system

Abstract

We provide the system. [Solution] Information gathering means for acquiring user operation data and storing said operation data, A behavioral analysis means that analyzes the aforementioned operation data using a generative artificial intelligence model and identifies the user's behavioral patterns, A notification means that generates notification information based on the aforementioned behavioral pattern and presents said notification information to the user, An evaluation method that provides personalized advice to users based on their purchasing behavior, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] When consumers use an e-commerce site, they may unconsciously make a biased purchase choice, and as a result, purchase unnecessary products. Such problems are particularly prominent among the younger generation and are one of the factors hindering planned and effective consumption behavior. To solve this problem and provide a more satisfactory purchase experience, a method for visualizing user biases and improving purchase behavior is necessary.

Means for Solving the Problems

[0005] This invention provides a system including data collection means for acquiring and storing user operation data, behavioral analysis means for analyzing the operation data using a generating artificial intelligence model to identify user behavior patterns, and notification means for generating notification information based on the behavior patterns and presenting it to the user. Furthermore, it uses algorithms based on behavioral economics to detect biases that influence purchasing behavior and assists users in making appropriate purchasing choices. In addition, the system is continuously improved by adding feedback processing means that collect user feedback and use it to improve the accuracy of the generating artificial intelligence model. This makes it possible to suppress unnecessary purchases and provide a more advanced e-commerce experience.

[0006] "User activity data" refers to information about a series of actions taken by a user when using an e-commerce site, such as browsing, clicking, searching, and making purchases.

[0007] "Data collection means" refers to the functions and methods used to acquire user operation data and store it within the system.

[0008] A "generative artificial intelligence model" is software designed to analyze patterns based on given data and make predictions or decisions according to specific purposes.

[0009] "Behavioral analysis means" refers to the processes and functions used to analyze collected operational data and extract user behavior patterns and tendencies.

[0010] "Behavioral patterns" refer to the consistent behaviors and tendencies in choices that users exhibit under specific circumstances.

[0011] "Notification information" refers to information such as advice, warnings, and suggestions that are generated based on analysis results and provided to the user.

[0012] "Notification means" refers to functions or mechanisms for presenting generated notification information to the user visually or audibly.

[0013] Behavioral economics is the field of study that investigates how people make decisions, particularly the biases and cognitive processes at play in economic choices.

[0014] "Bias" refers to a psychological tendency or inclination that unconsciously influences decision-making in a particular direction.

[0015] "Feedback processing means" refers to functions and methods for collecting user reactions and opinions and using them to improve systems and models. [Brief explanation of the drawing]

[0016] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 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 Embodiment 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Mode for Carrying Out the Invention

[0017] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0019] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

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

[0021] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

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

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0024] [First Embodiment]

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

[0026] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0029] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0033] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0036] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0037] The following describes embodiments for carrying out the present invention. This invention is a system for analyzing user purchasing behavior and suppressing unnecessary purchases. The system includes data collection means, behavioral analysis means, notification means, and feedback processing means.

[0038] First, the device acquires operational data when the user uses an e-commerce site. This operational data includes information about the products the user viewed, purchase history, and even the time of the session. This allows for a detailed record of the user's behavior.

[0039] Next, the server stores the operation data sent from the terminal in a database. Based on this data, it builds a generative artificial intelligence model. This model is used to analyze the user's past behavior and identify behavioral patterns and biases.

[0040] Based on the behavioral patterns identified by the generated AI model, the server detects potential biases in the user. In this process, behavioral economics theories can be referenced to reveal tendencies such as "having purchased similar products multiple times in the past."

[0041] Subsequently, the device displays notification information based on the analysis results to the user as a pop-up message. This notification includes advice to caution the user against making unnecessary purchases. The user can then use this information to review their purchasing behavior.

[0042] Furthermore, users can provide feedback via their devices regarding notification content and system feedback. This allows the system to receive user feedback, which the server then uses to improve its AI models and notification algorithms. This enables the system to continuously improve accuracy and enrich the user experience.

[0043] As a concrete example, consider a case where a user in their 20s tries to purchase the same type of accessory multiple times late at night. A server that references this user's data generates a notification based on their past similar purchase history, stating, "You have previously owned multiple items of the same type of accessory," and displays it to the user on their device. In response, the user can reconsider their need for the product before purchasing, preventing unnecessary purchases.

[0044] This system helps consumers make wiser decisions by improving transparency in purchasing choices.

[0045] The following describes the processing flow.

[0046] Step 1:

[0047] The device collects real-time data on user activity when visiting e-commerce sites. This includes details of products viewed, time spent on the site, links clicked, and keywords searched. The collected data is temporarily stored in local storage.

[0048] Step 2:

[0049] The device sends collected operational data to the server at regular intervals or based on event triggers. Secure protocols are used for transmission to protect data integrity and user privacy.

[0050] Step 3:

[0051] The server stores the received operation data in a database. This allows for the management of a long-term history of user purchasing behavior. In the database, the data is organized by user, preparing for quick searching and analysis.

[0052] Step 4:

[0053] The server analyzes user behavior patterns using a generative AI model based on accumulated data. Here, it identifies whether users are repeating similar behaviors or if specific biases exist, based on past purchase and browsing history.

[0054] Step 5:

[0055] The server applies behavioral economics-based algorithms to detect biases that may influence user decisions. Based on the detected biases, it selects advice for the user.

[0056] Step 6:

[0057] Upon receiving analysis results from the server, the device generates a pop-up notification for the user. The notification includes warnings about biases the user may not be aware of and about products similar to past purchases.

[0058] Step 7:

[0059] Based on the pop-up notification, users have the opportunity to re-evaluate their purchasing behavior. Depending on the content of the notification, they can reconsider their purchase or remove items from their shopping cart.

[0060] Step 8:

[0061] Users provide feedback on notifications through their devices. This feedback includes opinions on the system's usefulness and the content of the notifications.

[0062] Step 9:

[0063] The server collects user feedback and uses it to improve the accuracy of the generated AI model and adjust the notification algorithm. This allows the system to continuously improve itself to enhance the user experience.

[0064] (Example 1)

[0065] 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."

[0066] There is a need to reduce excessive spending and unnecessary purchases that users unconsciously make when shopping online, and to improve the transparency of purchasing behavior. However, conventional systems lacked sufficient means to analyze the past behavior patterns of individual users in detail and detect specific purchasing biases. Furthermore, they lacked mechanisms to effectively utilize user feedback to improve the accuracy of the system.

[0067] 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.

[0068] In this invention, the server includes information gathering means for acquiring and storing data related to user operations; behavioral analysis means for analyzing the data using a generated artificial intelligence model and identifying patterns of user behavior; notification means for generating information based on the behavioral patterns and presenting that information to the user; and feedback processing means for receiving feedback from the user and improving the artificial intelligence model and algorithms based on that feedback. This makes it possible to analyze the user's past purchasing behavior in detail, effectively detect and notify of specific purchasing biases, and continuously improve the accuracy of the system by utilizing feedback from the user.

[0069] "Data related to operations" refers to information generated when a user uses an information system, such as user selections, inputs, and browsing.

[0070] An "artificial intelligence model" is a collection of algorithms or programs that can learn patterns from large amounts of data and perform specific tasks.

[0071] "Behavioral patterns" refer to specific behavioral tendencies or habits that a user repeatedly exhibits.

[0072] "Bias" refers to a potential inclination or tendency that influences a user's decision-making.

[0073] A "feedback processing method" is a method or process for receiving opinions and evaluations from users and using them to improve or adjust the system.

[0074] A "notification method" is a method or interface for presenting information to a user.

[0075] "Information gathering means" refers to a system or technology for acquiring data from users and recording and storing it.

[0076] This invention is a system aimed at analyzing users' online purchasing behavior and suppressing unnecessary purchases. The system includes terminals, servers, and multiple software components for them to work together.

[0077] The device acquires data related to user interactions when they use e-commerce websites. This data includes information such as products viewed, purchase history, and session information, and is used to record user behavior in detail. The device temporarily stores this data, encrypts it for security purposes, and then sends it to the server.

[0078] The server receives data sent from the terminal and stores it in a database. Based on the stored data, the server builds a generative AI model. This AI model uses machine learning algorithms to analyze the data and identify user behavior patterns and biases. In this process, the AI ​​model is given prompts such as, "Model purchasing patterns from the user's browsing and purchase history over the past six months."

[0079] Based on the analysis by the AI ​​model, the server detects specific behavioral biases in users. For example, it might reveal a tendency for users to purchase multiple items from a particular brand in a short period of time. Based on this information, the server generates notification information and sends it to the device.

[0080] The device displays notification information received from the server to the user. The notification appears as a pop-up message, providing the user with advice to prevent unnecessary purchases. This gives the user an opportunity to reconsider their needs.

[0081] Furthermore, users can provide feedback on notification content and system improvements through their devices. This feedback is sent to the server and used as foundational data to improve AI models and notification algorithms. As a result, the overall accuracy of the system and the user experience are improved.

[0082] As a concrete example, if a user attempts to purchase the same type of accessory multiple times late at night, the server generates a notification stating, "You already own multiple items of the same category," and displays advice to the user through their device. This helps prevent users from making unnecessary purchases.

[0083] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0084] Step 1:

[0085] The device collects data on user actions on e-commerce sites. This input data includes product information viewed by the user, purchase history, and session information. The device temporarily stores this data and standardizes and encrypts it before sending it to the server as needed. This process prepares a dataset to understand user behavior in as much detail as possible.

[0086] Step 2:

[0087] The server stores the operation data received from the terminal in a database. It saves the entered data and converts it into a structured format for later analysis. The server properly indexes the database and builds a data model to enable efficient queries. This organizes user-specific historical data, allowing for quick access and searching.

[0088] Step 3:

[0089] The server builds a generative AI model based on accumulated data. It uses past user purchase patterns and behavioral history as input data, applying machine learning algorithms to learn behavioral patterns. At this stage, it receives a prompt message instructing it to "model purchase patterns from the user's browsing and purchase history over the past six months." The output is a modeling result showing the user's behavioral trends.

[0090] Step 4:

[0091] The server uses the generated AI model to detect potential biases in users. It uses behavioral patterns derived from the AI ​​model as input and performs analysis based on behavioral economics theory. Specifically, it identifies tendencies such as multiple purchases of the same item in a short period. This results in the generation of data for notifications.

[0092] Step 5:

[0093] The server generates notification information based on detected biases. The identified user behavior trends are used as input data, and the notification content is created as output. This notification message includes advice to help users prevent unnecessary purchases. The generated notification is delivered to the device.

[0094] Step 6:

[0095] The terminal's role is to present notification information received from the server to the user. It receives notification messages as input and displays them as pop-up messages in the user interface. This gives the user an opportunity to carefully reconsider their purchase. This output serves as direct feedback to the user.

[0096] Step 7:

[0097] Users provide feedback on notifications and advice from the system. This feedback is sent to the server via the user's device. This feedback is used to improve the AI ​​model and the overall system. As a result, algorithms are adapted and modified based on the feedback information, continuously improving the system's accuracy.

[0098] (Application Example 1)

[0099] 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."

[0100] When consumers use e-commerce, they often make wasteful purchases based on their past buying history and behavioral patterns, and there is insufficient support for making appropriate purchasing decisions. As a result, they may realize that the items they purchased were not actually necessary. This problem stems from the fact that consumers do not receive effective advice in real time to consciously control their purchasing.

[0101] 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.

[0102] In this invention, the server includes information gathering means, behavioral analysis means, notification means, and evaluation means. This makes it possible to provide consumers with personalized advice in real time based on their past purchasing behavior to prevent them from making unnecessary purchases.

[0103] "Information gathering means" refers to a device or software that is responsible for acquiring and storing user operation data.

[0104] "Behavioral analysis means" refers to a process or function that analyzes operational data acquired using a generative artificial intelligence model to identify user behavior patterns.

[0105] "Notification means" refers to a system or method for presenting notification information to a user, which is generated based on the information obtained as a result of the analysis.

[0106] "Evaluation method" refers to a process or function that analyzes users' purchasing behavior and provides purchasing advice optimized for each individual user.

[0107] A "feedback processing mechanism" is a mechanism that receives feedback from users and utilizes that data to improve the accuracy of artificial intelligence models.

[0108] The following are the embodiments for carrying out the invention.

[0109] This invention is based on a system that combines information gathering means, behavioral analysis means, notification means, and evaluation means. Specifically, the user's terminal collects operation data and transmits it to a server. This data includes past purchase history and browsing information. The server receives this operation data and stores it in a database.

[0110] The server uses machine learning libraries such as Python's TENSORFLOW® or PyTorch to construct a generative artificial intelligence model as a means of behavioral analysis. This model is used to analyze the user's past behavioral patterns and identify their consumption preferences. Once the analysis is complete, an evaluation tool generates personalized advice based on their purchasing tendencies.

[0111] This advice is sent to the user's device via a notification system and presented as a pop-up notification. The notification includes information about whether the user has previously purchased similar products, and the user can refer to this notification before making a purchase. Based on this information, the user can optimize their purchasing decisions.

[0112] The system also includes feedback processing mechanisms to collect user feedback on notification information. The server uses this feedback to improve the accuracy of the AI ​​model and notification algorithms. In other words, continuous improvement is possible, further enhancing the user experience.

[0113] For example, if a user in their 20s has purchased similar accessories multiple times in the past, the server will generate a notification stating "You have previously owned similar accessories" and display it to the user on their device. This allows the user to reconsider whether they need to purchase the product.

[0114] An example of a prompt message is: "Analyze the user's past purchase history and current purchase candidates to identify their purchasing trends and provide advice."

[0115] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0116] Step 1:

[0117] The device monitors user activity and collects activity data, including browsing history, purchase history, and session duration on e-commerce sites. This data is acquired in real time from sensors and trackers and temporarily stored on the device.

[0118] Step 2:

[0119] Operation data is sent from the terminal to the server. The server receives this data and saves it to a database. This allows the user's operation history to be accumulated and made available for later analysis.

[0120] Step 3:

[0121] The server builds a generative AI model using Python's TensorFlow or PyTorch based on the stored operation data. The model uses machine learning algorithms to analyze the user's purchasing patterns and behavioral trends. This analysis identifies the user's consumption preferences.

[0122] Step 4:

[0123] Based on the results analyzed by the generative artificial intelligence model, the server uses evaluation tools to generate advice for the user. This advice is personalized, taking into account the purchase history, and prompts are used in its generation.

[0124] Step 5:

[0125] The server sends the generated advice as notification data to the device. The device receives this notification and displays it to the user as a pop-up message. The user reviews the notification and has the opportunity to reconsider their purchasing decision.

[0126] Step 6:

[0127] Users can provide feedback on displayed notifications. The device collects this feedback and sends it to the server. The server uses the received feedback to improve the AI ​​model and notification algorithms, thereby improving the overall accuracy of the system.

[0128] 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.

[0129] The following describes embodiments for carrying out the present invention. This system not only analyzes the user's purchasing behavior but also integrates an emotion engine that recognizes the user's emotions to provide more personalized notification information.

[0130] First, the device collects real-time operational data when a user visits an e-commerce site. This includes information about the products the user viewed and their browsing history. Simultaneously, it detects and records emotional indicators such as facial expressions, tone of voice, and input speed obtained from the user's webcam and optional microphone sensors as emotional data.

[0131] Next, the server receives operation data and sentiment data transmitted from the terminal and stores it in a database. This allows for the continuous recording of the user's consistent behavior and emotional changes, preparing for later analysis.

[0132] Utilizing a generative AI model, the server analyzes all data to derive specific behavioral patterns and emotional tendencies. Behavioral patterns include purchasing tendencies, frequently viewed genres, and activity at specific times of day. Meanwhile, the emotion engine performs emotional economic analysis to measure the user's emotional state towards specific products.

[0133] The server generates notification information that takes into account the user's specific emotional information. For example, if a user expresses positive emotions towards a particular product, it evaluates whether it is appropriate to make a promotional suggestion.

[0134] The device displays received notification information to the user visually or audibly. This information is customized in tone and content to fit the user's current emotional state, allowing for more empathetic and meaningful advice. This enables users to become more aware of their own emotions and make better purchasing decisions.

[0135] As a concrete example, suppose a user is browsing expensive electronic products late at night, and their emotional data indicates fatigue and a desire to make an impulse purchase. In this case, the server uses this data to provide the user with a discreet suggestion from their device: "Why not think about it overnight before purchasing?" This reduces the risk of making an immediate decision and allows the user to make a more rational product choice.

[0136] This system is expected to make the user's purchasing experience more personalized and rational through emotion recognition, thereby preventing wasteful spending.

[0137] The following describes the processing flow.

[0138] Step 1:

[0139] The device acquires operational data every time the user browses or clicks on an e-commerce site. Furthermore, with the user's permission, it uses the camera and microphone to measure real-time emotional indicators and records emotional data such as facial expressions and voice tone.

[0140] Step 2:

[0141] The device sends operational and emotional data to the server at set intervals. The transmitted data is encrypted from the device to protect user privacy.

[0142] Step 3:

[0143] The server stores received operation data and emotion data in a database. This data is organized for each user, allowing for tracking of emotional changes and behavioral history.

[0144] Step 4:

[0145] The server uses a generative AI model to analyze data stored in the database. This analysis helps to understand user behavior patterns and identify which emotional states are related to purchasing behavior. This process utilizes algorithms based on behavioral economics.

[0146] Step 5:

[0147] When generating notification information based on analysis results, the server takes emotional data into consideration. For example, if a negative emotional state is detected, it prepares a suggestion to encourage the user to reconsider their decision.

[0148] Step 6:

[0149] The device displays a pop-up notification to the user based on notification information received from the server. This notification reflects the user's current emotional state and behavioral patterns and is delivered in an empathetic and personalized format.

[0150] Step 7:

[0151] Through the displayed notifications, users re-evaluate their purchasing decisions based on their emotions. This allows them to make choices that are mindful of their own feelings.

[0152] Step 8:

[0153] Users provide feedback on notifications and emotion recognition features through their devices. This includes opinions on the usefulness of notifications and the accuracy of emotion recognition.

[0154] Step 9:

[0155] The server collects feedback and uses it to improve the algorithms of the generative AI model and emotion engine. Through this process, the system's accuracy and user experience are enhanced.

[0156] (Example 2)

[0157] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0158] Traditional e-commerce systems are limited to general behavioral analysis based on user activity history. This prevents them from providing more personalized notifications and suggestions that take into account the user's emotional state, resulting in an inefficient purchasing experience and potentially leading to impulsive purchases or unsatisfactory shopping experiences. Therefore, there is a need to provide a more appropriate and rational purchasing experience by offering notification information that takes the user's emotional state into account.

[0159] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0160] In this invention, the server includes information gathering means for acquiring and storing user operation data and emotional data; analysis means for analyzing the operation data and emotional data using a generative artificial intelligence model to identify the user's behavior patterns and emotional state; and information generation means for generating personalized notification information for the user based on the behavior patterns and emotional state. This makes it possible to provide more individualized notifications and suggestions that reflect the user's emotional state.

[0161] "Information gathering means" refers to technical means for acquiring and storing user operation data and emotional data.

[0162] "Operation data" refers to data about a user's actions and inputs when using electronic devices or systems.

[0163] "Emotional data" refers to data related to emotions obtained from a user's facial expressions, tone of voice, and other physiological indicators.

[0164] A "generative artificial intelligence model" is a model that uses artificial intelligence to analyze large amounts of data and identify user behavior patterns and emotional states.

[0165] "Analysis means" refers to a method for analyzing acquired operational data and emotional data using a generating artificial intelligence model to identify the user's behavioral patterns and emotional state.

[0166] "Behavioral patterns" refer to data that shows a certain flow or trend of user behavior, such as purchasing behavior or browsing trends.

[0167] "Emotional state" refers to information that indicates the type and intensity of a user's emotions.

[0168] "Information generation means" refers to means for generating appropriate notification information for the user based on analyzed behavioral patterns and emotional states.

[0169] "Personalized notification information" refers to notification content that is tailored to the user based on their individual behavioral patterns and emotions.

[0170] An "information display means" is a technical means of presenting generated notification information to the user.

[0171] This invention is a system that utilizes operational data and emotional data to improve the user's purchasing experience. This system mainly consists of two components: a terminal and a server.

[0172] The device plays a role in collecting operational and sentiment data when users visit e-commerce sites. Specifically, it acquires operational data in real time, including the user's click history and browsing time, through JavaScript® code and browser extensions. Furthermore, after obtaining the user's consent, it uses the webcam and microphone to collect sentiment data such as facial expressions, tone of voice, and typing speed. This data is transmitted to the server using a secure protocol (e.g., HTTPS).

[0173] The server is responsible for storing and analyzing the received operational and emotional data. The data is systematically stored in relational or NoSQL databases in preparation for later analysis. The server uses generative artificial intelligence models to analyze this data. Frameworks such as TensorFlow and PyTorch may be used for analysis. As a result of the analysis, user behavior patterns (e.g., product categories frequently visited at specific times) and emotional states (e.g., positive feelings towards specific products) are identified.

[0174] Based on the analysis results, the server generates notification information optimized for the user. The generated notification information reflects the user's individual emotional state and behavioral patterns. For example, if a user's behavior of browsing high-priced items at night includes emotional data indicating fatigue, a suggestion such as "Why not think about it overnight before purchasing?" might be generated.

[0175] The device presents the generated notification information to the user. Notifications may appear visually as pop-ups or banners, or as audible alerts.

[0176] As a concrete example, a prompt message such as, "Generate a suggestion to notify a user if they are browsing high-priced items at night and are showing signs of anxiety or fatigue," is input into the AI ​​model.

[0177] In this way, personalized notifications are provided while taking into account the user's emotional state, resulting in a more personalized purchasing experience.

[0178] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0179] Step 1:

[0180] The device collects user interaction data while the user is browsing the web. Inputs are browsing actions such as clicks and page views, and outputs are interaction datasets summarizing these actions. The device retrieves this data through JavaScript code and browser extensions, and organizes and stores it in real time.

[0181] Step 2:

[0182] The device collects user emotion data. The input is real-time audio and video captured by a webcam and microphone, and the output is emotion data based on facial expressions and tone of voice. The device processes this data and calculates an emotion index using a facial expression analysis algorithm.

[0183] Step 3:

[0184] The device transmits collected operational and sentiment data to the server via a security protocol. The input is the dataset collected by the device, and the output is the secure data transfer to the server. Asynchronous communication ensures data transmission without compromising the user experience.

[0185] Step 4:

[0186] The server stores received operation data and sentiment data in a database. Input is data sent from the terminal, and output is data stored in a normalized format. A database management system (RDBMS or NoSQL) is used to efficiently manage the data.

[0187] Step 5:

[0188] The server inputs the stored data into a generating AI model for analysis. The input consists of user interaction and emotional data stored in a database, and the output is the analysis of behavioral patterns and emotional states. This analysis utilizes machine learning algorithms, sometimes employing TensorFlow or PyTorch.

[0189] Step 6:

[0190] The server generates user-optimized notification information based on the analysis results. The input is data on behavioral patterns and emotional states, and the output is customized notification information. The generation AI model uses prompt sentences to create personalized messages.

[0191] Step 7:

[0192] The device displays generated notification information to the user. The input is notification information sent from the server, and the output is a visual and auditory notification displayed on the user's screen. Notifications are presented as pop-ups or banners, providing the user with information to aid in their purchasing decisions.

[0193] (Application Example 2)

[0194] 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".

[0195] When users make online purchases, there is a challenge in avoiding irrational, emotion-driven buying and providing more personalized purchasing assistance. Furthermore, there is a need to improve the accuracy of purchasing decisions by presenting notifications that take the user's emotional state into consideration.

[0196] 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.

[0197] In this invention, the server includes data collection means for acquiring and storing user operation information and emotional information; behavior and emotion analysis means for analyzing the operation information and emotional information using a generative artificial intelligence model to identify the user's behavior patterns and emotional state; and emotion adaptation notification means for generating notification information based on the behavior patterns and emotional state and presenting the notification information to the user. This enables the provision of notifications tailored to the user's emotional state, prevents irrational purchasing behavior, and allows for rational purchasing decisions.

[0198] "User operation information" refers to data about a user's actions and choices when using the system.

[0199] "Emotional information" refers to data about a user's emotional state, inferred from their facial expressions, tone of voice, and other factors.

[0200] "Data collection means" refers to a device or process for acquiring and storing user operation information and emotional information.

[0201] A "generative artificial intelligence model" is an algorithm used to analyze large amounts of data and identify specific patterns or trends.

[0202] "Behavioral and emotional analysis means" refers to a device or process for identifying a user's behavioral patterns and emotional states using acquired operational information and emotional information.

[0203] An "emotion-adaptive notification means" is a device or process for generating and presenting appropriate notification information to the user according to the user's behavioral patterns and emotional state.

[0204] The system for implementing this invention consists of a user's terminal, a server, and a processing flow using a generated AI model.

[0205] On the user's device, user operation information and emotional information are acquired in real time using the camera and microphone. Operation information is data related to the user's actions such as selecting or browsing products, while emotional information is data indicating signs of emotion obtained by analyzing facial expressions and tone of voice. This information is transmitted from the device to the server.

[0206] On the server, this information is stored by data collection devices. The stored information is analyzed using a generative artificial intelligence model to estimate the user's behavior patterns and emotional state. This analysis generates specific notification information. This notification information is tailored to the user's emotional state and is sent to the user's terminal via an emotionally adapted notification device. For example, if a user is browsing a particular product and showing interest, a suggestion using a prompt such as "There is a special discount on this product" will be made.

[0207] As a concrete example, consider a situation where a user is browsing expensive electronic devices late at night. If the server analyzes the user's emotional state and determines that they are considering an impulsive purchase, a discreet notification such as, "Why not think about this product overnight?" is displayed. An example of a prompt message is, "Generate special suggestions for products the user is interested in." Such notifications allow users to make calmer and more rational purchasing decisions.

[0208] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0209] Step 1:

[0210] The user's device uses its camera and microphone to collect operational and emotional information in real time and transmit it to the server. Inputs include operational information such as product information the user is viewing and the time of day they are using the device, as well as emotional data analyzed from their voice and facial expressions. This input data is processed to quantify the emotional state. Outputs consist of data packets summarizing this information.

[0211] Step 2:

[0212] The server receives data packets sent from the terminal and stores them in a database using data collection means. In this step, filtering and formatting are performed to maintain data consistency and speed, and the data is converted into a format suitable for analysis. The input is user operation information and sentiment information, and the output is data in a neatly organized format recorded in the server's database.

[0213] Step 3:

[0214] The server analyzes the stored data using a generative artificial intelligence model. Specifically, it identifies user behavior patterns based on operation information and estimates emotional states from emotional information. At this stage, it processes the data through machine learning algorithms to derive the most likely behavioral scenarios and emotional tendencies. The input is the data organized in step 2, and the output is the analysis results showing the user's behavior patterns and emotional states.

[0215] Step 4:

[0216] The server generates notification information based on behavioral patterns and emotional states. This process uses prompts generated by a generative AI model to create the most appropriate communication message for the user. For example, if a user expresses positive feelings towards a product, a notification containing a special offer will be generated. The input is the analysis results from step 3, and the output is a notification message customized for each user.

[0217] Step 5:

[0218] The device receives notification information sent from the server and presents it to the user. The notification is displayed in an appropriate tone and format tailored to the user's current situation. Specific actions include attracting the user's attention through notification pop-ups and audio notifications. The input is the notification information generated in step 4, and the output is the content displayed directly to the user.

[0219] 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.

[0220] 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.

[0221] 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.

[0222] [Second Embodiment]

[0223] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0224] 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.

[0225] 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).

[0226] 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.

[0227] 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.

[0228] 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).

[0229] 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.

[0230] 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.

[0231] 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.

[0232] 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.

[0233] 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.

[0234] 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".

[0235] The following describes embodiments for carrying out the present invention. This invention is a system for analyzing user purchasing behavior and suppressing unnecessary purchases. The system includes data collection means, behavioral analysis means, notification means, and feedback processing means.

[0236] First, the device acquires operational data when the user uses an e-commerce site. This operational data includes information about the products the user viewed, purchase history, and even the time of the session. This allows for a detailed record of the user's behavior.

[0237] Next, the server stores the operation data sent from the terminal in a database. Based on this data, it builds a generative artificial intelligence model. This model is used to analyze the user's past behavior and identify behavioral patterns and biases.

[0238] Based on the behavioral patterns identified by the generated AI model, the server detects potential biases in the user. In this process, behavioral economics theories can be referenced to reveal tendencies such as "having purchased similar products multiple times in the past."

[0239] Subsequently, the device displays notification information based on the analysis results to the user as a pop-up message. This notification includes advice to caution the user against making unnecessary purchases. The user can then use this information to review their purchasing behavior.

[0240] Furthermore, users can provide feedback via their devices regarding notification content and system feedback. This allows the system to receive user feedback, which the server then uses to improve its AI models and notification algorithms. This enables the system to continuously improve accuracy and enrich the user experience.

[0241] As a concrete example, consider a case where a user in their 20s tries to purchase the same type of accessory multiple times late at night. A server that references this user's data generates a notification based on their past similar purchase history, stating, "You have previously owned multiple items of the same type of accessory," and displays it to the user on their device. In response, the user can reconsider their need for the product before purchasing, preventing unnecessary purchases.

[0242] This system helps consumers make wiser decisions by improving transparency in purchasing choices.

[0243] The following describes the processing flow.

[0244] Step 1:

[0245] The device collects real-time data on user activity when visiting e-commerce sites. This includes details of products viewed, time spent on the site, links clicked, and keywords searched. The collected data is temporarily stored in local storage.

[0246] Step 2:

[0247] The device sends collected operational data to the server at regular intervals or based on event triggers. Secure protocols are used for transmission to protect data integrity and user privacy.

[0248] Step 3:

[0249] The server stores the received operation data in a database. This allows for the management of a long-term history of user purchasing behavior. In the database, the data is organized by user, preparing for quick searching and analysis.

[0250] Step 4:

[0251] The server analyzes user behavior patterns using a generative AI model based on accumulated data. Here, it identifies whether users are repeating similar behaviors or if specific biases exist, based on past purchase and browsing history.

[0252] Step 5:

[0253] The server applies behavioral economics-based algorithms to detect biases that may influence user decisions. Based on the detected biases, it selects advice for the user.

[0254] Step 6:

[0255] Upon receiving analysis results from the server, the device generates a pop-up notification for the user. The notification includes warnings about biases the user may not be aware of and about products similar to past purchases.

[0256] Step 7:

[0257] Based on the pop-up notification, users have the opportunity to re-evaluate their purchasing behavior. Depending on the content of the notification, they can reconsider their purchase or remove items from their shopping cart.

[0258] Step 8:

[0259] Users provide feedback on notifications through their devices. This feedback includes opinions on the system's usefulness and the content of the notifications.

[0260] Step 9:

[0261] The server collects user feedback and uses it to improve the accuracy of the generated AI model and adjust the notification algorithm. This allows the system to continuously improve itself to enhance the user experience.

[0262] (Example 1)

[0263] 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."

[0264] There is a need to reduce excessive spending and unnecessary purchases that users unconsciously make when shopping online, and to improve the transparency of purchasing behavior. However, conventional systems lacked sufficient means to analyze the past behavior patterns of individual users in detail and detect specific purchasing biases. Furthermore, they lacked mechanisms to effectively utilize user feedback to improve the accuracy of the system.

[0265] 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.

[0266] In this invention, the server includes information gathering means for acquiring and storing data related to user operations; behavioral analysis means for analyzing the data using a generated artificial intelligence model and identifying patterns of user behavior; notification means for generating information based on the behavioral patterns and presenting that information to the user; and feedback processing means for receiving feedback from the user and improving the artificial intelligence model and algorithms based on that feedback. This makes it possible to analyze the user's past purchasing behavior in detail, effectively detect and notify of specific purchasing biases, and continuously improve the accuracy of the system by utilizing feedback from the user.

[0267] "Data related to operations" refers to information generated when a user uses an information system, such as user selections, inputs, and browsing.

[0268] An "artificial intelligence model" is a collection of algorithms or programs that can learn patterns from large amounts of data and perform specific tasks.

[0269] "Behavioral patterns" refer to specific behavioral tendencies or habits that a user repeatedly exhibits.

[0270] "Bias" refers to a potential inclination or tendency that influences a user's decision-making.

[0271] A "feedback processing method" is a method or process for receiving opinions and evaluations from users and using them to improve or adjust the system.

[0272] A "notification method" is a method or interface for presenting information to a user.

[0273] "Information gathering means" refers to a system or technology for acquiring data from users and recording and storing it.

[0274] This invention is a system aimed at analyzing users' online purchasing behavior and suppressing unnecessary purchases. The system includes terminals, servers, and multiple software components for them to work together.

[0275] The device acquires data related to user interactions when they use e-commerce websites. This data includes information such as products viewed, purchase history, and session information, and is used to record user behavior in detail. The device temporarily stores this data, encrypts it for security purposes, and then sends it to the server.

[0276] The server receives data sent from the terminal and stores it in a database. Based on the stored data, the server builds a generative AI model. This AI model uses machine learning algorithms to analyze the data and identify user behavior patterns and biases. In this process, the AI ​​model is given prompts such as, "Model purchasing patterns from the user's browsing and purchase history over the past six months."

[0277] Based on the analysis by the AI ​​model, the server detects specific behavioral biases in users. For example, it might reveal a tendency for users to purchase multiple items from a particular brand in a short period of time. Based on this information, the server generates notification information and sends it to the device.

[0278] The device displays notification information received from the server to the user. The notification appears as a pop-up message, providing the user with advice to prevent unnecessary purchases. This gives the user an opportunity to reconsider their needs.

[0279] Furthermore, the user can provide feedback on the notification content and system improvements through the terminal. These feedbacks are sent to the server and used as basic data for improving the AI model and notification algorithms. As a result, the accuracy of the entire system and the user experience are improved.

[0280] As a specific example, for a user who attempts to purchase the same type of accessory multiple times at night, the server generates a notification saying "You already own multiple items of the same genre in the past" and advice is displayed to the user through the terminal. This allows the user to prevent unnecessary purchases.

[0281] The flow of the specific process in Example 1 will be described using FIG. 11.

[0282] Step 1:

[0283] The terminal collects data on the operations performed by the user on the e-commerce site. This input data includes product information viewed by the user, purchase history, and session information. The terminal performs processes of standardizing and encrypting the data to temporarily store these data and sequentially transmit them to the server as needed. In this process, a dataset for grasping the user's behavior in as much detail as possible is prepared.

[0284] Step 2:

[0285] The server accumulates the operation data received from the terminal in the database. The input data is saved and converted into a structured format for use in later analysis. The server appropriately indexes the data in the database and constructs a data model so that queries can be performed efficiently. This organizes the historical data for each user and enables quick access and search.

[0286] Step 3:

[0287] The server builds a generative AI model based on accumulated data. It uses past user purchase patterns and behavioral history as input data, applying machine learning algorithms to learn behavioral patterns. At this stage, it receives a prompt message instructing it to "model purchase patterns from the user's browsing and purchase history over the past six months." The output is a modeling result showing the user's behavioral trends.

[0288] Step 4:

[0289] The server uses the generated AI model to detect potential biases in users. It uses behavioral patterns derived from the AI ​​model as input and performs analysis based on behavioral economics theory. Specifically, it identifies tendencies such as multiple purchases of the same item in a short period. This results in the generation of data for notifications.

[0290] Step 5:

[0291] The server generates notification information based on detected biases. The identified user behavior trends are used as input data, and the notification content is created as output. This notification message includes advice to help users prevent unnecessary purchases. The generated notification is delivered to the device.

[0292] Step 6:

[0293] The terminal's role is to present notification information received from the server to the user. It receives notification messages as input and displays them as pop-up messages in the user interface. This gives the user an opportunity to carefully reconsider their purchase. This output serves as direct feedback to the user.

[0294] Step 7:

[0295] Users provide feedback on notifications and advice from the system. This feedback is sent to the server via the user's device. This feedback is used to improve the AI ​​model and the overall system. As a result, algorithms are adapted and modified based on the feedback information, continuously improving the system's accuracy.

[0296] (Application Example 1)

[0297] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0298] When consumers use e-commerce, they often make wasteful purchases based on their past buying history and behavioral patterns, and there is insufficient support for making appropriate purchasing decisions. As a result, they may realize that the items they purchased were not actually necessary. This problem stems from the fact that consumers do not receive effective advice in real time to consciously control their purchasing.

[0299] 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.

[0300] In this invention, the server includes information gathering means, behavioral analysis means, notification means, and evaluation means. This makes it possible to provide consumers with personalized advice in real time based on their past purchasing behavior to prevent them from making unnecessary purchases.

[0301] "Information gathering means" refers to a device or software that is responsible for acquiring and storing user operation data.

[0302] "Behavioral analysis means" refers to a process or function that analyzes operational data acquired using a generative artificial intelligence model to identify user behavior patterns.

[0303] The "notification means" is a system or method for presenting notification information generated based on the information obtained as a result of analysis to the user.

[0304] The "evaluation means" is a process or function that analyzes the purchase behavior of users and provides purchase advice optimized for individual users.

[0305] The "feedback processing means" is a mechanism that receives feedback from users and utilizes that data to improve the accuracy of the artificial intelligence model.

[0306] The mode for carrying out the invention is as follows.

[0307] This invention is based on a system that combines information collection means, behavior analysis means, notification means, and evaluation means. Specifically, the user's terminal collects operation data and transmits it to the server. This data includes past purchase histories and browsing information, etc. The server receives this operation data and stores it in the database.

[0308] As the behavior analysis means, the server constructs an artificial intelligence model using a machine learning library such as Python's TensorFlow or PyTorch, analyzes the user's past behavior patterns using this model, and identifies consumption preferences. When the analysis is performed, the evaluation means generates personalized advice based on the purchase tendency.

[0309] This advice is transmitted to the user's terminal through the notification means and presented as a pop-up notification. The notification includes information when the user has purchased a similar product in the past, and the user can refer to the notification before purchasing. Based on this information, the user can optimize the judgment during consumption.

[0310] The system also includes feedback processing mechanisms to collect user feedback on notification information. The server uses this feedback to improve the accuracy of the AI ​​model and notification algorithms. In other words, continuous improvement is possible, further enhancing the user experience.

[0311] For example, if a user in their 20s has purchased similar accessories multiple times in the past, the server will generate a notification stating "You have previously owned similar accessories" and display it to the user on their device. This allows the user to reconsider whether they need to purchase the product.

[0312] An example of a prompt message is: "Analyze the user's past purchase history and current purchase candidates to identify their purchasing trends and provide advice."

[0313] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0314] Step 1:

[0315] The device monitors user activity and collects activity data, including browsing history, purchase history, and session duration on e-commerce sites. This data is acquired in real time from sensors and trackers and temporarily stored on the device.

[0316] Step 2:

[0317] Operation data is sent from the terminal to the server. The server receives this data and saves it to a database. This allows the user's operation history to be accumulated and made available for later analysis.

[0318] Step 3:

[0319] The server builds a generative AI model using Python's TensorFlow or PyTorch based on the stored operation data. The model uses machine learning algorithms to analyze the user's purchasing patterns and behavioral trends. This analysis identifies the user's consumption preferences.

[0320] Step 4:

[0321] Based on the results analyzed by the generative artificial intelligence model, the server uses evaluation tools to generate advice for the user. This advice is personalized, taking into account the purchase history, and prompts are used in its generation.

[0322] Step 5:

[0323] The server sends the generated advice as notification data to the device. The device receives this notification and displays it to the user as a pop-up message. The user reviews the notification and has the opportunity to reconsider their purchasing decision.

[0324] Step 6:

[0325] Users can provide feedback on displayed notifications. The device collects this feedback and sends it to the server. The server uses the received feedback to improve the AI ​​model and notification algorithms, thereby improving the overall accuracy of the system.

[0326] 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.

[0327] The following describes embodiments for carrying out the present invention. This system not only analyzes the user's purchasing behavior but also integrates an emotion engine that recognizes the user's emotions to provide more personalized notification information.

[0328] First, the device collects real-time operational data when a user visits an e-commerce site. This includes information about the products the user viewed and their browsing history. Simultaneously, it detects and records emotional indicators such as facial expressions, tone of voice, and input speed obtained from the user's webcam and optional microphone sensors as emotional data.

[0329] Next, the server receives operation data and sentiment data transmitted from the terminal and stores it in a database. This allows for the continuous recording of the user's consistent behavior and emotional changes, preparing for later analysis.

[0330] Utilizing a generative AI model, the server analyzes all data to derive specific behavioral patterns and emotional tendencies. Behavioral patterns include purchasing tendencies, frequently viewed genres, and activity at specific times of day. Meanwhile, the emotion engine performs emotional economic analysis to measure the user's emotional state towards specific products.

[0331] The server generates notification information that takes into account the user's specific emotional information. For example, if a user expresses positive emotions towards a particular product, it evaluates whether it is appropriate to make a promotional suggestion.

[0332] The device displays received notification information to the user visually or audibly. This information is customized in tone and content to fit the user's current emotional state, allowing for more empathetic and meaningful advice. This enables users to become more aware of their own emotions and make better purchasing decisions.

[0333] As a concrete example, suppose a user is browsing expensive electronic products late at night, and their emotional data indicates fatigue and a desire to make an impulse purchase. In this case, the server uses this data to provide the user with a discreet suggestion from their device: "Why not think about it overnight before purchasing?" This reduces the risk of making an immediate decision and allows the user to make a more rational product choice.

[0334] This system is expected to make the user's purchasing experience more personalized and rational through emotion recognition, thereby preventing wasteful spending.

[0335] The following describes the processing flow.

[0336] Step 1:

[0337] The device acquires operational data every time the user browses or clicks on an e-commerce site. Furthermore, with the user's permission, it uses the camera and microphone to measure real-time emotional indicators and records emotional data such as facial expressions and voice tone.

[0338] Step 2:

[0339] The device sends operational and emotional data to the server at set intervals. The transmitted data is encrypted from the device to protect user privacy.

[0340] Step 3:

[0341] The server stores received operation data and emotion data in a database. This data is organized for each user, allowing for tracking of emotional changes and behavioral history.

[0342] Step 4:

[0343] The server uses a generative AI model to analyze data stored in the database. This analysis helps to understand user behavior patterns and identify which emotional states are related to purchasing behavior. This process utilizes algorithms based on behavioral economics.

[0344] Step 5:

[0345] When generating notification information based on analysis results, the server takes emotional data into consideration. For example, if a negative emotional state is detected, it prepares a suggestion to encourage the user to reconsider their decision.

[0346] Step 6:

[0347] The device displays a pop-up notification to the user based on notification information received from the server. This notification reflects the user's current emotional state and behavioral patterns and is delivered in an empathetic and personalized format.

[0348] Step 7:

[0349] Through the displayed notifications, users re-evaluate their purchasing decisions based on their emotions. This allows them to make choices that are mindful of their own feelings.

[0350] Step 8:

[0351] Users provide feedback on notifications and emotion recognition features through their devices. This includes opinions on the usefulness of notifications and the accuracy of emotion recognition.

[0352] Step 9:

[0353] The server collects feedback and uses it to improve the algorithms of the generative AI model and emotion engine. Through this process, the system's accuracy and user experience are enhanced.

[0354] (Example 2)

[0355] 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".

[0356] Traditional e-commerce systems are limited to general behavioral analysis based on user activity history. This prevents them from providing more personalized notifications and suggestions that take into account the user's emotional state, resulting in an inefficient purchasing experience and potentially leading to impulsive purchases or unsatisfactory shopping experiences. Therefore, there is a need to provide a more appropriate and rational purchasing experience by offering notification information that takes the user's emotional state into account.

[0357] 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.

[0358] In this invention, the server includes information gathering means for acquiring and storing user operation data and emotional data; analysis means for analyzing the operation data and emotional data using a generative artificial intelligence model to identify the user's behavior patterns and emotional state; and information generation means for generating personalized notification information for the user based on the behavior patterns and emotional state. This makes it possible to provide more individualized notifications and suggestions that reflect the user's emotional state.

[0359] "Information gathering means" refers to technical means for acquiring and storing user operation data and emotional data.

[0360] "Operation data" refers to data about a user's actions and inputs when using electronic devices or systems.

[0361] "Emotional data" refers to data related to emotions obtained from a user's facial expressions, tone of voice, and other physiological indicators.

[0362] A "generative artificial intelligence model" is a model that uses artificial intelligence to analyze large amounts of data and identify user behavior patterns and emotional states.

[0363] "Analysis means" refers to a method for analyzing acquired operational data and emotional data using a generating artificial intelligence model to identify the user's behavioral patterns and emotional state.

[0364] "Behavioral patterns" refer to data that shows a certain flow or trend of user behavior, such as purchasing behavior or browsing trends.

[0365] "Emotional state" refers to information that indicates the type and intensity of a user's emotions.

[0366] "Information generation means" refers to means for generating appropriate notification information for the user based on analyzed behavioral patterns and emotional states.

[0367] "Personalized notification information" refers to notification content that is tailored to the user based on their individual behavioral patterns and emotions.

[0368] An "information display means" is a technical means of presenting generated notification information to the user.

[0369] This invention is a system that utilizes operational data and emotional data to improve the user's purchasing experience. This system mainly consists of two components: a terminal and a server.

[0370] The device plays a role in collecting operational and emotional data when users visit e-commerce sites. Specifically, it acquires operational data in real time, including the user's click history and browsing time, through JavaScript code and browser extensions. Furthermore, after obtaining the user's consent, it uses the webcam and microphone to collect emotional data such as facial expressions, tone of voice, and typing speed. This data is transmitted to the server using a secure protocol (e.g., HTTPS).

[0371] The server is responsible for storing and analyzing the received operational and emotional data. The data is systematically stored in relational or NoSQL databases in preparation for later analysis. The server uses generative artificial intelligence models to analyze this data. Frameworks such as TensorFlow and PyTorch may be used for analysis. As a result of the analysis, user behavior patterns (e.g., product categories frequently visited at specific times) and emotional states (e.g., positive feelings towards specific products) are identified.

[0372] Based on the analysis results, the server generates notification information optimized for the user. The generated notification information reflects the user's individual emotional state and behavioral patterns. For example, if a user's behavior of browsing high-priced items at night includes emotional data indicating fatigue, a suggestion such as "Why not think about it overnight before purchasing?" might be generated.

[0373] The device presents the generated notification information to the user. Notifications may appear visually as pop-ups or banners, or as audible alerts.

[0374] As a concrete example, a prompt message such as, "Generate a suggestion to notify a user if they are browsing high-priced items at night and are showing signs of anxiety or fatigue," is input into the AI ​​model.

[0375] In this way, personalized notifications are provided while taking into account the user's emotional state, resulting in a more personalized purchasing experience.

[0376] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0377] Step 1:

[0378] The device collects user interaction data while the user is browsing the web. Inputs are browsing actions such as clicks and page views, and outputs are interaction datasets summarizing these actions. The device retrieves this data through JavaScript code and browser extensions, and organizes and stores it in real time.

[0379] Step 2:

[0380] The device collects user emotion data. The input is real-time audio and video captured by a webcam and microphone, and the output is emotion data based on facial expressions and tone of voice. The device processes this data and calculates an emotion index using a facial expression analysis algorithm.

[0381] Step 3:

[0382] The device transmits collected operational and sentiment data to the server via a security protocol. The input is the dataset collected by the device, and the output is the secure data transfer to the server. Asynchronous communication ensures data transmission without compromising the user experience.

[0383] Step 4:

[0384] The server stores received operation data and sentiment data in a database. Input is data sent from the terminal, and output is data stored in a normalized format. A database management system (RDBMS or NoSQL) is used to efficiently manage the data.

[0385] Step 5:

[0386] The server inputs the stored data into a generating AI model for analysis. The input consists of user interaction and emotional data stored in a database, and the output is the analysis of behavioral patterns and emotional states. This analysis utilizes machine learning algorithms, sometimes employing TensorFlow or PyTorch.

[0387] Step 6:

[0388] The server generates user-optimized notification information based on the analysis results. The input is data on behavioral patterns and emotional states, and the output is customized notification information. The generation AI model uses prompt sentences to create personalized messages.

[0389] Step 7:

[0390] The device displays generated notification information to the user. The input is notification information sent from the server, and the output is a visual and auditory notification displayed on the user's screen. Notifications are presented as pop-ups or banners, providing the user with information to aid in their purchasing decisions.

[0391] (Application Example 2)

[0392] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0393] When users make online purchases, there is a challenge in avoiding irrational, emotion-driven buying and providing more personalized purchasing assistance. Furthermore, there is a need to improve the accuracy of purchasing decisions by presenting notifications that take the user's emotional state into consideration.

[0394] 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.

[0395] In this invention, the server includes data collection means for acquiring and storing user operation information and emotional information; behavior and emotion analysis means for analyzing the operation information and emotional information using a generative artificial intelligence model to identify the user's behavior patterns and emotional state; and emotion adaptation notification means for generating notification information based on the behavior patterns and emotional state and presenting the notification information to the user. This enables the provision of notifications tailored to the user's emotional state, prevents irrational purchasing behavior, and allows for rational purchasing decisions.

[0396] "User operation information" refers to data about a user's actions and choices when using the system.

[0397] "Emotional information" refers to data about a user's emotional state, inferred from their facial expressions, tone of voice, and other factors.

[0398] "Data collection means" refers to a device or process for acquiring and storing user operation information and emotional information.

[0399] A "generative artificial intelligence model" is an algorithm used to analyze large amounts of data and identify specific patterns or trends.

[0400] "Behavioral and emotional analysis means" refers to a device or process for identifying a user's behavioral patterns and emotional states using acquired operational information and emotional information.

[0401] An "emotion-adaptive notification means" is a device or process for generating and presenting appropriate notification information to the user according to the user's behavioral patterns and emotional state.

[0402] The system for implementing this invention consists of a user's terminal, a server, and a processing flow using a generated AI model.

[0403] On the user's device, user operation information and emotional information are acquired in real time using the camera and microphone. Operation information is data related to the user's actions such as selecting or browsing products, while emotional information is data indicating signs of emotion obtained by analyzing facial expressions and tone of voice. This information is transmitted from the device to the server.

[0404] On the server, this information is stored by data collection devices. The stored information is analyzed using a generative artificial intelligence model to estimate the user's behavior patterns and emotional state. This analysis generates specific notification information. This notification information is tailored to the user's emotional state and is sent to the user's terminal via an emotionally adapted notification device. For example, if a user is browsing a particular product and showing interest, a suggestion using a prompt such as "There is a special discount on this product" will be made.

[0405] As a concrete example, consider a situation where a user is browsing expensive electronic devices late at night. If the server analyzes the user's emotional state and determines that they are considering an impulsive purchase, a discreet notification such as, "Why not think about this product overnight?" is displayed. An example of a prompt message is, "Generate special suggestions for products the user is interested in." Such notifications allow users to make calmer and more rational purchasing decisions.

[0406] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0407] Step 1:

[0408] The user's device uses its camera and microphone to collect operational and emotional information in real time and transmit it to the server. Inputs include operational information such as product information the user is viewing and the time of day they are using the device, as well as emotional data analyzed from their voice and facial expressions. This input data is processed to quantify the emotional state. Outputs consist of data packets summarizing this information.

[0409] Step 2:

[0410] The server receives data packets sent from the terminal and stores them in a database using data collection means. In this step, filtering and formatting are performed to maintain data consistency and speed, and the data is converted into a format suitable for analysis. The input is user operation information and sentiment information, and the output is data in a neatly organized format recorded in the server's database.

[0411] Step 3:

[0412] The server analyzes the stored data using a generative artificial intelligence model. Specifically, it identifies user behavior patterns based on operation information and estimates emotional states from emotional information. At this stage, it processes the data through machine learning algorithms to derive the most likely behavioral scenarios and emotional tendencies. The input is the data organized in step 2, and the output is the analysis results showing the user's behavior patterns and emotional states.

[0413] Step 4:

[0414] The server generates notification information based on behavioral patterns and emotional states. This process uses prompts generated by a generative AI model to create the most appropriate communication message for the user. For example, if a user expresses positive feelings towards a product, a notification containing a special offer will be generated. The input is the analysis results from step 3, and the output is a notification message customized for each user.

[0415] Step 5:

[0416] The device receives notification information sent from the server and presents it to the user. The notification is displayed in an appropriate tone and format tailored to the user's current situation. Specific actions include attracting the user's attention through notification pop-ups and audio notifications. The input is the notification information generated in step 4, and the output is the content displayed directly to the user.

[0417] 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.

[0418] 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.

[0419] 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.

[0420] [Third Embodiment]

[0421] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0422] 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.

[0423] 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).

[0424] 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.

[0425] 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.

[0426] 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).

[0427] 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.

[0428] 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.

[0429] 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.

[0430] 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.

[0431] 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.

[0432] 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".

[0433] The following describes embodiments for carrying out the present invention. This invention is a system for analyzing user purchasing behavior and suppressing unnecessary purchases. The system includes data collection means, behavioral analysis means, notification means, and feedback processing means.

[0434] First, the device acquires operational data when the user uses an e-commerce site. This operational data includes information about the products the user viewed, purchase history, and even the time of the session. This allows for a detailed record of the user's behavior.

[0435] Next, the server stores the operation data sent from the terminal in a database. Based on this data, it builds a generative artificial intelligence model. This model is used to analyze the user's past behavior and identify behavioral patterns and biases.

[0436] Based on the behavioral patterns identified by the generated AI model, the server detects potential biases in the user. In this process, behavioral economics theories can be referenced to reveal tendencies such as "having purchased similar products multiple times in the past."

[0437] Subsequently, the device displays notification information based on the analysis results to the user as a pop-up message. This notification includes advice to caution the user against making unnecessary purchases. The user can then use this information to review their purchasing behavior.

[0438] Furthermore, users can provide feedback via their devices regarding notification content and system feedback. This allows the system to receive user feedback, which the server then uses to improve its AI models and notification algorithms. This enables the system to continuously improve accuracy and enrich the user experience.

[0439] As a concrete example, consider a case where a user in their 20s tries to purchase the same type of accessory multiple times late at night. A server that references this user's data generates a notification based on their past similar purchase history, stating, "You have previously owned multiple items of the same type of accessory," and displays it to the user on their device. In response, the user can reconsider their need for the product before purchasing, preventing unnecessary purchases.

[0440] This system helps consumers make wiser decisions by improving transparency in purchasing choices.

[0441] The following describes the processing flow.

[0442] Step 1:

[0443] The device collects real-time data on user activity when visiting e-commerce sites. This includes details of products viewed, time spent on the site, links clicked, and keywords searched. The collected data is temporarily stored in local storage.

[0444] Step 2:

[0445] The device sends collected operational data to the server at regular intervals or based on event triggers. Secure protocols are used for transmission to protect data integrity and user privacy.

[0446] Step 3:

[0447] The server stores the received operation data in a database. This allows for the management of a long-term history of user purchasing behavior. In the database, the data is organized by user, preparing for quick searching and analysis.

[0448] Step 4:

[0449] The server analyzes user behavior patterns using a generative AI model based on accumulated data. Here, it identifies whether users are repeating similar behaviors or if specific biases exist, based on past purchase and browsing history.

[0450] Step 5:

[0451] The server applies behavioral economics-based algorithms to detect biases that may influence user decisions. Based on the detected biases, it selects advice for the user.

[0452] Step 6:

[0453] Upon receiving analysis results from the server, the device generates a pop-up notification for the user. The notification includes warnings about biases the user may not be aware of and about products similar to past purchases.

[0454] Step 7:

[0455] Based on the pop-up notification, users have the opportunity to re-evaluate their purchasing behavior. Depending on the content of the notification, they can reconsider their purchase or remove items from their shopping cart.

[0456] Step 8:

[0457] Users provide feedback on notifications through their devices. This feedback includes opinions on the system's usefulness and the content of the notifications.

[0458] Step 9:

[0459] The server collects user feedback and uses it to improve the accuracy of the generated AI model and adjust the notification algorithm. This allows the system to continuously improve itself to enhance the user experience.

[0460] (Example 1)

[0461] 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."

[0462] There is a need to reduce excessive spending and unnecessary purchases that users unconsciously make when shopping online, and to improve the transparency of purchasing behavior. However, conventional systems lacked sufficient means to analyze the past behavior patterns of individual users in detail and detect specific purchasing biases. Furthermore, they lacked mechanisms to effectively utilize user feedback to improve the accuracy of the system.

[0463] 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.

[0464] In this invention, the server includes information gathering means for acquiring and storing data related to user operations; behavioral analysis means for analyzing the data using a generated artificial intelligence model and identifying patterns of user behavior; notification means for generating information based on the behavioral patterns and presenting that information to the user; and feedback processing means for receiving feedback from the user and improving the artificial intelligence model and algorithms based on that feedback. This makes it possible to analyze the user's past purchasing behavior in detail, effectively detect and notify of specific purchasing biases, and continuously improve the accuracy of the system by utilizing feedback from the user.

[0465] "Data related to operations" refers to information generated when a user uses an information system, such as user selections, inputs, and browsing.

[0466] An "artificial intelligence model" is a collection of algorithms or programs that can learn patterns from large amounts of data and perform specific tasks.

[0467] "Behavioral patterns" refer to specific behavioral tendencies or habits that a user repeatedly exhibits.

[0468] "Bias" refers to a potential inclination or tendency that influences a user's decision-making.

[0469] A "feedback processing method" is a method or process for receiving opinions and evaluations from users and using them to improve or adjust the system.

[0470] A "notification method" is a method or interface for presenting information to a user.

[0471] "Information gathering means" refers to a system or technology for acquiring data from users and recording and storing it.

[0472] This invention is a system aimed at analyzing users' online purchasing behavior and suppressing unnecessary purchases. The system includes terminals, servers, and multiple software components for them to work together.

[0473] The device acquires data related to user interactions when they use e-commerce websites. This data includes information such as products viewed, purchase history, and session information, and is used to record user behavior in detail. The device temporarily stores this data, encrypts it for security purposes, and then sends it to the server.

[0474] The server receives data sent from the terminal and stores it in a database. Based on the stored data, the server builds a generative AI model. This AI model uses machine learning algorithms to analyze the data and identify user behavior patterns and biases. In this process, the AI ​​model is given prompts such as, "Model purchasing patterns from the user's browsing and purchase history over the past six months."

[0475] Based on the analysis by the AI ​​model, the server detects specific behavioral biases in users. For example, it might reveal a tendency for users to purchase multiple items from a particular brand in a short period of time. Based on this information, the server generates notification information and sends it to the device.

[0476] The device displays notification information received from the server to the user. The notification appears as a pop-up message, providing the user with advice to prevent unnecessary purchases. This gives the user an opportunity to reconsider their needs.

[0477] Furthermore, users can provide feedback on notification content and system improvements through their devices. This feedback is sent to the server and used as foundational data to improve AI models and notification algorithms. As a result, the overall accuracy of the system and the user experience are improved.

[0478] As a concrete example, if a user attempts to purchase the same type of accessory multiple times late at night, the server generates a notification stating, "You already own multiple items of the same category," and displays advice to the user through their device. This helps prevent users from making unnecessary purchases.

[0479] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0480] Step 1:

[0481] The device collects data on user actions on e-commerce sites. This input data includes product information viewed by the user, purchase history, and session information. The device temporarily stores this data and standardizes and encrypts it before sending it to the server as needed. This process prepares a dataset to understand user behavior in as much detail as possible.

[0482] Step 2:

[0483] The server stores the operation data received from the terminal in a database. It saves the entered data and converts it into a structured format for later analysis. The server properly indexes the database and builds a data model to enable efficient queries. This organizes user-specific historical data, allowing for quick access and searching.

[0484] Step 3:

[0485] The server builds a generative AI model based on accumulated data. It uses past user purchase patterns and behavioral history as input data, applying machine learning algorithms to learn behavioral patterns. At this stage, it receives a prompt message instructing it to "model purchase patterns from the user's browsing and purchase history over the past six months." The output is a modeling result showing the user's behavioral trends.

[0486] Step 4:

[0487] The server uses the generated AI model to detect potential biases in users. It uses behavioral patterns derived from the AI ​​model as input and performs analysis based on behavioral economics theory. Specifically, it identifies tendencies such as multiple purchases of the same item in a short period. This results in the generation of data for notifications.

[0488] Step 5:

[0489] The server generates notification information based on detected biases. The identified user behavior trends are used as input data, and the notification content is created as output. This notification message includes advice to help users prevent unnecessary purchases. The generated notification is delivered to the device.

[0490] Step 6:

[0491] The terminal's role is to present notification information received from the server to the user. It receives notification messages as input and displays them as pop-up messages in the user interface. This gives the user an opportunity to carefully reconsider their purchase. This output serves as direct feedback to the user.

[0492] Step 7:

[0493] Users provide feedback on notifications and advice from the system. This feedback is sent to the server via the user's device. This feedback is used to improve the AI ​​model and the overall system. As a result, algorithms are adapted and modified based on the feedback information, continuously improving the system's accuracy.

[0494] (Application Example 1)

[0495] 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."

[0496] When consumers use e-commerce, they often make wasteful purchases based on their past buying history and behavioral patterns, and there is insufficient support for making appropriate purchasing decisions. As a result, they may realize that the items they purchased were not actually necessary. This problem stems from the fact that consumers do not receive effective advice in real time to consciously control their purchasing.

[0497] 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.

[0498] In this invention, the server includes information gathering means, behavioral analysis means, notification means, and evaluation means. This makes it possible to provide consumers with personalized advice in real time based on their past purchasing behavior to prevent them from making unnecessary purchases.

[0499] "Information gathering means" refers to a device or software that is responsible for acquiring and storing user operation data.

[0500] "Behavioral analysis means" refers to a process or function that analyzes operational data acquired using a generative artificial intelligence model to identify user behavior patterns.

[0501] "Notification means" refers to a system or method for presenting notification information to a user, which is generated based on the information obtained as a result of the analysis.

[0502] "Evaluation method" refers to a process or function that analyzes users' purchasing behavior and provides purchasing advice optimized for each individual user.

[0503] A "feedback processing mechanism" is a mechanism that receives feedback from users and utilizes that data to improve the accuracy of artificial intelligence models.

[0504] The following are the embodiments for carrying out the invention.

[0505] This invention is based on a system that combines information gathering means, behavioral analysis means, notification means, and evaluation means. Specifically, the user's terminal collects operation data and transmits it to a server. This data includes past purchase history and browsing information. The server receives this operation data and stores it in a database.

[0506] The server uses machine learning libraries such as TensorFlow or PyTorch in Python to build a generative artificial intelligence model as a means of behavioral analysis. This model is used to analyze the user's past behavioral patterns and identify their consumption preferences. Once the analysis is complete, an evaluation tool generates personalized advice based on their purchasing tendencies.

[0507] This advice is sent to the user's device via a notification system and presented as a pop-up notification. The notification includes information about whether the user has previously purchased similar products, and the user can refer to this notification before making a purchase. Based on this information, the user can optimize their purchasing decisions.

[0508] The system also includes feedback processing mechanisms to collect user feedback on notification information. The server uses this feedback to improve the accuracy of the AI ​​model and notification algorithms. In other words, continuous improvement is possible, further enhancing the user experience.

[0509] For example, if a user in their 20s has purchased similar accessories multiple times in the past, the server will generate a notification stating "You have previously owned similar accessories" and display it to the user on their device. This allows the user to reconsider whether they need to purchase the product.

[0510] An example of a prompt message is: "Analyze the user's past purchase history and current purchase candidates to identify their purchasing trends and provide advice."

[0511] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0512] Step 1:

[0513] The device monitors user activity and collects activity data, including browsing history, purchase history, and session duration on e-commerce sites. This data is acquired in real time from sensors and trackers and temporarily stored on the device.

[0514] Step 2:

[0515] Operation data is sent from the terminal to the server. The server receives this data and saves it to a database. This allows the user's operation history to be accumulated and made available for later analysis.

[0516] Step 3:

[0517] The server builds a generative AI model using Python's TensorFlow or PyTorch based on the stored operation data. The model uses machine learning algorithms to analyze the user's purchasing patterns and behavioral trends. This analysis identifies the user's consumption preferences.

[0518] Step 4:

[0519] Based on the results analyzed by the generative artificial intelligence model, the server uses evaluation tools to generate advice for the user. This advice is personalized, taking into account the purchase history, and prompts are used in its generation.

[0520] Step 5:

[0521] The server sends the generated advice as notification data to the device. The device receives this notification and displays it to the user as a pop-up message. The user reviews the notification and has the opportunity to reconsider their purchasing decision.

[0522] Step 6:

[0523] Users can provide feedback on displayed notifications. The device collects this feedback and sends it to the server. The server uses the received feedback to improve the AI ​​model and notification algorithms, thereby improving the overall accuracy of the system.

[0524] 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.

[0525] The following describes embodiments for carrying out the present invention. This system not only analyzes the user's purchasing behavior but also integrates an emotion engine that recognizes the user's emotions to provide more personalized notification information.

[0526] First, the device collects real-time operational data when a user visits an e-commerce site. This includes information about the products the user viewed and their browsing history. Simultaneously, it detects and records emotional indicators such as facial expressions, tone of voice, and input speed obtained from the user's webcam and optional microphone sensors as emotional data.

[0527] Next, the server receives operation data and sentiment data transmitted from the terminal and stores it in a database. This allows for the continuous recording of the user's consistent behavior and emotional changes, preparing for later analysis.

[0528] Utilizing a generative AI model, the server analyzes all data to derive specific behavioral patterns and emotional tendencies. Behavioral patterns include purchasing tendencies, frequently viewed genres, and activity at specific times of day. Meanwhile, the emotion engine performs emotional economic analysis to measure the user's emotional state towards specific products.

[0529] The server generates notification information that takes into account the user's specific emotional information. For example, if a user expresses positive emotions towards a particular product, it evaluates whether it is appropriate to make a promotional suggestion.

[0530] The device displays received notification information to the user visually or audibly. This information is customized in tone and content to fit the user's current emotional state, allowing for more empathetic and meaningful advice. This enables users to become more aware of their own emotions and make better purchasing decisions.

[0531] As a concrete example, suppose a user is browsing expensive electronic products late at night, and their emotional data indicates fatigue and a desire to make an impulse purchase. In this case, the server uses this data to provide the user with a discreet suggestion from their device: "Why not think about it overnight before purchasing?" This reduces the risk of making an immediate decision and allows the user to make a more rational product choice.

[0532] This system is expected to make the user's purchasing experience more personalized and rational through emotion recognition, thereby preventing wasteful spending.

[0533] The following describes the processing flow.

[0534] Step 1:

[0535] The device acquires operational data every time the user browses or clicks on an e-commerce site. Furthermore, with the user's permission, it uses the camera and microphone to measure real-time emotional indicators and records emotional data such as facial expressions and voice tone.

[0536] Step 2:

[0537] The device sends operational and emotional data to the server at set intervals. The transmitted data is encrypted from the device to protect user privacy.

[0538] Step 3:

[0539] The server stores received operation data and emotion data in a database. This data is organized for each user, allowing for tracking of emotional changes and behavioral history.

[0540] Step 4:

[0541] The server uses a generative AI model to analyze data stored in the database. This analysis helps to understand user behavior patterns and identify which emotional states are related to purchasing behavior. This process utilizes algorithms based on behavioral economics.

[0542] Step 5:

[0543] When generating notification information based on analysis results, the server takes emotional data into consideration. For example, if a negative emotional state is detected, it prepares a suggestion to encourage the user to reconsider their decision.

[0544] Step 6:

[0545] The device displays a pop-up notification to the user based on notification information received from the server. This notification reflects the user's current emotional state and behavioral patterns and is delivered in an empathetic and personalized format.

[0546] Step 7:

[0547] Through the displayed notifications, users re-evaluate their purchasing decisions based on their emotions. This allows them to make choices that are mindful of their own feelings.

[0548] Step 8:

[0549] Users provide feedback on notifications and emotion recognition features through their devices. This includes opinions on the usefulness of notifications and the accuracy of emotion recognition.

[0550] Step 9:

[0551] The server collects feedback and uses it to improve the algorithms of the generative AI model and emotion engine. Through this process, the system's accuracy and user experience are enhanced.

[0552] (Example 2)

[0553] 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."

[0554] Traditional e-commerce systems are limited to general behavioral analysis based on user activity history. This prevents them from providing more personalized notifications and suggestions that take into account the user's emotional state, resulting in an inefficient purchasing experience and potentially leading to impulsive purchases or unsatisfactory shopping experiences. Therefore, there is a need to provide a more appropriate and rational purchasing experience by offering notification information that takes the user's emotional state into account.

[0555] 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.

[0556] In this invention, the server includes information gathering means for acquiring and storing user operation data and emotional data; analysis means for analyzing the operation data and emotional data using a generative artificial intelligence model to identify the user's behavior patterns and emotional state; and information generation means for generating personalized notification information for the user based on the behavior patterns and emotional state. This makes it possible to provide more individualized notifications and suggestions that reflect the user's emotional state.

[0557] "Information gathering means" refers to technical means for acquiring and storing user operation data and emotional data.

[0558] "Operation data" refers to data about a user's actions and inputs when using electronic devices or systems.

[0559] "Emotional data" refers to data related to emotions obtained from a user's facial expressions, tone of voice, and other physiological indicators.

[0560] A "generative artificial intelligence model" is a model that uses artificial intelligence to analyze large amounts of data and identify user behavior patterns and emotional states.

[0561] "Analysis means" refers to a method for analyzing acquired operational data and emotional data using a generating artificial intelligence model to identify the user's behavioral patterns and emotional state.

[0562] "Behavioral patterns" refer to data that shows a certain flow or trend of user behavior, such as purchasing behavior or browsing trends.

[0563] "Emotional state" refers to information that indicates the type and intensity of a user's emotions.

[0564] "Information generation means" refers to means for generating appropriate notification information for the user based on analyzed behavioral patterns and emotional states.

[0565] "Personalized notification information" refers to notification content that is tailored to the user based on their individual behavioral patterns and emotions.

[0566] An "information display means" is a technical means of presenting generated notification information to the user.

[0567] This invention is a system that utilizes operational data and emotional data to improve the user's purchasing experience. This system mainly consists of two components: a terminal and a server.

[0568] The device plays a role in collecting operational and emotional data when users visit e-commerce sites. Specifically, it acquires operational data in real time, including the user's click history and browsing time, through JavaScript code and browser extensions. Furthermore, after obtaining the user's consent, it uses the webcam and microphone to collect emotional data such as facial expressions, tone of voice, and typing speed. This data is transmitted to the server using a secure protocol (e.g., HTTPS).

[0569] The server is responsible for storing and analyzing the received operational and emotional data. The data is systematically stored in relational or NoSQL databases in preparation for later analysis. The server uses generative artificial intelligence models to analyze this data. Frameworks such as TensorFlow and PyTorch may be used for analysis. As a result of the analysis, user behavior patterns (e.g., product categories frequently visited at specific times) and emotional states (e.g., positive feelings towards specific products) are identified.

[0570] Based on the analysis results, the server generates notification information optimized for the user. The generated notification information reflects the user's individual emotional state and behavioral patterns. For example, if a user's behavior of browsing high-priced items at night includes emotional data indicating fatigue, a suggestion such as "Why not think about it overnight before purchasing?" might be generated.

[0571] The device presents the generated notification information to the user. Notifications may appear visually as pop-ups or banners, or as audible alerts.

[0572] As a concrete example, a prompt message such as, "Generate a suggestion to notify a user if they are browsing high-priced items at night and are showing signs of anxiety or fatigue," is input into the AI ​​model.

[0573] In this way, personalized notifications are provided while taking into account the user's emotional state, resulting in a more personalized purchasing experience.

[0574] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0575] Step 1:

[0576] The device collects user interaction data while the user is browsing the web. Inputs are browsing actions such as clicks and page views, and outputs are interaction datasets summarizing these actions. The device retrieves this data through JavaScript code and browser extensions, and organizes and stores it in real time.

[0577] Step 2:

[0578] The device collects user emotion data. The input is real-time audio and video captured by a webcam and microphone, and the output is emotion data based on facial expressions and tone of voice. The device processes this data and calculates an emotion index using a facial expression analysis algorithm.

[0579] Step 3:

[0580] The device transmits collected operational and sentiment data to the server via a security protocol. The input is the dataset collected by the device, and the output is the secure data transfer to the server. Asynchronous communication ensures data transmission without compromising the user experience.

[0581] Step 4:

[0582] The server stores received operation data and sentiment data in a database. Input is data sent from the terminal, and output is data stored in a normalized format. A database management system (RDBMS or NoSQL) is used to efficiently manage the data.

[0583] Step 5:

[0584] The server inputs the stored data into a generating AI model for analysis. The input consists of user interaction and emotional data stored in a database, and the output is the analysis of behavioral patterns and emotional states. This analysis utilizes machine learning algorithms, sometimes employing TensorFlow or PyTorch.

[0585] Step 6:

[0586] The server generates user-optimized notification information based on the analysis results. The input is data on behavioral patterns and emotional states, and the output is customized notification information. The generation AI model uses prompt sentences to create personalized messages.

[0587] Step 7:

[0588] The device displays generated notification information to the user. The input is notification information sent from the server, and the output is a visual and auditory notification displayed on the user's screen. Notifications are presented as pop-ups or banners, providing the user with information to aid in their purchasing decisions.

[0589] (Application Example 2)

[0590] 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."

[0591] When users make online purchases, there is a challenge in avoiding irrational, emotion-driven buying and providing more personalized purchasing assistance. Furthermore, there is a need to improve the accuracy of purchasing decisions by presenting notifications that take the user's emotional state into consideration.

[0592] 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.

[0593] In this invention, the server includes data collection means for acquiring and storing user operation information and emotional information; behavior and emotion analysis means for analyzing the operation information and emotional information using a generative artificial intelligence model to identify the user's behavior patterns and emotional state; and emotion adaptation notification means for generating notification information based on the behavior patterns and emotional state and presenting the notification information to the user. This enables the provision of notifications tailored to the user's emotional state, prevents irrational purchasing behavior, and allows for rational purchasing decisions.

[0594] "User operation information" refers to data about a user's actions and choices when using the system.

[0595] "Emotional information" refers to data about a user's emotional state, inferred from their facial expressions, tone of voice, and other factors.

[0596] "Data collection means" refers to a device or process for acquiring and storing user operation information and emotional information.

[0597] A "generative artificial intelligence model" is an algorithm used to analyze large amounts of data and identify specific patterns or trends.

[0598] "Behavioral and emotional analysis means" refers to a device or process for identifying a user's behavioral patterns and emotional states using acquired operational information and emotional information.

[0599] An "emotion-adaptive notification means" is a device or process for generating and presenting appropriate notification information to the user according to the user's behavioral patterns and emotional state.

[0600] The system for implementing this invention consists of a user's terminal, a server, and a processing flow using a generated AI model.

[0601] On the user's device, user operation information and emotional information are acquired in real time using the camera and microphone. Operation information is data related to the user's actions such as selecting or browsing products, while emotional information is data indicating signs of emotion obtained by analyzing facial expressions and tone of voice. This information is transmitted from the device to the server.

[0602] On the server, this information is stored by data collection devices. The stored information is analyzed using a generative artificial intelligence model to estimate the user's behavior patterns and emotional state. This analysis generates specific notification information. This notification information is tailored to the user's emotional state and is sent to the user's terminal via an emotionally adapted notification device. For example, if a user is browsing a particular product and showing interest, a suggestion using a prompt such as "There is a special discount on this product" will be made.

[0603] As a concrete example, consider a situation where a user is browsing expensive electronic devices late at night. If the server analyzes the user's emotional state and determines that they are considering an impulsive purchase, a discreet notification such as, "Why not think about this product overnight?" is displayed. An example of a prompt message is, "Generate special suggestions for products the user is interested in." Such notifications allow users to make calmer and more rational purchasing decisions.

[0604] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0605] Step 1:

[0606] The user's device uses its camera and microphone to collect operational and emotional information in real time and transmit it to the server. Inputs include operational information such as product information the user is viewing and the time of day they are using the device, as well as emotional data analyzed from their voice and facial expressions. This input data is processed to quantify the emotional state. Outputs consist of data packets summarizing this information.

[0607] Step 2:

[0608] The server receives data packets sent from the terminal and stores them in a database using data collection means. In this step, filtering and formatting are performed to maintain data consistency and speed, and the data is converted into a format suitable for analysis. The input is user operation information and sentiment information, and the output is data in a neatly organized format recorded in the server's database.

[0609] Step 3:

[0610] The server analyzes the stored data using a generative artificial intelligence model. Specifically, it identifies user behavior patterns based on operation information and estimates emotional states from emotional information. At this stage, it processes the data through machine learning algorithms to derive the most likely behavioral scenarios and emotional tendencies. The input is the data organized in step 2, and the output is the analysis results showing the user's behavior patterns and emotional states.

[0611] Step 4:

[0612] The server generates notification information based on behavioral patterns and emotional states. This process uses prompts generated by a generative AI model to create the most appropriate communication message for the user. For example, if a user expresses positive feelings towards a product, a notification containing a special offer will be generated. The input is the analysis results from step 3, and the output is a notification message customized for each user.

[0613] Step 5:

[0614] The device receives notification information sent from the server and presents it to the user. The notification is displayed in an appropriate tone and format tailored to the user's current situation. Specific actions include attracting the user's attention through notification pop-ups and audio notifications. The input is the notification information generated in step 4, and the output is the content displayed directly to the user.

[0615] 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.

[0616] 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.

[0617] 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.

[0618] [Fourth Embodiment]

[0619] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0620] 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.

[0621] 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).

[0622] 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.

[0623] 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.

[0624] 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).

[0625] 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.

[0626] 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.

[0627] 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.

[0628] 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.

[0629] 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.

[0630] 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.

[0631] 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".

[0632] The following describes embodiments for carrying out the present invention. This invention is a system for analyzing user purchasing behavior and suppressing unnecessary purchases. The system includes data collection means, behavioral analysis means, notification means, and feedback processing means.

[0633] First, the device acquires operational data when the user uses an e-commerce site. This operational data includes information about the products the user viewed, purchase history, and even the time of the session. This allows for a detailed record of the user's behavior.

[0634] Next, the server stores the operation data sent from the terminal in a database. Based on this data, it builds a generative artificial intelligence model. This model is used to analyze the user's past behavior and identify behavioral patterns and biases.

[0635] Based on the behavioral patterns identified by the generated AI model, the server detects potential biases in the user. In this process, behavioral economics theories can be referenced to reveal tendencies such as "having purchased similar products multiple times in the past."

[0636] Subsequently, the device displays notification information based on the analysis results to the user as a pop-up message. This notification includes advice to caution the user against making unnecessary purchases. The user can then use this information to review their purchasing behavior.

[0637] Furthermore, users can provide feedback via their devices regarding notification content and system feedback. This allows the system to receive user feedback, which the server then uses to improve its AI models and notification algorithms. This enables the system to continuously improve accuracy and enrich the user experience.

[0638] As a concrete example, consider a case where a user in their 20s tries to purchase the same type of accessory multiple times late at night. A server that references this user's data generates a notification based on their past similar purchase history, stating, "You have previously owned multiple items of the same type of accessory," and displays it to the user on their device. In response, the user can reconsider their need for the product before purchasing, preventing unnecessary purchases.

[0639] This system helps consumers make wiser decisions by improving transparency in purchasing choices.

[0640] The following describes the processing flow.

[0641] Step 1:

[0642] The device collects real-time data on user activity when visiting e-commerce sites. This includes details of products viewed, time spent on the site, links clicked, and keywords searched. The collected data is temporarily stored in local storage.

[0643] Step 2:

[0644] The device sends collected operational data to the server at regular intervals or based on event triggers. Secure protocols are used for transmission to protect data integrity and user privacy.

[0645] Step 3:

[0646] The server stores the received operation data in a database. This allows for the management of a long-term history of user purchasing behavior. In the database, the data is organized by user, preparing for quick searching and analysis.

[0647] Step 4:

[0648] The server analyzes user behavior patterns using a generative AI model based on accumulated data. Here, it identifies whether users are repeating similar behaviors or if specific biases exist, based on past purchase and browsing history.

[0649] Step 5:

[0650] The server applies behavioral economics-based algorithms to detect biases that may influence user decisions. Based on the detected biases, it selects advice for the user.

[0651] Step 6:

[0652] Upon receiving analysis results from the server, the device generates a pop-up notification for the user. The notification includes warnings about biases the user may not be aware of and about products similar to past purchases.

[0653] Step 7:

[0654] Based on the pop-up notification, users have the opportunity to re-evaluate their purchasing behavior. Depending on the content of the notification, they can reconsider their purchase or remove items from their shopping cart.

[0655] Step 8:

[0656] Users provide feedback on notifications through their devices. This feedback includes opinions on the system's usefulness and the content of the notifications.

[0657] Step 9:

[0658] The server collects user feedback and uses it to improve the accuracy of the generated AI model and adjust the notification algorithm. This allows the system to continuously improve itself to enhance the user experience.

[0659] (Example 1)

[0660] 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".

[0661] There is a need to reduce excessive spending and unnecessary purchases that users unconsciously make when shopping online, and to improve the transparency of purchasing behavior. However, conventional systems lacked sufficient means to analyze the past behavior patterns of individual users in detail and detect specific purchasing biases. Furthermore, they lacked mechanisms to effectively utilize user feedback to improve the accuracy of the system.

[0662] 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.

[0663] In this invention, the server includes information gathering means for acquiring and storing data related to user operations; behavioral analysis means for analyzing the data using a generated artificial intelligence model and identifying patterns of user behavior; notification means for generating information based on the behavioral patterns and presenting that information to the user; and feedback processing means for receiving feedback from the user and improving the artificial intelligence model and algorithms based on that feedback. This makes it possible to analyze the user's past purchasing behavior in detail, effectively detect and notify of specific purchasing biases, and continuously improve the accuracy of the system by utilizing feedback from the user.

[0664] "Data related to operations" refers to information generated when a user uses an information system, such as user selections, inputs, and browsing.

[0665] An "artificial intelligence model" is a collection of algorithms or programs that can learn patterns from large amounts of data and perform specific tasks.

[0666] "Behavioral patterns" refer to specific behavioral tendencies or habits that a user repeatedly exhibits.

[0667] "Bias" refers to a potential inclination or tendency that influences a user's decision-making.

[0668] A "feedback processing method" is a method or process for receiving opinions and evaluations from users and using them to improve or adjust the system.

[0669] A "notification method" is a method or interface for presenting information to a user.

[0670] "Information gathering means" refers to a system or technology for acquiring data from users and recording and storing it.

[0671] This invention is a system aimed at analyzing users' online purchasing behavior and suppressing unnecessary purchases. The system includes terminals, servers, and multiple software components for them to work together.

[0672] The device acquires data related to user interactions when they use e-commerce websites. This data includes information such as products viewed, purchase history, and session information, and is used to record user behavior in detail. The device temporarily stores this data, encrypts it for security purposes, and then sends it to the server.

[0673] The server receives data sent from the terminal and stores it in a database. Based on the stored data, the server builds a generative AI model. This AI model uses machine learning algorithms to analyze the data and identify user behavior patterns and biases. In this process, the AI ​​model is given prompts such as, "Model purchasing patterns from the user's browsing and purchase history over the past six months."

[0674] Based on the analysis by the AI ​​model, the server detects specific behavioral biases in users. For example, it might reveal a tendency for users to purchase multiple items from a particular brand in a short period of time. Based on this information, the server generates notification information and sends it to the device.

[0675] The device displays notification information received from the server to the user. The notification appears as a pop-up message, providing the user with advice to prevent unnecessary purchases. This gives the user an opportunity to reconsider their needs.

[0676] Furthermore, users can provide feedback on notification content and system improvements through their devices. This feedback is sent to the server and used as foundational data to improve AI models and notification algorithms. As a result, the overall accuracy of the system and the user experience are improved.

[0677] As a concrete example, if a user attempts to purchase the same type of accessory multiple times late at night, the server generates a notification stating, "You already own multiple items of the same category," and displays advice to the user through their device. This helps prevent users from making unnecessary purchases.

[0678] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0679] Step 1:

[0680] The device collects data on user actions on e-commerce sites. This input data includes product information viewed by the user, purchase history, and session information. The device temporarily stores this data and standardizes and encrypts it before sending it to the server as needed. This process prepares a dataset to understand user behavior in as much detail as possible.

[0681] Step 2:

[0682] The server stores the operation data received from the terminal in a database. It saves the entered data and converts it into a structured format for later analysis. The server properly indexes the database and builds a data model to enable efficient queries. This organizes user-specific historical data, allowing for quick access and searching.

[0683] Step 3:

[0684] The server builds a generative AI model based on accumulated data. It uses past user purchase patterns and behavioral history as input data, applying machine learning algorithms to learn behavioral patterns. At this stage, it receives a prompt message instructing it to "model purchase patterns from the user's browsing and purchase history over the past six months." The output is a modeling result showing the user's behavioral trends.

[0685] Step 4:

[0686] The server uses the generated AI model to detect potential biases in users. It uses behavioral patterns derived from the AI ​​model as input and performs analysis based on behavioral economics theory. Specifically, it identifies tendencies such as multiple purchases of the same item in a short period. This results in the generation of data for notifications.

[0687] Step 5:

[0688] The server generates notification information based on detected biases. The identified user behavior trends are used as input data, and the notification content is created as output. This notification message includes advice to help users prevent unnecessary purchases. The generated notification is delivered to the device.

[0689] Step 6:

[0690] The terminal's role is to present notification information received from the server to the user. It receives notification messages as input and displays them as pop-up messages in the user interface. This gives the user an opportunity to carefully reconsider their purchase. This output serves as direct feedback to the user.

[0691] Step 7:

[0692] Users provide feedback on notifications and advice from the system. This feedback is sent to the server via the user's device. This feedback is used to improve the AI ​​model and the overall system. As a result, algorithms are adapted and modified based on the feedback information, continuously improving the system's accuracy.

[0693] (Application Example 1)

[0694] 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".

[0695] When consumers use e-commerce, they often make wasteful purchases based on their past buying history and behavioral patterns, and there is insufficient support for making appropriate purchasing decisions. As a result, they may realize that the items they purchased were not actually necessary. This problem stems from the fact that consumers do not receive effective advice in real time to consciously control their purchasing.

[0696] 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.

[0697] In this invention, the server includes information gathering means, behavioral analysis means, notification means, and evaluation means. This makes it possible to provide consumers with personalized advice in real time based on their past purchasing behavior to prevent them from making unnecessary purchases.

[0698] "Information gathering means" refers to a device or software that is responsible for acquiring and storing user operation data.

[0699] "Behavioral analysis means" refers to a process or function that analyzes operational data acquired using a generative artificial intelligence model to identify user behavior patterns.

[0700] "Notification means" refers to a system or method for presenting notification information to a user, which is generated based on the information obtained as a result of the analysis.

[0701] "Evaluation method" refers to a process or function that analyzes users' purchasing behavior and provides purchasing advice optimized for each individual user.

[0702] A "feedback processing mechanism" is a mechanism that receives feedback from users and utilizes that data to improve the accuracy of artificial intelligence models.

[0703] The following are the embodiments for carrying out the invention.

[0704] This invention is based on a system that combines information gathering means, behavioral analysis means, notification means, and evaluation means. Specifically, the user's terminal collects operation data and transmits it to a server. This data includes past purchase history and browsing information. The server receives this operation data and stores it in a database.

[0705] The server uses machine learning libraries such as TensorFlow or PyTorch in Python to build a generative artificial intelligence model as a means of behavioral analysis. This model is used to analyze the user's past behavioral patterns and identify their consumption preferences. Once the analysis is complete, an evaluation tool generates personalized advice based on their purchasing tendencies.

[0706] This advice is sent to the user's device via a notification system and presented as a pop-up notification. The notification includes information about whether the user has previously purchased similar products, and the user can refer to this notification before making a purchase. Based on this information, the user can optimize their purchasing decisions.

[0707] The system also includes feedback processing mechanisms to collect user feedback on notification information. The server uses this feedback to improve the accuracy of the AI ​​model and notification algorithms. In other words, continuous improvement is possible, further enhancing the user experience.

[0708] For example, if a user in their 20s has purchased similar accessories multiple times in the past, the server will generate a notification stating "You have previously owned similar accessories" and display it to the user on their device. This allows the user to reconsider whether they need to purchase the product.

[0709] An example of a prompt message is: "Analyze the user's past purchase history and current purchase candidates to identify their purchasing trends and provide advice."

[0710] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0711] Step 1:

[0712] The device monitors user activity and collects activity data, including browsing history, purchase history, and session duration on e-commerce sites. This data is acquired in real time from sensors and trackers and temporarily stored on the device.

[0713] Step 2:

[0714] Operation data is sent from the terminal to the server. The server receives this data and saves it to a database. This allows the user's operation history to be accumulated and made available for later analysis.

[0715] Step 3:

[0716] The server builds a generative AI model using Python's TensorFlow or PyTorch based on the stored operation data. The model uses machine learning algorithms to analyze the user's purchasing patterns and behavioral trends. This analysis identifies the user's consumption preferences.

[0717] Step 4:

[0718] Based on the results analyzed by the generative artificial intelligence model, the server uses evaluation tools to generate advice for the user. This advice is personalized, taking into account the purchase history, and prompts are used in its generation.

[0719] Step 5:

[0720] The server sends the generated advice as notification data to the device. The device receives this notification and displays it to the user as a pop-up message. The user reviews the notification and has the opportunity to reconsider their purchasing decision.

[0721] Step 6:

[0722] Users can provide feedback on displayed notifications. The device collects this feedback and sends it to the server. The server uses the received feedback to improve the AI ​​model and notification algorithms, thereby improving the overall accuracy of the system.

[0723] 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.

[0724] The following describes embodiments for carrying out the present invention. This system not only analyzes the user's purchasing behavior but also integrates an emotion engine that recognizes the user's emotions to provide more personalized notification information.

[0725] First, the device collects real-time operational data when a user visits an e-commerce site. This includes information about the products the user viewed and their browsing history. Simultaneously, it detects and records emotional indicators such as facial expressions, tone of voice, and input speed obtained from the user's webcam and optional microphone sensors as emotional data.

[0726] Next, the server receives operation data and sentiment data transmitted from the terminal and stores it in a database. This allows for the continuous recording of the user's consistent behavior and emotional changes, preparing for later analysis.

[0727] Utilizing a generative AI model, the server analyzes all data to derive specific behavioral patterns and emotional tendencies. Behavioral patterns include purchasing tendencies, frequently viewed genres, and activity at specific times of day. Meanwhile, the emotion engine performs emotional economic analysis to measure the user's emotional state towards specific products.

[0728] The server generates notification information that takes into account the user's specific emotional information. For example, if a user expresses positive emotions towards a particular product, it evaluates whether it is appropriate to make a promotional suggestion.

[0729] The device displays received notification information to the user visually or audibly. This information is customized in tone and content to fit the user's current emotional state, allowing for more empathetic and meaningful advice. This enables users to become more aware of their own emotions and make better purchasing decisions.

[0730] As a concrete example, suppose a user is browsing expensive electronic products late at night, and their emotional data indicates fatigue and a desire to make an impulse purchase. In this case, the server uses this data to provide the user with a discreet suggestion from their device: "Why not think about it overnight before purchasing?" This reduces the risk of making an immediate decision and allows the user to make a more rational product choice.

[0731] This system is expected to make the user's purchasing experience more personalized and rational through emotion recognition, thereby preventing wasteful spending.

[0732] The following describes the processing flow.

[0733] Step 1:

[0734] The device acquires operational data every time the user browses or clicks on an e-commerce site. Furthermore, with the user's permission, it uses the camera and microphone to measure real-time emotional indicators and records emotional data such as facial expressions and voice tone.

[0735] Step 2:

[0736] The device sends operational and emotional data to the server at set intervals. The transmitted data is encrypted from the device to protect user privacy.

[0737] Step 3:

[0738] The server stores received operation data and emotion data in a database. This data is organized for each user, allowing for tracking of emotional changes and behavioral history.

[0739] Step 4:

[0740] The server uses a generative AI model to analyze data stored in the database. This analysis helps to understand user behavior patterns and identify which emotional states are related to purchasing behavior. This process utilizes algorithms based on behavioral economics.

[0741] Step 5:

[0742] When generating notification information based on analysis results, the server takes emotional data into consideration. For example, if a negative emotional state is detected, it prepares a suggestion to encourage the user to reconsider their decision.

[0743] Step 6:

[0744] The device displays a pop-up notification to the user based on notification information received from the server. This notification reflects the user's current emotional state and behavioral patterns and is delivered in an empathetic and personalized format.

[0745] Step 7:

[0746] Through the displayed notifications, users re-evaluate their purchasing decisions based on their emotions. This allows them to make choices that are mindful of their own feelings.

[0747] Step 8:

[0748] Users provide feedback on notifications and emotion recognition features through their devices. This includes opinions on the usefulness of notifications and the accuracy of emotion recognition.

[0749] Step 9:

[0750] The server collects feedback and uses it to improve the algorithms of the generative AI model and emotion engine. Through this process, the system's accuracy and user experience are enhanced.

[0751] (Example 2)

[0752] 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".

[0753] Traditional e-commerce systems are limited to general behavioral analysis based on user activity history. This prevents them from providing more personalized notifications and suggestions that take into account the user's emotional state, resulting in an inefficient purchasing experience and potentially leading to impulsive purchases or unsatisfactory shopping experiences. Therefore, there is a need to provide a more appropriate and rational purchasing experience by offering notification information that takes the user's emotional state into account.

[0754] 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.

[0755] In this invention, the server includes information gathering means for acquiring and storing user operation data and emotional data; analysis means for analyzing the operation data and emotional data using a generative artificial intelligence model to identify the user's behavior patterns and emotional state; and information generation means for generating personalized notification information for the user based on the behavior patterns and emotional state. This makes it possible to provide more individualized notifications and suggestions that reflect the user's emotional state.

[0756] "Information gathering means" refers to technical means for acquiring and storing user operation data and emotional data.

[0757] "Operation data" refers to data about a user's actions and inputs when using electronic devices or systems.

[0758] "Emotional data" refers to data related to emotions obtained from a user's facial expressions, tone of voice, and other physiological indicators.

[0759] A "generative artificial intelligence model" is a model that uses artificial intelligence to analyze large amounts of data and identify user behavior patterns and emotional states.

[0760] "Analysis means" refers to a method for analyzing acquired operational data and emotional data using a generating artificial intelligence model to identify the user's behavioral patterns and emotional state.

[0761] "Behavioral patterns" refer to data that shows a certain flow or trend of user behavior, such as purchasing behavior or browsing trends.

[0762] "Emotional state" refers to information that indicates the type and intensity of a user's emotions.

[0763] "Information generation means" refers to means for generating appropriate notification information for the user based on analyzed behavioral patterns and emotional states.

[0764] "Personalized notification information" refers to notification content that is tailored to the user based on their individual behavioral patterns and emotions.

[0765] An "information display means" is a technical means of presenting generated notification information to the user.

[0766] This invention is a system that utilizes operational data and emotional data to improve the user's purchasing experience. This system mainly consists of two components: a terminal and a server.

[0767] The device plays a role in collecting operational and emotional data when users visit e-commerce sites. Specifically, it acquires operational data in real time, including the user's click history and browsing time, through JavaScript code and browser extensions. Furthermore, after obtaining the user's consent, it uses the webcam and microphone to collect emotional data such as facial expressions, tone of voice, and typing speed. This data is transmitted to the server using a secure protocol (e.g., HTTPS).

[0768] The server is responsible for storing and analyzing the received operational and emotional data. The data is systematically stored in relational or NoSQL databases in preparation for later analysis. The server uses generative artificial intelligence models to analyze this data. Frameworks such as TensorFlow and PyTorch may be used for analysis. As a result of the analysis, user behavior patterns (e.g., product categories frequently visited at specific times) and emotional states (e.g., positive feelings towards specific products) are identified.

[0769] Based on the analysis results, the server generates notification information optimized for the user. The generated notification information reflects the user's individual emotional state and behavioral patterns. For example, if a user's behavior of browsing high-priced items at night includes emotional data indicating fatigue, a suggestion such as "Why not think about it overnight before purchasing?" might be generated.

[0770] The device presents the generated notification information to the user. Notifications may appear visually as pop-ups or banners, or as audible alerts.

[0771] As a concrete example, a prompt message such as, "Generate a suggestion to notify a user if they are browsing high-priced items at night and are showing signs of anxiety or fatigue," is input into the AI ​​model.

[0772] In this way, personalized notifications are provided while taking into account the user's emotional state, resulting in a more personalized purchasing experience.

[0773] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0774] Step 1:

[0775] The device collects user interaction data while the user is browsing the web. Inputs are browsing actions such as clicks and page views, and outputs are interaction datasets summarizing these actions. The device retrieves this data through JavaScript code and browser extensions, and organizes and stores it in real time.

[0776] Step 2:

[0777] The device collects user emotion data. The input is real-time audio and video captured by a webcam and microphone, and the output is emotion data based on facial expressions and tone of voice. The device processes this data and calculates an emotion index using a facial expression analysis algorithm.

[0778] Step 3:

[0779] The device transmits collected operational and sentiment data to the server via a security protocol. The input is the dataset collected by the device, and the output is the secure data transfer to the server. Asynchronous communication ensures data transmission without compromising the user experience.

[0780] Step 4:

[0781] The server stores received operation data and sentiment data in a database. Input is data sent from the terminal, and output is data stored in a normalized format. A database management system (RDBMS or NoSQL) is used to efficiently manage the data.

[0782] Step 5:

[0783] The server inputs the stored data into a generating AI model for analysis. The input consists of user interaction and emotional data stored in a database, and the output is the analysis of behavioral patterns and emotional states. This analysis utilizes machine learning algorithms, sometimes employing TensorFlow or PyTorch.

[0784] Step 6:

[0785] The server generates user-optimized notification information based on the analysis results. The input is data on behavioral patterns and emotional states, and the output is customized notification information. The generation AI model uses prompt sentences to create personalized messages.

[0786] Step 7:

[0787] The device displays generated notification information to the user. The input is notification information sent from the server, and the output is a visual and auditory notification displayed on the user's screen. Notifications are presented as pop-ups or banners, providing the user with information to aid in their purchasing decisions.

[0788] (Application Example 2)

[0789] 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".

[0790] When users make online purchases, there is a challenge in avoiding irrational, emotion-driven buying and providing more personalized purchasing assistance. Furthermore, there is a need to improve the accuracy of purchasing decisions by presenting notifications that take the user's emotional state into consideration.

[0791] 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.

[0792] In this invention, the server includes data collection means for acquiring and storing user operation information and emotional information; behavior and emotion analysis means for analyzing the operation information and emotional information using a generative artificial intelligence model to identify the user's behavior patterns and emotional state; and emotion adaptation notification means for generating notification information based on the behavior patterns and emotional state and presenting the notification information to the user. This enables the provision of notifications tailored to the user's emotional state, prevents irrational purchasing behavior, and allows for rational purchasing decisions.

[0793] "User operation information" refers to data about a user's actions and choices when using the system.

[0794] "Emotional information" refers to data about a user's emotional state, inferred from their facial expressions, tone of voice, and other factors.

[0795] "Data collection means" refers to a device or process for acquiring and storing user operation information and emotional information.

[0796] A "generative artificial intelligence model" is an algorithm used to analyze large amounts of data and identify specific patterns or trends.

[0797] "Behavioral and emotional analysis means" refers to a device or process for identifying a user's behavioral patterns and emotional states using acquired operational information and emotional information.

[0798] An "emotion-adaptive notification means" is a device or process for generating and presenting appropriate notification information to the user according to the user's behavioral patterns and emotional state.

[0799] The system for implementing this invention consists of a user's terminal, a server, and a processing flow using a generated AI model.

[0800] On the user's device, user operation information and emotional information are acquired in real time using the camera and microphone. Operation information is data related to the user's actions such as selecting or browsing products, while emotional information is data indicating signs of emotion obtained by analyzing facial expressions and tone of voice. This information is transmitted from the device to the server.

[0801] On the server, this information is stored by data collection devices. The stored information is analyzed using a generative artificial intelligence model to estimate the user's behavior patterns and emotional state. This analysis generates specific notification information. This notification information is tailored to the user's emotional state and is sent to the user's terminal via an emotionally adapted notification device. For example, if a user is browsing a particular product and showing interest, a suggestion using a prompt such as "There is a special discount on this product" will be made.

[0802] As a concrete example, consider a situation where a user is browsing expensive electronic devices late at night. If the server analyzes the user's emotional state and determines that they are considering an impulsive purchase, a discreet notification such as, "Why not think about this product overnight?" is displayed. An example of a prompt message is, "Generate special suggestions for products the user is interested in." Such notifications allow users to make calmer and more rational purchasing decisions.

[0803] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0804] Step 1:

[0805] The user's device uses its camera and microphone to collect operational and emotional information in real time and transmit it to the server. Inputs include operational information such as product information the user is viewing and the time of day they are using the device, as well as emotional data analyzed from their voice and facial expressions. This input data is processed to quantify the emotional state. Outputs consist of data packets summarizing this information.

[0806] Step 2:

[0807] The server receives data packets sent from the terminal and stores them in a database using data collection means. In this step, filtering and formatting are performed to maintain data consistency and speed, and the data is converted into a format suitable for analysis. The input is user operation information and sentiment information, and the output is data in a neatly organized format recorded in the server's database.

[0808] Step 3:

[0809] The server analyzes the stored data using a generative artificial intelligence model. Specifically, it identifies user behavior patterns based on operation information and estimates emotional states from emotional information. At this stage, it processes the data through machine learning algorithms to derive the most likely behavioral scenarios and emotional tendencies. The input is the data organized in step 2, and the output is the analysis results showing the user's behavior patterns and emotional states.

[0810] Step 4:

[0811] The server generates notification information based on behavioral patterns and emotional states. This process uses prompts generated by a generative AI model to create the most appropriate communication message for the user. For example, if a user expresses positive feelings towards a product, a notification containing a special offer will be generated. The input is the analysis results from step 3, and the output is a notification message customized for each user.

[0812] Step 5:

[0813] The device receives notification information sent from the server and presents it to the user. The notification is displayed in an appropriate tone and format tailored to the user's current situation. Specific actions include attracting the user's attention through notification pop-ups and audio notifications. The input is the notification information generated in step 4, and the output is the content displayed directly to the user.

[0814] 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.

[0815] 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.

[0816] 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.

[0817] 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.

[0818] 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.

[0819] 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.

[0820] 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.

[0821] 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.

[0822] 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."

[0823] 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.

[0824] 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.

[0825] 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.

[0826] 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.

[0827] 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.

[0828] 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.

[0829] 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.

[0830] 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.

[0831] 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.

[0832] 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.

[0833] 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.

[0834] 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.

[0835] The following is further disclosed regarding the embodiments described above.

[0836] (Claim 1)

[0837] A data collection means that acquires user operation data and stores said operation data,

[0838] A behavioral analysis means that analyzes the aforementioned operation data using a generative artificial intelligence model and identifies the user's behavioral patterns,

[0839] A notification means that generates notification information based on the aforementioned behavioral pattern and presents said notification information to the user,

[0840] A system that includes this.

[0841] (Claim 2)

[0842] The system according to claim 1, characterized in that the behavioral analysis means detects biases that influence purchasing using an algorithm based on behavioral economics.

[0843] (Claim 3)

[0844] The system according to claim 1, further comprising a feedback processing means for receiving user feedback and utilizing said feedback to improve the accuracy of the generated artificial intelligence model.

[0845] "Example 1"

[0846] (Claim 1)

[0847] Information gathering means that acquires and stores data related to user actions,

[0848] A behavioral analysis means that uses the generated artificial intelligence model to analyze the aforementioned data and identify patterns in user behavior,

[0849] A notification means that generates information based on the aforementioned behavioral pattern and presents said information to the user,

[0850] A feedback processing means that receives user feedback and uses it to improve artificial intelligence models and algorithms,

[0851] ...

[0852] A system that includes this.

[0853] (Claim 2)

[0854] The system according to claim 1, characterized in that the behavioral analysis means detects biases that influence purchasing using an economics-based algorithm.

[0855] (Claim 3)

[0856] The system according to claim 1, characterized in that it accepts user feedback and utilizes such feedback to improve the accuracy of the artificial intelligence model.

[0857] "Application Example 1"

[0858] (Claim 1)

[0859] Information gathering means for acquiring user operation data and storing said operation data,

[0860] A behavioral analysis means that analyzes the aforementioned operation data using a generative artificial intelligence model and identifies the user's behavioral patterns,

[0861] A notification means that generates notification information based on the aforementioned behavioral pattern and presents said notification information to the user,

[0862] An evaluation method that provides personalized advice to users based on their purchasing behavior,

[0863] A system that includes this.

[0864] (Claim 2)

[0865] The system according to claim 1, characterized in that the behavioral analysis means detects purchasing influencing factors using an algorithm based on behavioral economics theory.

[0866] (Claim 3)

[0867] The system according to claim 1, further comprising an evaluation processing means for receiving user feedback and utilizing said feedback to improve the accuracy of the generated artificial intelligence model.

[0868] "Example 2 of combining an emotion engine"

[0869] (Claim 1)

[0870] Information gathering means for acquiring user operation data and emotional data, and storing said data,

[0871] An analysis means that uses a generative artificial intelligence model to analyze the operation data and emotion data and identify the user's behavior patterns and emotional state,

[0872] Information generation means that generates personalized notification information for the user based on the aforementioned behavioral patterns and emotional states,

[0873] Information display means for presenting the aforementioned notification information to the user,

[0874] A system that includes this.

[0875] (Claim 2)

[0876] The system according to claim 1, wherein the analysis means is characterized by detecting biases that influence purchasing using an algorithm based on behavioral economics.

[0877] (Claim 3)

[0878] The system according to claim 1, further comprising evaluation processing means for receiving user evaluation data and utilizing said evaluation data to improve the performance of the generated artificial intelligence model.

[0879] "Application example 2 when combining with an emotional engine"

[0880] (Claim 1)

[0881] A data collection means that acquires user operation information and emotional information and stores such information,

[0882] A behavior and emotion analysis means that analyzes the aforementioned operation information and emotion information using a generative artificial intelligence model to identify the user's behavior patterns and emotional state,

[0883] An emotion-adaptive notification means that generates notification information based on the aforementioned behavioral patterns and emotional states and presents said notification information to the user,

[0884] A system that includes this.

[0885] (Claim 2)

[0886] The system according to claim 1, characterized in that the behavior and emotion analysis means detects biases that influence purchasing using algorithms based on behavioral economics and emotional economics.

[0887] (Claim 3)

[0888] The system according to claim 1, further comprising a feedback processing means for receiving user feedback and utilizing said feedback to improve the accuracy of the generated artificial intelligence model. [Explanation of Symbols]

[0889] 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. Information gathering means for acquiring user operation data and storing said operation data, A behavioral analysis means that analyzes the aforementioned operation data using a generative artificial intelligence model and identifies the user's behavioral patterns, A notification means that generates notification information based on the aforementioned behavioral pattern and presents said notification information to the user, An evaluation method that provides personalized advice to users based on their purchasing behavior, A system that includes this.

2. The system according to claim 1, characterized in that the behavioral analysis means detects purchasing influencing factors using an algorithm based on behavioral economics theory.

3. The system according to claim 1, further comprising an evaluation processing means for receiving user feedback and utilizing said feedback to improve the accuracy of the generated artificial intelligence model.

Images