedback, and uses this to personalize the generated products and improve the recommendation algorithm.

[0567] This sequence of events allows the system to combine sentiment analysis with the user authentication process, collect more detailed and valuable feedback, and improve the performance of its generative AI models.

[0568] (Application Example 2)

[0569] 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."

[0570] Existing content delivery services lack personalized content recommendations that adequately consider users' emotional states, thus limiting improvements to the user experience. Therefore, there is a need for a system that recognizes user emotions in real time and provides content recommendations based on those emotions.

[0571] 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.

[0572] In this invention, the server includes an information processing device that receives authentication information and emotional state from a user; processing means that receives an authentication request based on the authentication information and emotional state and generates authentication data including image data, product evaluation questions, and emotional analysis results; means that transmit the authentication data to the information processing device and receive response data and emotional data entered by the user; and means that create model improvement data for improving the performance of products, including content recommendations, based on the response data and emotional data. This enables personalized content recommendations based on the user's emotions.

[0573] A "user" is a person who operates an information processing device and uses a service.

[0574] "Authentication information" refers to information necessary to verify the legitimacy of a user, and may include passwords and biometric authentication data.

[0575] "Emotional state" refers to a temporary psychological condition detected from the user's facial expressions, tone of voice, etc., and includes states such as relaxation and stress.

[0576] An "information processing device" is a terminal used by users to input authentication information and transmit emotional states, and includes smartphones and computers.

[0577] "Image data" refers to digital data containing visual information, and in this invention, it is used as part of the authentication process.

[0578] A "product evaluation question" is a question presented to a user to evaluate a specific product.

[0579] "Emotional analysis results" refer to data obtained by analyzing the user's emotional state, and represent information that demonstrates the success of emotional recognition.

[0580] "Authentication data" refers to a dataset that includes user authentication information, image data, product evaluation questions, and sentiment analysis results.

[0581] "Processing means" refers to a server or software program that performs specific functions such as data generation or receiving authentication requests.

[0582] "Response data" refers to the data entered by the user in response to the presented product evaluation questions.

[0583] "Model improvement data" refers to a dataset containing user response data and sentiment data used to improve generative AI.

[0584] "Content recommendation" is the act of suggesting appropriate digital content based on the user's preferences and emotional state.

[0585] The system for implementing this invention operates during the process of a user logging into a service through an information processing device. The information processing device includes terminals such as smartphones and personal computers. The user enters authentication information into the terminal, which then sends it to the server. Based on the received authentication information, the server initiates the authentication request process. Simultaneously, the server performs sentiment analysis to recognize the user's emotional state. For sentiment analysis, machine learning libraries such as OpenCV and TensorFlow are used to analyze the user's face and tone of voice.

[0586] The server generates authentication data consisting of authentication information, sentiment analysis results, image data, and product evaluation questions, and sends it to the terminal. Based on this authentication data, the user provides answers to the product evaluation questions, and the terminal sends this response data and sentiment analysis results to the server. The server stores this data as model improvement data and uses it to improve the generating AI model. This data processing makes it possible to improve the accuracy of products, including content recommendations.

[0587] A concrete example is using facial recognition technology to determine if a user is smiling while watching a video. If the emotional state is "joyful," similar videos are recommended to improve the user experience. An example of a prompt message would be: "Analyze what kind of content the user is watching when they are displaying certain facial expressions and tone of voice, and collect the most appropriate emotional feedback for that content. Then, based on that, recommend new content that is suitable for the user."

[0588] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0589] Step 1:

[0590] The user enters authentication information into the terminal. This input information includes data such as the user's ID and password. The terminal performs initial processing to send this authentication information to the server. The input is the authentication information from the user, and the output is the authentication request to the server.

[0591] Step 2:

[0592] The server verifies the user's legitimacy based on the authentication information received from the terminal. This verification process checks the consistency of user information by comparing it with the database. The input is the authentication information from the terminal, and the output is the result of user authentication.

[0593] Step 3:

[0594] The server begins processing to analyze the user's emotional state. Using video and audio data obtained from the terminal, it performs facial and vocal analysis using tools such as OpenCV and TensorFlow. The input is video and audio data from the terminal, and the output is the analyzed emotional state data.

[0595] Step 4:

[0596] The server generates authentication data, which includes analyzed emotional state data, image data, and a product evaluation question. This authentication data is prepared to be presented to the user in the next step. The input is emotional state data and additional image data, and the output is the configured authentication data.

[0597] Step 5:

[0598] The terminal displays authentication data received from the server to the user. The user answers the generated evaluation questions and inputs the responses into the terminal. The input is the authentication data from the server, and the output is the user's response to the evaluation questions.

[0599] Step 6:

[0600] The terminal sends user response data and emotional state data to the server. The server receives this data and uses it as a dataset to improve the generative AI model. The input is the response data and emotional state data from the terminal, and the output is the stored dataset.

[0601] Step 7:

[0602] The server uses accumulated data to provide content recommendations optimized for the user's emotions. This recommendation process executes a recommendation algorithm based on the emotion data. The input is emotion data and response data stored in the database, and the output is content recommendations for the user.

[0603] 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.

[0604] 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.

[0605] 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.

[0606] [Fourth Embodiment]

[0607] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0608] 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.

[0609] 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).

[0610] 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.

[0611] 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.

[0612] 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).

[0613] 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.

[0614] 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.

[0615] 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.

[0616] 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.

[0617] 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.

[0618] 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.

[0619] 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".

[0620] The system for implementing this invention can efficiently collect feedback using the user login process and use it to improve the model of the generated AI. This system is built on the cooperation between the user's terminal, the authentication server, and the AI ​​improvement server.

[0621] First, to log in to a service, the user enters authentication information (such as a user ID and password) into their device. This information is then sent from the device to the server. The server receives the authentication information and generates a CAPTCHA containing image data and a generated evaluation question to verify the user's legitimacy.

[0622] The generated CAPTCHA is sent to the user's device, which then displays it to the user. The user reviews the image presented in the CAPTCHA and answers questions regarding their evaluation of the generated product. For example, they might select a specific object in the image or rate their satisfaction with the email summary provided by the generating AI.

[0623] The response data entered by the user is returned to the server via the terminal. This response data is stored in a database on the server. This data is used as model improvement data for the generated AI and is aggregated and analyzed on the AI ​​improvement server. The AI ​​model is retrained using this feedback data to improve its performance.

[0624] As a concrete example, consider a user logging into a shopping cart on an e-commerce platform. When the user attempts to log in, the system displays a CAPTCHA containing an image of an animal, along with the question, "Please rate your satisfaction with the AI-generated summary of this product description." The user responds based on the image, rating the AI ​​summary as "satisfied," "somewhat satisfied," etc. The data collected during this process contributes to improving subsequent AI models.

[0625] In this way, the system utilizes routine authentication processes to efficiently collect and aggregate feedback for improving generated AI. This system makes it possible to utilize a large amount of feedback without incurring high costs.

[0626] The following describes the processing flow.

[0627] Step 1:

[0628] The user accesses the service's login page and enters their user ID and password. The device then sends these authentication details to the server.

[0629] Step 2:

[0630] The server analyzes the received authentication information to verify the user's legitimacy. In this process, the server generates a CAPTCHA that includes image data and a generated evaluation question.

[0631] Step 3:

[0632] The server sends the generated CAPTCHA to the user's device. The device displays the received CAPTCHA and presents a screen prompting the user for an answer.

[0633] Step 4:

[0634] Users select specified objects within an image based on the displayed CAPTCHA and answer the generated evaluation questions. For example, they might answer questions such as "Select all the cars in the image" or "Evaluate the AI-generated summary of this service."

[0635] Step 5:

[0636] The terminal returns the user's CAPTCHA response and the generated evaluation response data to the server.

[0637] Step 6:

[0638] The server stores the received response data in a database. Furthermore, it prepares to create data for improving the AI ​​model based on the accumulated feedback.

[0639] Step 7:

[0640] The server analyzes the collected data and retrains the AI ​​model. This improvement enhances the performance of the generative AI.

[0641] (Example 1)

[0642] 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".

[0643] Modern authentication processes require more than just user verification; they need to efficiently collect useful feedback to improve the performance of generative AI models. However, systems that perform authentication and feedback collection simultaneously are often complex and costly, making it a challenge to collect large amounts of feedback in a cost-effective way.

[0644] 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.

[0645] In this invention, the server includes terminal means for receiving information from users, server means for generating authentication information including various types of data and evaluation questions, and means for creating model improvement information to improve the performance of the data based on the answer data. This makes it possible to efficiently collect feedback necessary for improving the generated AI through the authentication process and improve the performance of the model while keeping costs down.

[0646] A "terminal device" is a device that receives information from users and displays data from a server.

[0647] A "server device" is a device that processes requests based on information received from users and generates authentication information.

[0648] "Authentication information" refers to information generated to authenticate a user's information, including various types of data and evaluation questions.

[0649] "Answer data" refers to data that includes the responses entered by users in response to evaluation questions.

[0650] "Model improvement information" refers to information generated based on the answer data and used to improve the performance of the data.

[0651] To implement this invention, a system is constructed primarily by combining terminal means, server means, database means, and AI-enhanced server means. The details are shown below.

[0652] The user enters login information using a terminal device equipped with an internet connection. This terminal device transmits authentication information to the server device using a security protocol.

[0653] The server system processes user authentication information using a central processing unit and, if necessary, an image processing library. Based on the received information, the server system generates a CAPTCHA using an image processing library such as OpenCV. This includes visual elements such as images of animals or nature, and evaluation questions related to AI. This CAPTCHA is sent to the terminal system and presented to the user.

[0654] The user responds appropriately based on the visual information contained in the displayed CAPTCHA and provides feedback such as "satisfied" or "dissatisfied" in response to evaluation questions. This response data is then sent back to the server via the terminal. The server stores the received data using PostgreSQL or a similar database.

[0655] The AI ​​improvement server analyzes accumulated data using software such as TensorFlow and PyTorch, and generates a new data structure as a model. This generated data provides important information for improving the performance of the generated AI model.

[0656] As a concrete example, this system can be applied when logging into a shopping cart on an e-commerce platform. When a user attempts to log in, the system will present a CAPTCHA containing an automatically generated animal image and a question asking, "Please rate your satisfaction with this AI-generated summary of the product description."

[0657] Examples of prompts include, "How can we proceed with collecting satisfaction ratings for AI-generated products based on user CAPTCHA response data on an e-commerce site?" and "What is the best way to collect data to improve the generated AI when users log in to a shopping platform?" In this way, a system conforming to the embodiment of the invention enables the collection of useful data for improving the generated AI model during the user authentication process.

[0658] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0659] Step 1:

[0660] The user accesses a specific service using their device and enters their login information (user ID and password). This input data is processed by the device as authentication information and sent to the server. The authentication information is then obtained as output data.

[0661] Step 2:

[0662] The server verifies the user's legitimacy based on the received authentication information. This verification uses a database query to search for information that matches the input, and as a result, the authentication status is output. This process also utilizes OpenCV and PIL to select image data for CAPTCHA generation.

[0663] Step 3:

[0664] The server generates a CAPTCHA after successful user authentication. The CAPTCHA consists of randomly selected image data and questions. Using an image template and a list of questions as input, the generated CAPTCHA is sent to the device as output data.

[0665] Step 4:

[0666] The device displays the received CAPTCHA on the user interface. When displaying it, HTML and JavaScript are used to show the CAPTCHA image and text question to the user. This results in the CAPTCHA display being obtained as output data.

[0667] Step 5:

[0668] The user enters a response based on a CAPTCHA displayed on their device. Specifically, they select content related to the image and rate their satisfaction with the summary generated by the AI. This response is then taken into the device as new input data.

[0669] Step 6:

[0670] The terminal sends user response data to the server and provides the response data as output data. Secure protocols such as HTTPS are used for transmission.

[0671] Step 7:

[0672] The server saves the received response data to the database. It takes the response data as input data, performs the process of saving it to the database, and generates a status indicating that saving is complete as output data.

[0673] Step 8:

[0674] The AI ​​improvement server analyzes the response data stored in the database. Here, TensorFlow and PyTorch are used to treat the data as model improvement information, and the AI ​​model is retrained. As a result, the improved AI model is obtained as output data.

[0675] Step 9:

[0676] The improved AI model can be used for new predictions and processing and is ready for use on the server. The optimized AI model is obtained as output data.

[0677] (Application Example 1)

[0678] 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".

[0679] A challenge is efficiently collecting the feedback data necessary to improve generative AI models. In particular, in electronic payment services, it is essential to obtain this feedback naturally through the user authentication process. Existing methods make it difficult to collect data frequently and accurately without disrupting the user experience, and therefore, improvement is necessary.

[0680] 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.

[0681] In this invention, the server includes an information processing device that receives authentication information from a user, a data processing device that receives an authentication request based on the authentication information and generates authentication data including visual information and a product evaluation question, and means for presenting a product evaluation question including transaction information in an electronic payment service and collecting the user's evaluation. This makes it possible to improve the performance of a generative AI model using feedback that is naturally collected in the daily authentication process.

[0682] An "information processing device" is an electronic system used to receive user authentication information.

[0683] "Visual information" refers to images and video data presented to the user.

[0684] "Product evaluation questions" are questions designed to allow users to evaluate the quality and content of the product.

[0685] A "data processing device" is an electronic system that generates authentication data based on authentication information and exchanges data with users.

[0686] "Response data" refers to the data entered by users in response to visual information and product evaluation questions.

[0687] "Model improvement data" refers to data used to improve the performance of the generated product.

[0688] An "electronic payment service" is a service that allows users to conduct monetary transactions via the internet.

[0689] "Transaction information" refers to data concerning the specific movement and handling of money in electronic payment services.

[0690] The system for implementing this invention is primarily a network configuration including an information processing device, a data processing device, and a server for AI improvement. The information processing device is responsible for receiving authentication information from the user, and this information is transmitted to the data processing device. Based on the received authentication information, the data processing device generates authentication data including visual information and product evaluation questions, and transmits it to the information processing device. By approving this authentication data, the user can answer product evaluation questions based on their transaction information.

[0691] On the server side, the response data entered by the user is analyzed, and model improvement data is generated. This allows the generated AI model to be continuously improved. Specifically, the AI ​​improvement server runs on a cloud platform such as Google Cloud and performs data analysis using image recognition libraries such as OpenCV.

[0692] For example, consider a scenario where a user uses an electronic payment service application and logs in regularly. When the user attempts to log in, the application displays an image of an animal as a CAPTCHA and presents an evaluation question: "Are you satisfied with the AI ​​summary of your recent payment history?" If the user answers "satisfied," this information is used as data necessary to improve the performance of the AI ​​model, contributing to the improvement of the quality of subsequent AI generation.

[0693] An example of a prompt message is: "Are you satisfied with the AI ​​summary of your recent payment history? Please provide your rating for each item."

[0694] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0695] Step 1:

[0696] The terminal receives authentication information (such as username and password) from the user as input and sends it to the data processing unit. The entered authentication information is then generated as data to be transmitted.

[0697] Step 2:

[0698] The server uses the authentication information received from the terminal as input to initiate an authentication request. This generates authentication data that includes visual information and product evaluation questions. For the visual information, OpenCV is used to select an appropriate image, and the product evaluation questions are automatically generated by AI based on past transaction data.

[0699] Step 3:

[0700] The terminal receives visual information and product evaluation questions sent from the server and presents them to the user. The user then reviews this presented data and prepares to enter their response.

[0701] Step 4:

[0702] The user selects a specific object based on the displayed visual information and enters an evaluation in response to a product evaluation question. This input data is compiled into response data on the terminal.

[0703] Step 5:

[0704] The terminal sends user response data to the server. This transmitted data is used on the server to generate AI improvement data.

[0705] Step 6:

[0706] The server takes the received response data as input, stores it in a database, and generates model improvement data for AI enhancement. This allows the generated AI model to reflect new feedback from the prompt messages, enabling more accurate output.

[0707] 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.

[0708] This invention is a feedback collection system that can recognize a user's emotional state and contribute to improving the model of a generative AI in a way that takes that state into account. This system enhances the value of the collected data by incorporating emotion recognition into the authentication process that is normally performed when a user logs in.

[0709] First, the user enters authentication information on their device when accessing the service. The device sends this information to the server, which then begins a process to verify the user's legitimacy using the authentication information. At this point, the server generates a CAPTCHA that includes image data and a product evaluation question, and sends it to the user's device.

[0710] The device not only displays a CAPTCHA to the user, but also uses an emotion engine to recognize the user's emotions from their facial expressions and tone of voice. This emotion analysis utilizes machine learning algorithms to identify the user's emotional state (e.g., relaxed, stressed, dissatisfied).

[0711] The user solves a CAPTCHA, answers evaluation questions about the generated product, and the sentiment data analyzed by the sentiment engine is sent from the device to the server. The server stores this response data and sentiment data in a database and creates a dataset necessary for improving the generative AI model. In model improvement, the sentiment data is used as important information to complement the subtle nuances behind the user's feedback.

[0712] As a concrete example, when a user logs into a video streaming service, they are presented with a CAPTCHA that requires them to evaluate a specific video clip. During this process, the user's face is scanned with a camera to recognize emotions such as smiles or confusion. This information is used as data to evaluate the emotional impact the video content has on the user, and is used to personalize the generative AI and improve recommendation algorithms.

[0713] Thus, the present invention is a system that can effectively collect rich, emotion-based feedback through the user's daily authentication operations, thereby improving the accuracy of the generated AI and the user experience.

[0714] The following describes the processing flow.

[0715] Step 1:

[0716] The user accesses the service's login screen and enters their user ID and password. The device then sends this authentication information to the server.

[0717] Step 2:

[0718] The server verifies the user's legitimacy based on the received authentication information. Simultaneously, it generates a CAPTCHA containing image data and a product evaluation question.

[0719] Step 3:

[0720] The server sends the generated CAPTCHA to the device. The device displays it to the user and activates the sentiment engine.

[0721] Step 4:

[0722] The user reviews the CAPTCHA, selects a specified object in the image, and answers a generated evaluation question. During this time, the device's emotion engine analyzes the user's facial expressions and tone of voice through the camera and microphone to estimate their current emotional state.

[0723] Step 5:

[0724] Once the user has finished answering the CAPTCHA, the device sends the CAPTCHA answers along with the emotion data recognized by the emotion engine to the server.

[0725] Step 6:

[0726] The server stores the received response data and sentiment data in a database. This data is then incorporated into the dataset for improving the generative AI model.

[0727] Step 7:

[0728] The server analyzes the accumulated data and retrains the AI ​​model based on user feedback. At this stage, emotional data provides in-depth insights into the quality of the feedback, which is expected to improve the AI's performance.

[0729] (Example 2)

[0730] 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".

[0731] Conventional authentication systems typically do not incorporate emotional states when collecting user feedback, and therefore fail to fully utilize the emotional nuances behind the feedback. Furthermore, it was difficult to effectively use the collected feedback to improve the generating AI model. As a result, the performance of the generated products sometimes failed to fully meet user expectations.

[0732] 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.

[0733] In this invention, the server includes means for analyzing the user's emotional state, means for storing and aggregating response data and emotional data, and means for presenting product evaluation questions and evaluating satisfaction. This makes it possible to collect detailed and rich feedback that takes emotions into account.

[0734] A "data input device" is a device that receives authentication information from users and transmits that information to the server.

[0735] A "processing unit" is a device that processes authentication information and generates authentication data, including image data and product evaluation questions.

[0736] "Device" refers to hardware or software that has the function of transmitting authentication data to a data input device and receiving response data.

[0737] "Model improvement data" refers to a dataset used to improve the performance of the generated model by analyzing response data and the emotional state of the user.

[0738] An "information processing system" refers to the entire system used to perform a series of processes, from the authentication process to the evaluation of the resulting products.

[0739] "Emotional state" refers to data that indicates the psychological or emotional condition of a user, estimated from their facial expressions, tone of voice, and other physiological indicators.

[0740] "Product evaluation questions" are questions presented to users to evaluate their opinions and satisfaction with the generated content and services.

[0741] "Response data" refers to the information entered by the user in response to the product evaluation questions presented.

[0742] "Visual information" refers to information that can be seen with the eyes, such as images and videos.

[0743] This invention is an information processing system that collects user feedback that takes emotions into account and improves the performance of the generated AI model. The system mainly consists of a terminal, a server, and a data input device.

[0744] The user enters authentication information into the terminal via a data entry device. The terminal sends the entered information to the server. The server uses the received authentication information to verify the user's legitimacy. This verification step includes database matching using a processing unit.

[0745] The server generates authentication data for authenticated users, including image data and a product evaluation question, and sends it to the terminal. CAPTCHA generation algorithms and image processing software are used at this stage.

[0746] The device is equipped with the ability to recognize the user's emotional state in real time. A model trained with machine learning algorithms is used as the emotion engine, analyzing facial expressions and tone of voice. Specific software used for emotion recognition includes TensorFlow and PyTorch.

[0747] The user answers CAPTCHA and product evaluation questions on their device. In addition to this response data, the device sends sentiment data to the server. This data is processed on the server as model improvement data. The data is used to personalize the AI ​​model and improve recommendation algorithms.

[0748] As a concrete example, when a user logs into a music streaming service, they are presented with a CAPTCHA that requires them to rate a specific song. During this process, the user's face is scanned with a camera to recognize emotions such as joy and sadness. The emotional data obtained through this process will be used as parameters for future music recommendation algorithms.

[0749] Examples of prompts include, "Please describe how you felt when you listened to this song. Briefly explain why you smiled." In this way, this invention enhances the generative AI model by utilizing user feedback and emotional information.

[0750] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0751] Step 1:

[0752] The user enters authentication information on their device to access the service. This input includes basic information such as a user ID and password. The device receives this information, encrypts the data using TLS (Transport Layer Security), and sends it to the server.

[0753] Step 2:

[0754] The server verifies the user's legitimacy by comparing the authentication information received from the terminal with the database. This process involves querying whether the entered information matches the information in the pre-registered database. If the user is confirmed to be legitimate, the server proceeds to the next step.

[0755] Step 3:

[0756] The server generates a CAPTCHA containing image data and a product evaluation question for authenticated users. This CAPTCHA generation uses a CAPTCHA generation algorithm to test the user's attention and judgment. The generated CAPTCHA data is then sent to the device.

[0757] Step 4:

[0758] The device displays a CAPTCHA to the user. Simultaneously, the device senses the user's facial expressions and tone of voice via its built-in emotion engine and collects emotion data. GPU acceleration for image processing is used for emotion recognition. Specifically, machine learning algorithms using TensorFlow and PyTorch perform real-time analysis.

[0759] Step 5:

[0760] The user correctly answers the CAPTCHA and enters their thoughts and evaluations in response to the presented product evaluation questions. The device sends this user input, along with sentiment data, to the server. The data is packaged in JSON format and transmitted using a secure protocol.

[0761] Step 6:

[0762] The server stores response and sentiment data sent from the terminal in a database. This data is used as model improvement data to improve the generative AI model. The server applies aggregation and analysis algorithms to integrate user sentiment and feedback, and uses this to personalize the generated products and improve the recommendation algorithm.

[0763] This sequence of events allows the system to combine sentiment analysis with the user authentication process, collect more detailed and valuable feedback, and improve the performance of its generative AI models.

[0764] (Application Example 2)

[0765] 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".

[0766] Existing content delivery services lack personalized content recommendations that adequately consider users' emotional states, thus limiting improvements to the user experience. Therefore, there is a need for a system that recognizes user emotions in real time and provides content recommendations based on those emotions.

[0767] 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.

[0768] In this invention, the server includes an information processing device that receives authentication information and emotional state from a user; processing means that receives an authentication request based on the authentication information and emotional state and generates authentication data including image data, product evaluation questions, and emotional analysis results; means that transmit the authentication data to the information processing device and receive response data and emotional data entered by the user; and means that create model improvement data for improving the performance of products, including content recommendations, based on the response data and emotional data. This enables personalized content recommendations based on the user's emotions.

[0769] A "user" is a person who operates an information processing device and uses a service.

[0770] "Authentication information" refers to information necessary to verify the legitimacy of a user, and may include passwords and biometric authentication data.

[0771] "Emotional state" refers to a temporary psychological condition detected from the user's facial expressions, tone of voice, etc., and includes states such as relaxation and stress.

[0772] An "information processing device" is a terminal used by users to input authentication information and transmit emotional states, and includes smartphones and computers.

[0773] "Image data" refers to digital data containing visual information, and in this invention, it is used as part of the authentication process.

[0774] A "product evaluation question" is a question presented to a user to evaluate a specific product.

[0775] "Emotional analysis results" refer to data obtained by analyzing the user's emotional state, and represent information that demonstrates the success of emotional recognition.

[0776] "Authentication data" refers to a dataset that includes user authentication information, image data, product evaluation questions, and sentiment analysis results.

[0777] "Processing means" refers to a server or software program that performs specific functions such as data generation or receiving authentication requests.

[0778] "Response data" refers to the data entered by the user in response to the presented product evaluation questions.

[0779] "Model improvement data" refers to a dataset containing user response data and sentiment data used to improve generative AI.

[0780] "Content recommendation" is the act of suggesting appropriate digital content based on the user's preferences and emotional state.

[0781] The system for implementing this invention operates during the process of a user logging into a service through an information processing device. The information processing device includes terminals such as smartphones and personal computers. The user enters authentication information into the terminal, which then sends it to the server. Based on the received authentication information, the server initiates the authentication request process. Simultaneously, the server performs sentiment analysis to recognize the user's emotional state. For sentiment analysis, machine learning libraries such as OpenCV and TensorFlow are used to analyze the user's face and tone of voice.

[0782] The server generates authentication data consisting of authentication information, sentiment analysis results, image data, and product evaluation questions, and sends it to the terminal. Based on this authentication data, the user provides answers to the product evaluation questions, and the terminal sends this response data and sentiment analysis results to the server. The server stores this data as model improvement data and uses it to improve the generating AI model. This data processing makes it possible to improve the accuracy of products, including content recommendations.

[0783] A concrete example is using facial recognition technology to determine if a user is smiling while watching a video. If the emotional state is "joyful," similar videos are recommended to improve the user experience. An example of a prompt message would be: "Analyze what kind of content the user is watching when they are displaying certain facial expressions and tone of voice, and collect the most appropriate emotional feedback for that content. Then, based on that, recommend new content that is suitable for the user."

[0784] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0785] Step 1:

[0786] The user enters authentication information into the terminal. This input information includes data such as the user's ID and password. The terminal performs initial processing to send this authentication information to the server. The input is the authentication information from the user, and the output is the authentication request to the server.

[0787] Step 2:

[0788] The server verifies the user's legitimacy based on the authentication information received from the terminal. This verification process checks the consistency of user information by comparing it with the database. The input is the authentication information from the terminal, and the output is the result of user authentication.

[0789] Step 3:

[0790] The server begins processing to analyze the user's emotional state. Using video and audio data obtained from the terminal, it performs facial and vocal analysis using tools such as OpenCV and TensorFlow. The input is video and audio data from the terminal, and the output is the analyzed emotional state data.

[0791] Step 4:

[0792] The server generates authentication data, which includes analyzed emotional state data, image data, and a product evaluation question. This authentication data is prepared to be presented to the user in the next step. The input is emotional state data and additional image data, and the output is the configured authentication data.

[0793] Step 5:

[0794] The terminal displays authentication data received from the server to the user. The user answers the generated evaluation questions and inputs the responses into the terminal. The input is the authentication data from the server, and the output is the user's response to the evaluation questions.

[0795] Step 6:

[0796] The terminal sends user response data and emotional state data to the server. The server receives this data and uses it as a dataset to improve the generative AI model. The input is the response data and emotional state data from the terminal, and the output is the stored dataset.

[0797] Step 7:

[0798] The server uses accumulated data to provide content recommendations optimized for the user's emotions. This recommendation process executes a recommendation algorithm based on the emotion data. The input is emotion data and response data stored in the database, and the output is content recommendations for the user.

[0799] 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.

[0800] 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.

[0801] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0802] 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.

[0803] 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.

[0804] 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.

[0805] 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.

[0806] 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.

[0807] 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."

[0808] 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.

[0809] 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.

[0810] 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.

[0811] 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.

[0812] 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.

[0813] 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.

[0814] 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.

[0815] 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.

[0816] 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.

[0817] 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.

[0818] 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.

[0819] 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.

[0820] The following is further disclosed regarding the embodiments described above.

[0821] (Claim 1)

[0822] An information processing device that receives authentication information from users,

[0823] A server means that receives an authentication request based on the authentication information and generates authentication data including image data and product evaluation questions,

[0824] A means for transmitting the authentication data to the information processing device and receiving the response data entered by the user,

[0825] A means for creating model improvement data to improve the performance of the product based on the response data,

[0826] A system that includes this.

[0827] (Claim 2)

[0828] The system according to claim 1, wherein the server means has means for storing and aggregating the response data.

[0829] (Claim 3)

[0830] The system according to claim 1, wherein the product evaluation question includes the selection of visual information or an evaluation of satisfaction with the product.

[0831] "Example 1"

[0832] (Claim 1)

[0833] A terminal device for receiving information from users,

[0834] A server means that receives a request based on the said information and generates authentication information including various types of data and evaluation questions,

[0835] A means for transmitting the authentication information to the terminal means and receiving the answer data entered by the user,

[0836] A means for creating model improvement information to improve the performance of the data based on the aforementioned answer data,

[0837] A system that includes this.

[0838] (Claim 2)

[0839] The system according to claim 1, wherein the server means has means for storing and processing the answer data.

[0840] (Claim 3)

[0841] The system according to claim 1, wherein the evaluation question includes the selection of visual information or an evaluation of the product.

[0842] "Application Example 1"

[0843] (Claim 1)

[0844] An information processing device that receives authentication information from users,

[0845] A data processing device that receives an authentication request based on the authentication information and generates authentication data including visual information and product evaluation questions,

[0846] A device that transmits the authentication data to the information processing device and receives the response data entered by the user,

[0847] An apparatus for creating model improvement data to improve the performance of the product based on the response data,

[0848] A means of presenting evaluation questions for generated products containing transaction information in electronic payment services and collecting user evaluations,

[0849] A system that includes this.

[0850] (Claim 2)

[0851] The system according to claim 1, wherein the data processing device has a device for storing and aggregating the response data.

[0852] (Claim 3)

[0853] The system according to claim 1, wherein the product evaluation question includes a satisfaction evaluation of the selection of visual information or a transaction summary.

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

[0855] (Claim 1)

[0856] A data input device that receives authentication information from users,

[0857] A computing device that receives an authentication request based on the authentication information and generates authentication data including image data and product evaluation questions,

[0858] A device that transmits the authentication data to the data input device and receives the response data entered by the user,

[0859] An apparatus for analyzing the response data and the user's emotional state, and for creating model improvement data to improve the performance of the product,

[0860] An information processing system that includes this.

[0861] (Claim 2)

[0862] The information processing system according to claim 1, wherein the computing device has means for storing and aggregating the response data and emotion data.

[0863] (Claim 3)

[0864] The information processing system according to claim 1, wherein the product evaluation question includes the selection of visual information or an evaluation of satisfaction with the product.

[0865] "Application example 2 when combining with an emotional engine"

[0866] (Claim 1)

[0867] An information processing device that receives authentication information and emotional state from a user,

[0868] Processing means that receive an authentication request based on the authentication information and emotional state, and generate authentication data including image data, product evaluation questions, and emotional analysis results,

[0869] A means for transmitting the authentication data to the information processing device and receiving the response data and emotion data entered by the user,

[0870] A means for creating model improvement data to improve the performance of the generated product, including content recommendation, based on the response data and sentiment data,

[0871] A system that includes this.

[0872] (Claim 2)

[0873] The system according to claim 1, wherein the processing means includes means for storing and aggregating the response data and emotion data.

[0874] (Claim 3)

[0875] The system according to claim 1, wherein the product evaluation questions and sentiment analysis results include the selection of visual information and tone or an evaluation of emotional satisfaction with the product. [Explanation of symbols]

[0876] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. An information processing device that receives authentication information from users, A server means that receives an authentication request based on the authentication information and generates authentication data including image data and product evaluation questions, A means for transmitting the authentication data to the information processing device and receiving the response data entered by the user, A means for creating model improvement data to improve the performance of the product based on the response data, A system that includes this.

2. The system according to claim 1, wherein the server means has means for storing and aggregating the response data.

3. The system according to claim 1, wherein the product evaluation question includes the selection of visual information or an evaluation of satisfaction with the product.

Images