system

Abstract

We provide the system. [Solution] Means for collecting user behavior information, Means for integrating the aforementioned behavioral information and generating a profile, Means for generating personalized information based on the aforementioned profile, The means for providing the personalized information, A means for collecting user feedback information and providing feedback to the generating means, 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, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance that responds to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Conventional information provision systems using artificial intelligence can only propose general information and cannot provide services that sufficiently respond to the backgrounds and preferences of individual users. There is also a problem that it is difficult to update information in real time and continuously improve services based on specific feedback from users. As a result, there has been a problem that the quality of the user experience has deteriorated and individual needs cannot be met.

Means for Solving the Problems

[0005] This invention provides a means for generating personalized information by collecting and integrating user online and offline behavioral information to create a profile. The generated information is provided to the user's terminal, enabling the user to use products and services based on it. Furthermore, by collecting user feedback information and feeding it back into the generated information, the quality and appropriateness of the service can be continuously improved. This enhances the user experience and makes it possible to meet individual needs.

[0006] "User" refers to an individual who uses the system to receive information or services.

[0007] "Behavioral information" refers to data related to actions taken by users, whether online or offline.

[0008] "Means of collection" refers to the process or device for acquiring behavioral information and storing it in a database.

[0009] "Means of integration" refers to the process of processing collected behavioral information and generating a unified profile.

[0010] A "profile" refers to a dataset that integrates user preferences, behavioral patterns, purchase history, and other data.

[0011] "Personalized information" refers to information and services that are identified and customized based on the user's profile.

[0012] "Means of providing" refers to the process or device that presents and makes accessible personalized information to users.

[0013] "Feedback information" refers to the reactions and evaluations that users have given to the information and services provided.

[0014] "Means of providing feedback" refers to the process of improving and optimizing the information and services generated based on the collected feedback information. [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a labeled 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), etc.

[0019] In the following embodiments, a labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, a labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0021] 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).

[0022] 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."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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".

[0036] This invention is a system for collecting user behavior information and providing personalized services. The server, terminal, and user each play their respective roles, ensuring the smooth progress of the overall process.

[0037] The servers use distributed digital technologies to collect user behavior information both online and offline. This information includes browsing history on websites and purchase history at partner stores. This data is encrypted and stored securely.

[0038] Next, the server generates a profile for each user based on the collected behavioral information. This profile reflects the user's preferences and behavioral patterns in detail, forming the basis for generating personalized information.

[0039] Personalized information generated on the server is sent to the terminal. The terminal's role is to present this information to the user. For example, information is provided in the form of coupons or product recommendations based on the user's profile. This allows the user to receive information optimized for them.

[0040] Furthermore, feedback information is acquired that reflects how the user interacted with the information and services provided. The device sends the user's responses to the server. The server analyzes this feedback information and optimizes the generated AI model to improve the accuracy of information in the future.

[0041] As a concrete example, suppose a user expresses interest in healthcare products. The server updates the user's profile based on their purchase history and browsing information, generating coupons for health foods and special promotional offers. This information is presented to the user via their device, allowing them to purchase products using it. Through this entire process, users receive information that directly addresses their personal needs, resulting in a richer experience.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The server uses distributed digital technology to collect user behavior information. Specifically, it captures historical data when users browse websites or make purchases in stores and stores it securely stores the data.

[0045] Step 2:

[0046] The server generates individual user profiles from collected behavioral data. These profiles include user preferences, purchase history, and browsing patterns, and are updated in real time with new behavioral information.

[0047] Step 3:

[0048] The AI ​​on the server generates personalized information based on the user profile. For example, it might refer to past purchase data to create discount coupons for specific products.

[0049] Step 4:

[0050] The device provides users with personalized information generated by the server. Through apps and web interfaces, users can view information that matches their personal interests and past behavior.

[0051] Step 5:

[0052] The device records how the user reacts to the information and services presented. For example, it collects information on whether the user actually used a coupon.

[0053] Step 6:

[0054] The server receives feedback information sent from the terminal and optimizes the information generation process through a generation AI. This ensures that future information delivery is even more aligned with user needs.

[0055] (Example 1)

[0056] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0057] Based on user behavior data, there is a need to build efficient systems to securely provide personalized services and to appropriately deliver personalized information to users. However, conventional systems have been insufficient in the secure collection and analysis of behavior data, and in the generation and provision of personalized information based on user preferences. As a result, improvements in the user experience have been limited, and challenges remain in providing optimal information.

[0058] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0059] In this invention, the server includes means for encrypting and collecting user behavior information, means for analyzing the behavior information and generating a profile using a generative AI model, and means for creating personalized information based on the profile. This makes it possible to generate and provide safe and appropriate personalized information to the user.

[0060] "User behavior information" refers to the behavioral and contact history associated with individual users, and includes data such as purchase history and browsing information that occurred both online and offline.

[0061] "Encryption" is a process performed to maintain data security, and it refers to converting information into a format that cannot be understood without decryption in order to protect it from unauthorized access.

[0062] A "generative AI model" refers to an algorithm that uses artificial intelligence technology to generate profiles from data, learns and analyzes user behavior and preferences.

[0063] A "profile" is a collection of information that reflects a user's behavioral patterns and preferences, and refers to a data structure that forms the basis for generating personalized information.

[0064] "Personalized information" refers to customized content generated based on a user's profile, including information specific to the user, such as coupons and product recommendations.

[0065] "Feedback information" refers to data that records users' reactions and choices to personalized information and services, and is used to improve the system and enhance its accuracy.

[0066] "Optimization" refers to adjustments and improvements made to enhance the performance and accuracy of a system, and includes improving processes based on user feedback.

[0067] This invention is a system for securely collecting user behavior information and providing personalized information. The system mainly consists of the interaction between a server, a terminal, and a user, and its operation is described in detail below.

[0068] The server uses distributed digital technology to encrypt and collect users' online and offline behavioral information. This behavioral information includes website browsing history and purchase history at partner stores. Specific data processing techniques include browser tracking and POS system data mining. The collected data is stored in a secure database.

[0069] Next, the server uses a high-performance generative AI model to generate a detailed profile of each user based on this behavioral information. This profile helps generate personalized information by analyzing user preferences and patterns through machine learning techniques.

[0070] Next, based on the generated profile, the server creates personalized information and sends it to the terminal. The terminal is responsible for displaying the received information to the user. Personalized information such as coupons and product recommendations are presented to the user through a mobile or web app installed on the terminal. For example, it is possible to provide health-conscious users with discount coupons for health foods identified from their profile.

[0071] Furthermore, the device sends feedback to the server about how the user reacted to the information presented. The server analyzes this feedback and fine-tunes the generating AI model to improve the accuracy of future information provision. An example of a prompt message is, "Recommend the best products based on a specific user's past purchase history."

[0072] This system ensures that users consistently receive valuable information and enhances their personalized experience.

[0073] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0074] Step 1:

[0075] The server collects user behavior information both online and offline. This process tracks web browsing history and in-store purchase history. Specifically, it collects data using browser cookies and in-app tracking tools. The input is user behavior data, and the output is encrypted behavior data. This data is securely stored in a database for use in subsequent processing.

[0076] Step 2:

[0077] The server generates profiles based on collected behavioral data. This process uses a generative AI model to analyze the data and identify user preferences and behavioral patterns. The input is encrypted behavioral data, and the output is a detailed profile for each user. Specifically, machine learning algorithms analyze past purchase history and frequently visited websites to identify user interests.

[0078] Step 3:

[0079] The server creates personalized information based on the generated profile. Using a generative AI model, it generates coupons and product recommendations tailored to the user. The input is the user's profile data, and the output is personalized information. For example, if the profile is determined to be health-conscious, it will generate coupons for suitable health foods.

[0080] Step 4:

[0081] The device presents personalized information received from the server to the user. This information is delivered through notifications and displays in mobile and web applications. The input is personalized information, and the output is the display or notification to the user. Specifically, the device uses push notifications to inform the user of the expiration date of a particular coupon.

[0082] Step 5:

[0083] The device records how the user reacted to the information provided and sends feedback to the server. The input is user reaction data, and the output is feedback data sent to the server. For example, it records whether the user used a coupon they received and sends that information to the server.

[0084] Step 6:

[0085] The server optimizes the generated AI model based on the feedback it receives. This improves the accuracy of information provided in subsequent instances. The input is feedback data, and the output is the optimized AI model. Specifically, it learns new data based on user selections and adjusts the model's parameters.

[0086] (Application Example 1)

[0087] 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."

[0088] There is a need to improve the accuracy of personalized information delivery and provide users with a more valuable purchasing experience. Traditional methods make it difficult to quickly and effectively utilize collected data and appropriately optimize user profiles, making the presentation of highly accurate information and improvement of the user experience a challenge.

[0089] 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.

[0090] In this invention, the server includes means for collecting user behavior information, means for optimizing an artificial intelligence model generated using the feedback, and means for providing special information based on specific behavioral history. This makes it possible to present optimal information tailored to the user's preferences.

[0091] "User" refers to an individual or group that uses this system.

[0092] "Behavioral information" refers to information such as a user's online and offline purchase history and browsing history.

[0093] A "profile" is a set of data generated based on collected behavioral information, reflecting the user's preferences and behavioral patterns.

[0094] "Personalized information" refers to information such as product recommendations and discount coupons that are generated based on a user's profile and are tailored to their needs.

[0095] "Feedback information" refers to data about users' reactions and actions to the information provided.

[0096] A "generating artificial intelligence model" is a machine learning algorithm that generates personalized information based on collected behavioral and feedback data.

[0097] A "special offer" refers to a special offer or promotion made to a user based on their specific behavioral history.

[0098] The system of this invention collects user behavior information and enables personalized services based on that information. The entire process proceeds smoothly when the server, terminal, and user each fulfill their respective roles.

[0099] The server uses cloud infrastructure to collect diverse behavioral information from both online and offline sources, encrypts it, and stores it. This process is implemented using cloud services such as AWS® Lambda and Amazon S3. Based on the collected data, the server generates user profiles using a generative AI model on Amazon SageMaker. This profile includes the user's past purchase history and browsing patterns, forming the basis for generating personalized information.

[0100] The device provides users with personalized information transmitted from the server. For example, it may provide discount coupons for specific products or notifications of recommended products. This information is presented to the user's device, such as a smartphone or smart glasses, as a push notification or display within the app.

[0101] Based on the information provided, users choose actions such as purchasing products. Feedback information regarding the user's choices and actions is sent back to the server from the terminal, and the server uses this to optimize the generated AI model. This improves the accuracy of information provided in the future.

[0102] As a concrete example, consider a case where a user is presented with a new coupon for health food based on their past purchase history. If the user uses this coupon to purchase the product, their behavioral information is fed back, and the server uses a generative AI model to help generate more appropriate offers for other users.

[0103] An example of a prompt message is, "Use purchase history data to generate new promotional ideas for diet foods and design notification messages to attract user interest." This can improve the accuracy and effectiveness of promotions.

[0104] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0105] Step 1:

[0106] The server collects user behavior information. Data such as purchase history from websites and partner stores is collected, and the data is anonymized using AWS Lambda. The input is raw behavioral data, and the output is encrypted behavioral information.

[0107] Step 2:

[0108] The server generates a profile based on collected behavioral information. A generative AI model running on Amazon SageMaker analyzes the data and generates a profile that reflects the user's preferences. The input is encrypted behavioral information, and the output is profile data.

[0109] Step 3:

[0110] The server generates personalized information based on the generated profile data. Using the profile as input, it creates recommended products and discount coupons, and structures them as personalized information. The output is personalized information.

[0111] Step 4:

[0112] The device receives personalized information transmitted from the server. This information is displayed to the user via a smartphone or smart glasses and presented as a push notification. The input is personalized information, and the output is the information displayed on the user interface.

[0113] Step 5:

[0114] The user acts on information provided through the device. For example, they might choose to use a coupon presented for purchasing a product. The input is the information displayed on the device, and the output is the user's chosen action.

[0115] Step 6:

[0116] The device sends feedback information about the user's actions to the server. User selections and interaction data are aggregated and sent back to the server. The input is the user's actions (e.g., using a coupon), and the output is feedback data.

[0117] Step 7:

[0118] The server analyzes feedback data and optimizes the generative AI model. Using Google Cloud AI, it generates new prompts and tunes the model to improve the accuracy of information delivery. The input is feedback data, and the output is the optimized generative AI model.

[0119] 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.

[0120] This invention provides a system that delivers personalized services for users, and by incorporating an emotion engine, it enables even more advanced customization. In this invention, the server, terminal, and user each play their respective roles to realize the overall functionality.

[0121] The server first collects information about users' online and offline behavior. This information includes web browsing history and in-store purchase history, and is securely stored in a database. Next, the server integrates the collected behavioral information to create a detailed profile of each user. Using this profile, the server understands the user's interests and preferences and generates personalized information. In this process, an emotion engine is utilized. The emotion engine can analyze text or audio data to determine the user's emotional state.

[0122] The generated personalized information takes emotional information into account and includes content tailored to the user's current emotions. For example, if the server determines that the user is feeling stressed, it can present information and discounts on relaxation products.

[0123] The terminal's role is to provide users with personalized information supplied from the server. This information is presented through applications and websites, and users can purchase products or use services based on that information.

[0124] The device also collects user responses as feedback information and sends it to the server. The server uses this feedback information to optimize the algorithms of the emotion engine and generative AI model, improving the accuracy and relevance of the information it provides.

[0125] As a concrete example, let's assume a user is experiencing fatigue in their daily life. The server, through its emotion engine, interprets the user's emotional state as stress and suggests products and services that promote relaxation. This allows the user to select products that are appropriate for their state and enjoy a personalized experience.

[0126] The following describes the processing flow.

[0127] Step 1:

[0128] The server continuously collects information about users' online and offline activities. It captures data when users browse websites or make purchases at physical stores and stores it in a database.

[0129] Step 2:

[0130] The server integrates the collected behavioral information and generates a profile for each user. This profile includes past purchase history, browsing patterns, and preferences, and is updated in real time.

[0131] Step 3:

[0132] An emotion engine is used to analyze the user's text messages and voice input to understand their current emotional state. For example, it can recognize emotions such as joy, sadness, and stress from voice tone and text content.

[0133] Step 4:

[0134] The server combines the generated user profile and emotional information to create personalized information. It then creates information such as product recommendations and special offers that reflect the user's emotional state. During this process, adjustments are made based on the user's emotions.

[0135] Step 5:

[0136] The device provides users with personalized information. Through applications and websites, for example, it might present users with discount information on products designed to relieve stress.

[0137] Step 6:

[0138] The device records feedback information about how the user utilized the presented information and services. This includes coupon usage and purchase history.

[0139] Step 7:

[0140] The server collects feedback information and optimizes the generative AI model and emotion engine. This process enables the provision of even more accurate personalized information for future use.

[0141] (Example 2)

[0142] 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".

[0143] In today's consumer society, there is a need to establish methods for providing personalized information that meets the diverse needs and emotions of users. However, conventional systems have the challenge of providing limited information based on users' behavioral history and preferences, making it difficult to provide appropriate information that takes into account the user's emotional state.

[0144] 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.

[0145] In this invention, the server includes means for collecting user behavior information, means for integrating the behavior information and generating a detailed profile, means for analyzing the user's emotional state using an emotion engine, means for generating personalized information using a generative AI model, and means for providing feedback to means for collecting and generating user feedback information and optimizing it. This makes it possible to provide highly accurate information that meets the diverse needs and emotional states of users.

[0146] "Behavioral information" refers to data related to a user's online and offline activities, and is a general term for information including purchase history and browsing information.

[0147] A "profile" is a dataset that shows detailed attributes and preferences of a user, generated based on collected behavioral information.

[0148] An "emotion engine" refers to an algorithm or software that analyzes text and audio data to determine a user's emotional state.

[0149] A "generative AI model" is a system or algorithm that uses artificial intelligence technology to generate personalized information or content.

[0150] "Feedback information" refers to data about the reactions and actions that users have taken in response to the information provided, and is used to optimize and improve the system.

[0151] This invention involves a server, terminal, and user collaborating using their respective hardware and software to provide personalized services. The server is responsible for collecting user behavioral information, including web browsing history and in-store purchase history. This information is securely stored in a database using a relational database management system (e.g., MySQL® or PostgreSQL).

[0152] The server then integrates this behavioral information to generate a detailed user profile. This profile creation utilizes data mining techniques to recognize user preferences and patterns. Additionally, natural language processing (NLP) techniques are used to leverage an emotion engine to determine the user's emotional state from text or audio data.

[0153] The terminal provides users with personalized information supplied by the server. This information is presented through applications and websites, and users can purchase products or use services based on this information. For example, if a user is feeling fatigued, the system can suggest products or services that promote relaxation. In this case, the server inputs a prompt message into the generative model such as, "Generate suggestions for products and services suitable for a specific user who is feeling fatigued."

[0154] Furthermore, the device collects user responses as feedback information and sends it to the server. The server uses this feedback information to optimize the algorithms of the emotion engine and generative AI model. This optimization is performed using machine learning techniques, which can improve the accuracy and relevance of the information provided.

[0155] In this way, the system becomes capable of providing more accurate, personalized services that respond to the diverse needs and emotional states of users.

[0156] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0157] Step 1:

[0158] The server collects user behavior information. It uses the user's web browsing history and in-store purchase history as input. This information is securely stored in a database on the server. Specifically, web tracking tools and POS systems collect the data.

[0159] Step 2:

[0160] The server integrates collected behavioral information to generate user profiles. The input is behavioral information stored in a database. Data processing involves organizing the information, removing duplicates, and extracting user preferences and past behavioral patterns. The output is the generation of a detailed user profile. Specifically, data mining algorithms are applied to identify user interests.

[0161] Step 3:

[0162] The server uses an emotion engine to analyze the user's emotional state. It takes text or audio data obtained from the user as input. For data processing, it utilizes natural language processing techniques to analyze emotions from the text and audio. The output is an evaluation result indicating the user's current emotional state.

[0163] Step 4:

[0164] The server generates personalized information using a generative AI model based on user profiles and emotional states. The inputs used are profile data and emotional analysis results. For data processing, prompts are input to the generative AI model for the target user, generating content tailored to the user's interests. For example, a prompt such as "Suggest the best product for a specific user seeking relaxation" might be input. The output consists of personalized information and product recommendations.

[0165] Step 5:

[0166] The terminal provides personalized information to the user from the server. It uses content received from the server as input. Data processing involves formatting to match the display format of the user interface. The output is the presentation of information to the user. Specifically, this information is presented to the user through a smartphone app or website.

[0167] Step 6:

[0168] The terminal collects user responses as feedback information and sends it to the server. User behavior data and selected options are used as input. Data processing involves collecting and organizing the feedback data. The output is the provision of feedback information to the server.

[0169] Step 7:

[0170] The server optimizes the generative AI model and emotion engine using feedback information. It uses feedback information received from the terminal as input. As data calculation, it uses machine learning algorithms to make adjustments to improve the model's accuracy. The output is the improved model and engine performance. Specifically, the algorithm parameters are adjusted to improve the accuracy of information provided in subsequent instances.

[0171] (Application Example 2)

[0172] 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".

[0173] In today's world, consumers need to choose the best products and services from a wide range of options, but finding the right ones amidst the vast amount of information is difficult. Furthermore, while it's known that consumers' emotional states significantly influence their purchasing decisions, conventional systems have been unable to provide emotionally balanced recommendations. Therefore, there is a need for a system that can provide personalized services using both consumer behavioral and emotional information.

[0174] 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.

[0175] In this invention, the server includes means for collecting user behavior information, means for integrating behavior information and emotional information to generate a profile, and means equipped with an emotion engine for analyzing emotional states. This enables the provision of personalized products and coupons based on the user's preferences and emotions, allowing consumers to make more appropriate choices.

[0176] "Behavioral information" refers to data about the activities that users engage in both online and offline.

[0177] A "profile" is detailed information about an individual user, generated by integrating behavioral and emotional data.

[0178] "Personalized information" refers to information about products and services that is generated based on a user's profile and tailored to the specific needs and interests of that user.

[0179] A "visualization device" is a device used to present information to a user, and in this context refers to smart glasses, etc.

[0180] "Feedback information" refers to data that shows users' reactions and opinions to the information and suggestions they receive.

[0181] An "emotion engine" is a technology that analyzes text and audio to determine the emotional state of a user.

[0182] "Sale information" refers to special discounts and promotional information regarding products and services.

[0183] To realize this invention, the server first collects user behavior information. This behavior information includes online and offline purchase and browsing history. This information is stored in a database and used for analysis. The server analyzes the stored behavior data using data processing techniques with pandas and scikit-learn and generates profiles for individual users.

[0184] Next, the server uses an emotion engine to analyze emotional information from the user's text and voice data. NLTK and Transformers are utilized for this emotional analysis. The analysis results and profiles are integrated to generate personalized information for the user. This generated information is then provided to the user through visualization devices such as smart glasses.

[0185] The terminal helps users select products and services that match their current emotions based on information received from the server. The terminal uses OpenCV and PyQt to provide visually appealing information.

[0186] For example, if a user is feeling stressed, the server might present special discount information or services related to relaxation products. This allows the user to make purchasing choices that align with their emotional state.

[0187] An example of a prompt message is, "Based on past purchase history and current emotional state, please suggest the most suitable products." In this way, the entire system can provide consumers with an efficient and better purchasing experience.

[0188] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0189] Step 1:

[0190] The server collects information on users' online and offline behavior. This information, including purchase and browsing history, is stored in a database. User behavior data is taken as input, and the organized information is stored in the database as output. Specifically, it utilizes website tracking and sales history systems.

[0191] Step 2:

[0192] The server uses pandas and scikit-learn to analyze behavioral data and generate a profile for each user. This profile reveals the user's purchasing patterns and interests, which form the basis for personalized service delivery. The input is behavioral data retrieved from a database, and the output is user-specific profile information.

[0193] Step 3:

[0194] The server processes the user's text and voice data through an emotion engine and analyzes their emotional state using NLTK and Transformers. The input is voice or text data, and the output is information about the user's emotional state. Specifically, this involves analyzing voice recordings and text messages.

[0195] Step 4:

[0196] The server integrates profile information and emotional information to generate personalized information. This generation process utilizes a generative AI model to suggest optimal products and services based on past purchase history and emotional states. The input is profile information and emotional information, and the output is personalized information provided to the user.

[0197] Step 5:

[0198] The terminal receives personalized information transmitted from the server and presents it to the user through a visualization device such as smart glasses. Specifically, it displays the information on a visual display and provides audio guidance as needed. The input is personalized information from the server, and the output is the presentation of information to the user.

[0199] Step 6:

[0200] Users receive personalized information provided by their devices and use it to select products and utilize services. As a result, user feedback is generated. The input is the displayed information, and the output is user behavior and feedback information.

[0201] Step 7:

[0202] The server collects user feedback information and optimizes the algorithms of the emotion engine and generative AI model. This process improves the accuracy and relevance of the information based on the feedback. The input is user feedback, and the output is the improved algorithm model.

[0203] 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.

[0204] 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 those described above. 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 shown 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.

[0205] 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.

[0206] [Second Embodiment]

[0207] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0208] 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.

[0209] 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).

[0210] 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.

[0211] 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.

[0212] 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).

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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.

[0218] 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".

[0219] This invention is a system for collecting user behavior information and providing personalized services. The server, terminal, and user each play their respective roles, ensuring the smooth progress of the overall process.

[0220] The servers use distributed digital technologies to collect user behavior information both online and offline. This information includes browsing history on websites and purchase history at partner stores. This data is encrypted and stored securely.

[0221] Next, the server generates a profile for each user based on the collected behavioral information. This profile reflects the user's preferences and behavioral patterns in detail, forming the basis for generating personalized information.

[0222] Personalized information generated on the server is sent to the terminal. The terminal's role is to present this information to the user. For example, information is provided in the form of coupons or product recommendations based on the user's profile. This allows the user to receive information optimized for them.

[0223] Furthermore, feedback information is acquired that reflects how the user interacted with the information and services provided. The device sends the user's responses to the server. The server analyzes this feedback information and optimizes the generated AI model to improve the accuracy of information in the future.

[0224] As a concrete example, suppose a user expresses interest in healthcare products. The server updates the user's profile based on their purchase history and browsing information, generating coupons for health foods and special promotional offers. This information is presented to the user via their device, allowing them to purchase products using it. Through this entire process, users receive information that directly addresses their personal needs, resulting in a richer experience.

[0225] The following describes the processing flow.

[0226] Step 1:

[0227] The server uses distributed digital technology to collect user behavior information. Specifically, it captures historical data when users browse websites or make purchases in stores and stores it securely stores the data.

[0228] Step 2:

[0229] The server generates individual user profiles from collected behavioral data. These profiles include user preferences, purchase history, and browsing patterns, and are updated in real time with new behavioral information.

[0230] Step 3:

[0231] The AI ​​on the server generates personalized information based on the user profile. For example, it might refer to past purchase data to create discount coupons for specific products.

[0232] Step 4:

[0233] The device provides users with personalized information generated by the server. Through apps and web interfaces, users can view information that matches their personal interests and past behavior.

[0234] Step 5:

[0235] The device records how the user reacts to the information and services presented. For example, it collects information on whether the user actually used a coupon.

[0236] Step 6:

[0237] The server receives feedback information sent from the terminal and optimizes the information generation process through a generation AI. This ensures that future information delivery is even more aligned with user needs.

[0238] (Example 1)

[0239] 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."

[0240] Based on user behavior data, there is a need to build efficient systems to securely provide personalized services and to appropriately deliver personalized information to users. However, conventional systems have been insufficient in the secure collection and analysis of behavior data, and in the generation and provision of personalized information based on user preferences. As a result, improvements in the user experience have been limited, and challenges remain in providing optimal information.

[0241] 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.

[0242] In this invention, the server includes means for encrypting and collecting user behavior information, means for analyzing the behavior information and generating a profile using a generative AI model, and means for creating personalized information based on the profile. This makes it possible to generate and provide safe and appropriate personalized information to the user.

[0243] "User behavior information" refers to the behavioral and contact history associated with individual users, and includes data such as purchase history and browsing information that occurred both online and offline.

[0244] "Encryption" is a process performed to maintain data security, and it refers to converting information into a format that cannot be understood without decryption in order to protect it from unauthorized access.

[0245] A "generative AI model" refers to an algorithm that uses artificial intelligence technology to generate profiles from data, learns and analyzes user behavior and preferences.

[0246] A "profile" is a collection of information that reflects a user's behavioral patterns and preferences, and refers to a data structure that forms the basis for generating personalized information.

[0247] "Personalized information" refers to customized content generated based on a user's profile, including information specific to the user, such as coupons and product recommendations.

[0248] "Feedback information" refers to data that records users' reactions and choices to personalized information and services, and is used to improve the system and enhance its accuracy.

[0249] "Optimization" refers to adjustments and improvements made to enhance the performance and accuracy of a system, and includes improving processes based on user feedback.

[0250] This invention is a system for securely collecting user behavior information and providing personalized information. The system mainly consists of the interaction between a server, a terminal, and a user, and its operation is described in detail below.

[0251] The server uses distributed digital technology to encrypt and collect users' online and offline behavioral information. This behavioral information includes website browsing history and purchase history at partner stores. Specific data processing techniques include browser tracking and POS system data mining. The collected data is stored in a secure database.

[0252] Next, the server uses a high-performance generative AI model to generate a detailed profile of each user based on this behavioral information. This profile helps generate personalized information by analyzing user preferences and patterns through machine learning techniques.

[0253] Next, based on the generated profile, the server creates personalized information and sends it to the terminal. The terminal is responsible for displaying the received information to the user. Personalized information such as coupons and product recommendations are presented to the user through a mobile or web app installed on the terminal. For example, it is possible to provide health-conscious users with discount coupons for health foods identified from their profile.

[0254] Furthermore, the device sends feedback to the server about how the user reacted to the information presented. The server analyzes this feedback and fine-tunes the generating AI model to improve the accuracy of future information provision. An example of a prompt message is, "Recommend the best products based on a specific user's past purchase history."

[0255] This system ensures that users consistently receive valuable information and enhances their personalized experience.

[0256] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0257] Step 1:

[0258] The server collects user behavior information both online and offline. This process tracks web browsing history and in-store purchase history. Specifically, it collects data using browser cookies and in-app tracking tools. The input is user behavior data, and the output is encrypted behavior data. This data is securely stored in a database for use in subsequent processing.

[0259] Step 2:

[0260] The server generates profiles based on collected behavioral data. This process uses a generative AI model to analyze the data and identify user preferences and behavioral patterns. The input is encrypted behavioral data, and the output is a detailed profile for each user. Specifically, machine learning algorithms analyze past purchase history and frequently visited websites to identify user interests.

[0261] Step 3:

[0262] The server creates personalized information based on the generated profile. Using a generative AI model, it generates coupons and product recommendations tailored to the user. The input is the user's profile data, and the output is personalized information. For example, if the profile is determined to be health-conscious, it will generate coupons for suitable health foods.

[0263] Step 4:

[0264] The device presents personalized information received from the server to the user. This information is delivered through notifications and displays in mobile and web applications. The input is personalized information, and the output is the display or notification to the user. Specifically, the device uses push notifications to inform the user of the expiration date of a particular coupon.

[0265] Step 5:

[0266] The device records how the user reacted to the information provided and sends feedback to the server. The input is user reaction data, and the output is feedback data sent to the server. For example, it records whether the user used a coupon they received and sends that information to the server.

[0267] Step 6:

[0268] The server optimizes the generated AI model based on the feedback it receives. This improves the accuracy of information provided in subsequent instances. The input is feedback data, and the output is the optimized AI model. Specifically, it learns new data based on user selections and adjusts the model's parameters.

[0269] (Application Example 1)

[0270] 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."

[0271] There is a need to improve the accuracy of personalized information delivery and provide users with a more valuable purchasing experience. Traditional methods make it difficult to quickly and effectively utilize collected data and appropriately optimize user profiles, making the presentation of highly accurate information and improvement of the user experience a challenge.

[0272] 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.

[0273] In this invention, the server includes means for collecting user behavior information, means for optimizing an artificial intelligence model generated using the feedback, and means for providing special information based on specific behavioral history. This makes it possible to present optimal information tailored to the user's preferences.

[0274] "User" refers to an individual or group that uses this system.

[0275] "Behavioral information" refers to information such as a user's online and offline purchase history and browsing history.

[0276] A "profile" is a set of data generated based on collected behavioral information, reflecting the user's preferences and behavioral patterns.

[0277] "Personalized information" refers to information such as product recommendations and discount coupons that are generated based on a user's profile and are tailored to their needs.

[0278] "Feedback information" refers to data about users' reactions and actions to the information provided.

[0279] A "generating artificial intelligence model" is a machine learning algorithm that generates personalized information based on collected behavioral and feedback data.

[0280] A "special offer" refers to a special offer or promotion made to a user based on their specific behavioral history.

[0281] The system of this invention collects user behavior information and enables personalized services based on that information. The entire process proceeds smoothly when the server, terminal, and user each fulfill their respective roles.

[0282] The server uses cloud infrastructure to collect diverse behavioral information from both online and offline sources, encrypts it, and stores it. This process is implemented using cloud services such as AWS Lambda and Amazon S3. Based on the collected data, the server generates user profiles using a generative AI model on Amazon SageMaker. These profiles include the user's past purchase history and browsing patterns, forming the basis for generating personalized information.

[0283] The device provides users with personalized information transmitted from the server. For example, it may provide discount coupons for specific products or notifications of recommended products. This information is presented to the user's device, such as a smartphone or smart glasses, as a push notification or display within the app.

[0284] Based on the provided information, the user selects actions such as purchasing products. Feedback information regarding the user's selections and operations is sent back to the server from the terminal, and the server optimizes the generated AI model based on this. As a result, the accuracy of the next information provision is improved.

[0285] As a specific example, consider the case where a new coupon for health food is presented to a certain user based on past history. If the user purchases a product using this coupon, the action information is fed back, and the server uses the generated AI model to help generate more appropriate offers for other users.

[0286] An example of a prompt sentence is "Using the purchase history data, generate a new promotion plan for diet food and design a notification message to attract the user's interest." This makes it possible to improve the accuracy and effectiveness of the promotion.

[0287] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0288] Step 1:

[0289] The server collects the user's action information. Data such as purchase history on the website or partner stores is collected, and the data is anonymized using AWS Lambda. The input is raw action data, and the output is encrypted action information.

[0290] Step 2:

[0291] The server generates a profile based on the collected action information. The generated AI model operating on Amazon Sagemaker analyzes the data and generates a profile reflecting the user's preferences. The input is encrypted action information, and the output is profile data.

[0292] Step 3:

[0293] The server generates personalized information based on the generated profile data. Using the profile as input, it creates recommended products and discount coupons, and structures them as personalized information. The output is personalized information.

[0294] Step 4:

[0295] The device receives personalized information transmitted from the server. This information is displayed to the user via a smartphone or smart glasses and presented as a push notification. The input is personalized information, and the output is the information displayed on the user interface.

[0296] Step 5:

[0297] The user acts on information provided through the device. For example, they might choose to use a coupon presented for purchasing a product. The input is the information displayed on the device, and the output is the user's chosen action.

[0298] Step 6:

[0299] The device sends feedback information about the user's actions to the server. User selections and interaction data are aggregated and sent back to the server. The input is the user's actions (e.g., using a coupon), and the output is feedback data.

[0300] Step 7:

[0301] The server analyzes feedback data and optimizes the generative AI model. Using Google Cloud AI, it generates new prompts and tunes the model to improve the accuracy of information delivery. The input is feedback data, and the output is the optimized generative AI model.

[0302] Furthermore, an emotion engine for estimating the user's emotions may be combined. That is, the specific processing unit 290 may estimate the user's emotions using the emotion specific model 59 and perform specific processing using the user's emotions.

[0303] The present invention is a system that provides personalized services for users, and by incorporating an emotion engine, it enables even more advanced customization. In the present invention, the server, the terminal, and the user each play their respective roles to realize the overall function.

[0304] First, the server collects the user's behavior information both online and offline. This information includes web browsing history and purchase history at physical stores, and is securely stored in a database. Next, the server integrates the collected behavior information and creates a detailed profile for each user. By using this profile, the server can grasp the user's interests and preferences and generate personalized information. In this process, the emotion engine is utilized. The emotion engine can analyze text or voice data and determine the user's emotional state.

[0305] The generated personalized information takes into account the emotion information and includes content corresponding to the user's current emotions. For example, when the server determines that the user is feeling stressed, it can present information about relaxation products or discounts.

[0306] The terminal has the role of providing the user with the personalized information supplied from the server. The information is presented through applications or websites, and the user can purchase products or use services based on that information.

[0307] In addition, the terminal collects the user's reactions as feedback information and transmits this to the server. The server uses this feedback information to optimize the algorithms of the emotion engine and the generation AI model, and improve the accuracy and relevance of the information provided.

[0308] As a concrete example, let's assume a user is experiencing fatigue in their daily life. The server, through its emotion engine, interprets the user's emotional state as stress and suggests products and services that promote relaxation. This allows the user to select products that are appropriate for their state and enjoy a personalized experience.

[0309] The following describes the processing flow.

[0310] Step 1:

[0311] The server continuously collects information about users' online and offline activities. It captures data when users browse websites or make purchases at physical stores and stores it in a database.

[0312] Step 2:

[0313] The server integrates the collected behavioral information and generates a profile for each user. This profile includes past purchase history, browsing patterns, and preferences, and is updated in real time.

[0314] Step 3:

[0315] An emotion engine is used to analyze the user's text messages and voice input to understand their current emotional state. For example, it can recognize emotions such as joy, sadness, and stress from voice tone and text content.

[0316] Step 4:

[0317] The server combines the generated user profile and emotional information to create personalized information. It then creates information such as product recommendations and special offers that reflect the user's emotional state. During this process, adjustments are made based on the user's emotions.

[0318] Step 5:

[0319] The device provides users with personalized information. Through applications and websites, for example, it might present users with discount information on products designed to relieve stress.

[0320] Step 6:

[0321] The device records feedback information about how the user utilized the presented information and services. This includes coupon usage and purchase history.

[0322] Step 7:

[0323] The server collects feedback information and optimizes the generative AI model and emotion engine. This process enables the provision of even more accurate personalized information for future use.

[0324] (Example 2)

[0325] 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".

[0326] In today's consumer society, there is a need to establish methods for providing personalized information that meets the diverse needs and emotions of users. However, conventional systems have the challenge of providing limited information based on users' behavioral history and preferences, making it difficult to provide appropriate information that takes into account the user's emotional state.

[0327] 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.

[0328] In this invention, the server includes means for collecting user behavior information, means for integrating the behavior information and generating a detailed profile, means for analyzing the user's emotional state using an emotion engine, means for generating personalized information using a generative AI model, and means for providing feedback to means for collecting and generating user feedback information and optimizing it. This makes it possible to provide highly accurate information that meets the diverse needs and emotional states of users.

[0329] "Behavioral information" refers to data related to a user's online and offline activities, and is a general term for information including purchase history and browsing information.

[0330] A "profile" is a dataset that shows detailed attributes and preferences of a user, generated based on collected behavioral information.

[0331] An "emotion engine" refers to an algorithm or software that analyzes text and audio data to determine a user's emotional state.

[0332] A "generative AI model" is a system or algorithm that uses artificial intelligence technology to generate personalized information or content.

[0333] "Feedback information" refers to data about the reactions and actions that users have taken in response to the information provided, and is used to optimize and improve the system.

[0334] This invention involves a server, terminal, and user collaborating using their respective hardware and software to provide personalized services. The server is responsible for collecting user behavioral information, including web browsing history and in-store purchase history. A relational database management system (such as MySQL or PostgreSQL) is used to securely store this information in a database.

[0335] The server then integrates this behavioral information to generate a detailed user profile. This profile creation utilizes data mining techniques to recognize user preferences and patterns. Additionally, natural language processing (NLP) techniques are used to leverage an emotion engine to determine the user's emotional state from text or audio data.

[0336] The terminal provides users with personalized information supplied by the server. This information is presented through applications and websites, and users can purchase products or use services based on this information. For example, if a user is feeling fatigued, the system can suggest products or services that promote relaxation. In this case, the server inputs a prompt message into the generative model such as, "Generate suggestions for products and services suitable for a specific user who is feeling fatigued."

[0337] Furthermore, the device collects user responses as feedback information and sends it to the server. The server uses this feedback information to optimize the algorithms of the emotion engine and generative AI model. This optimization is performed using machine learning techniques, which can improve the accuracy and relevance of the information provided.

[0338] In this way, the system becomes capable of providing more accurate, personalized services that respond to the diverse needs and emotional states of users.

[0339] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0340] Step 1:

[0341] The server collects user behavior information. It uses the user's web browsing history and in-store purchase history as input. This information is securely stored in a database on the server. Specifically, web tracking tools and POS systems collect the data.

[0342] Step 2:

[0343] The server integrates collected behavioral information to generate user profiles. The input is behavioral information stored in a database. Data processing involves organizing the information, removing duplicates, and extracting user preferences and past behavioral patterns. The output is the generation of a detailed user profile. Specifically, data mining algorithms are applied to identify user interests.

[0344] Step 3:

[0345] The server uses an emotion engine to analyze the user's emotional state. It takes text or audio data obtained from the user as input. For data processing, it utilizes natural language processing techniques to analyze emotions from the text and audio. The output is an evaluation result indicating the user's current emotional state.

[0346] Step 4:

[0347] The server generates personalized information using a generative AI model based on user profiles and emotional states. The inputs used are profile data and emotional analysis results. For data processing, prompts are input to the generative AI model for the target user, generating content tailored to the user's interests. For example, a prompt such as "Suggest the best product for a specific user seeking relaxation" might be input. The output consists of personalized information and product recommendations.

[0348] Step 5:

[0349] The terminal provides personalized information to the user from the server. It uses content received from the server as input. Data processing involves formatting to match the display format of the user interface. The output is the presentation of information to the user. Specifically, this information is presented to the user through a smartphone app or website.

[0350] Step 6:

[0351] The terminal collects user responses as feedback information and sends it to the server. User behavior data and selected options are used as input. Data processing involves collecting and organizing the feedback data. The output is the provision of feedback information to the server.

[0352] Step 7:

[0353] The server optimizes the generative AI model and emotion engine using feedback information. It uses feedback information received from the terminal as input. As data calculation, it uses machine learning algorithms to make adjustments to improve the model's accuracy. The output is the improved model and engine performance. Specifically, the algorithm parameters are adjusted to improve the accuracy of information provided in subsequent instances.

[0354] (Application Example 2)

[0355] 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."

[0356] In today's world, consumers need to choose the best products and services from a wide range of options, but finding the right ones amidst the vast amount of information is difficult. Furthermore, while it's known that consumers' emotional states significantly influence their purchasing decisions, conventional systems have been unable to provide emotionally balanced recommendations. Therefore, there is a need for a system that can provide personalized services using both consumer behavioral and emotional information.

[0357] 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.

[0358] In this invention, the server includes means for collecting user behavior information, means for integrating behavior information and emotional information to generate a profile, and means equipped with an emotion engine for analyzing emotional states. This enables the provision of personalized products and coupons based on the user's preferences and emotions, allowing consumers to make more appropriate choices.

[0359] "Behavioral information" refers to data about the activities that users engage in both online and offline.

[0360] A "profile" is detailed information about an individual user, generated by integrating behavioral and emotional data.

[0361] "Personalized information" refers to information about products and services that is generated based on a user's profile and tailored to the specific needs and interests of that user.

[0362] A "visualization device" is a device used to present information to a user, and in this context refers to smart glasses, etc.

[0363] "Feedback information" refers to data that shows users' reactions and opinions to the information and suggestions they receive.

[0364] An "emotion engine" is a technology that analyzes text and audio to determine the emotional state of a user.

[0365] "Sale information" refers to special discounts and promotional information regarding products and services.

[0366] To realize this invention, the server first collects user behavior information. This behavior information includes online and offline purchase and browsing history. This information is stored in a database and used for analysis. The server analyzes the stored behavior data using data processing techniques with pandas and scikit-learn and generates profiles for individual users.

[0367] Next, the server uses an emotion engine to analyze emotional information from the user's text and voice data. NLTK and Transformers are utilized for this emotional analysis. The analysis results and profiles are integrated to generate personalized information for the user. This generated information is then provided to the user through visualization devices such as smart glasses.

[0368] The terminal helps users select products and services that match their current emotions based on information received from the server. The terminal uses OpenCV and PyQt to provide visually appealing information.

[0369] For example, if a user is feeling stressed, the server might present special discount information or services related to relaxation products. This allows the user to make purchasing choices that align with their emotional state.

[0370] An example of a prompt message is, "Based on past purchase history and current emotional state, please suggest the most suitable products." In this way, the entire system can provide consumers with an efficient and better purchasing experience.

[0371] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0372] Step 1:

[0373] The server collects information on users' online and offline behavior. This information, including purchase and browsing history, is stored in a database. User behavior data is taken as input, and the organized information is stored in the database as output. Specifically, it utilizes website tracking and sales history systems.

[0374] Step 2:

[0375] The server uses pandas and scikit-learn to analyze behavioral data and generate a profile for each user. This profile reveals the user's purchasing patterns and interests, which form the basis for personalized service delivery. The input is behavioral data retrieved from a database, and the output is user-specific profile information.

[0376] Step 3:

[0377] The server processes the user's text and voice data through an emotion engine and analyzes their emotional state using NLTK and Transformers. The input is voice or text data, and the output is information about the user's emotional state. Specifically, this involves analyzing voice recordings and text messages.

[0378] Step 4:

[0379] The server integrates profile information and emotional information to generate personalized information. This generation process utilizes a generative AI model to suggest optimal products and services based on past purchase history and emotional states. The input is profile information and emotional information, and the output is personalized information provided to the user.

[0380] Step 5:

[0381] The terminal receives personalized information transmitted from the server and presents it to the user through a visualization device such as smart glasses. Specifically, it displays the information on a visual display and provides audio guidance as needed. The input is personalized information from the server, and the output is the presentation of information to the user.

[0382] Step 6:

[0383] Users receive personalized information provided by their devices and use it to select products and utilize services. As a result, user feedback is generated. The input is the displayed information, and the output is user behavior and feedback information.

[0384] Step 7:

[0385] The server collects user feedback information and optimizes the algorithms of the emotion engine and generative AI model. This process improves the accuracy and relevance of the information based on the feedback. The input is user feedback, and the output is the improved algorithm model.

[0386] 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.

[0387] 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 those described above. 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 shown 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.

[0388] 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.

[0389] [Third Embodiment]

[0390] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0391] 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.

[0392] 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).

[0393] 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.

[0394] 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.

[0395] 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).

[0396] 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.

[0397] 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.

[0398] 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.

[0399] 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.

[0400] 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.

[0401] 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".

[0402] This invention is a system for collecting user behavior information and providing personalized services. The server, terminal, and user each play their respective roles, ensuring the smooth progress of the overall process.

[0403] The servers use distributed digital technologies to collect user behavior information both online and offline. This information includes browsing history on websites and purchase history at partner stores. This data is encrypted and stored securely.

[0404] Next, the server generates a profile for each user based on the collected behavioral information. This profile reflects the user's preferences and behavioral patterns in detail, forming the basis for generating personalized information.

[0405] Personalized information generated on the server is sent to the terminal. The terminal's role is to present this information to the user. For example, information is provided in the form of coupons or product recommendations based on the user's profile. This allows the user to receive information optimized for them.

[0406] Furthermore, feedback information is acquired that reflects how the user interacted with the information and services provided. The device sends the user's responses to the server. The server analyzes this feedback information and optimizes the generated AI model to improve the accuracy of information in the future.

[0407] As a concrete example, suppose a user expresses interest in healthcare products. The server updates the user's profile based on their purchase history and browsing information, generating coupons for health foods and special promotional offers. This information is presented to the user via their device, allowing them to purchase products using it. Through this entire process, users receive information that directly addresses their personal needs, resulting in a richer experience.

[0408] The following describes the processing flow.

[0409] Step 1:

[0410] The server uses distributed digital technology to collect user behavior information. Specifically, it captures historical data when users browse websites or make purchases in stores and stores it securely stores the data.

[0411] Step 2:

[0412] The server generates individual user profiles from collected behavioral data. These profiles include user preferences, purchase history, and browsing patterns, and are updated in real time with new behavioral information.

[0413] Step 3:

[0414] The AI ​​on the server generates personalized information based on the user profile. For example, it might refer to past purchase data to create discount coupons for specific products.

[0415] Step 4:

[0416] The device provides users with personalized information generated by the server. Through apps and web interfaces, users can view information that matches their personal interests and past behavior.

[0417] Step 5:

[0418] The device records how the user reacts to the information and services presented. For example, it collects information on whether the user actually used a coupon.

[0419] Step 6:

[0420] The server receives feedback information sent from the terminal and optimizes the information generation process through a generation AI. This ensures that future information delivery is even more aligned with user needs.

[0421] (Example 1)

[0422] 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."

[0423] Based on user behavior data, there is a need to build efficient systems to securely provide personalized services and to appropriately deliver personalized information to users. However, conventional systems have been insufficient in the secure collection and analysis of behavior data, and in the generation and provision of personalized information based on user preferences. As a result, improvements in the user experience have been limited, and challenges remain in providing optimal information.

[0424] 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.

[0425] In this invention, the server includes means for encrypting and collecting user behavior information, means for analyzing the behavior information and generating a profile using a generative AI model, and means for creating personalized information based on the profile. This makes it possible to generate and provide safe and appropriate personalized information to the user.

[0426] "User behavior information" refers to the behavioral and contact history associated with individual users, and includes data such as purchase history and browsing information that occurred both online and offline.

[0427] "Encryption" is a process performed to maintain data security, and it refers to converting information into a format that cannot be understood without decryption in order to protect it from unauthorized access.

[0428] A "generative AI model" refers to an algorithm that uses artificial intelligence technology to generate profiles from data, learns and analyzes user behavior and preferences.

[0429] A "profile" is a collection of information that reflects a user's behavioral patterns and preferences, and refers to a data structure that forms the basis for generating personalized information.

[0430] "Personalized information" refers to customized content generated based on a user's profile, including information specific to the user, such as coupons and product recommendations.

[0431] "Feedback information" refers to data that records users' reactions and choices to personalized information and services, and is used to improve the system and enhance its accuracy.

[0432] "Optimization" refers to adjustments and improvements made to enhance the performance and accuracy of a system, and includes improving processes based on user feedback.

[0433] This invention is a system for securely collecting user behavior information and providing personalized information. The system mainly consists of the interaction between a server, a terminal, and a user, and its operation is described in detail below.

[0434] The server uses distributed digital technology to encrypt and collect users' online and offline behavioral information. This behavioral information includes website browsing history and purchase history at partner stores. Specific data processing techniques include browser tracking and POS system data mining. The collected data is stored in a secure database.

[0435] Next, the server uses a high-performance generative AI model to generate a detailed profile of each user based on this behavioral information. This profile helps generate personalized information by analyzing user preferences and patterns through machine learning techniques.

[0436] Next, based on the generated profile, the server creates personalized information and sends it to the terminal. The terminal is responsible for displaying the received information to the user. Personalized information such as coupons and product recommendations are presented to the user through a mobile or web app installed on the terminal. For example, it is possible to provide health-conscious users with discount coupons for health foods identified from their profile.

[0437] Furthermore, the device sends feedback to the server about how the user reacted to the information presented. The server analyzes this feedback and fine-tunes the generating AI model to improve the accuracy of future information provision. An example of a prompt message is, "Recommend the best products based on a specific user's past purchase history."

[0438] This system ensures that users consistently receive valuable information and enhances their personalized experience.

[0439] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0440] Step 1:

[0441] The server collects user behavior information both online and offline. This process tracks web browsing history and in-store purchase history. Specifically, it collects data using browser cookies and in-app tracking tools. The input is user behavior data, and the output is encrypted behavior data. This data is securely stored in a database for use in subsequent processing.

[0442] Step 2:

[0443] The server generates profiles based on collected behavioral data. This process uses a generative AI model to analyze the data and identify user preferences and behavioral patterns. The input is encrypted behavioral data, and the output is a detailed profile for each user. Specifically, machine learning algorithms analyze past purchase history and frequently visited websites to identify user interests.

[0444] Step 3:

[0445] The server creates personalized information based on the generated profile. Using a generative AI model, it generates coupons and product recommendations tailored to the user. The input is the user's profile data, and the output is personalized information. For example, if the profile is determined to be health-conscious, it will generate coupons for suitable health foods.

[0446] Step 4:

[0447] The device presents personalized information received from the server to the user. This information is delivered through notifications and displays in mobile and web applications. The input is personalized information, and the output is the display or notification to the user. Specifically, the device uses push notifications to inform the user of the expiration date of a particular coupon.

[0448] Step 5:

[0449] The device records how the user reacted to the information provided and sends feedback to the server. The input is user reaction data, and the output is feedback data sent to the server. For example, it records whether the user used a coupon they received and sends that information to the server.

[0450] Step 6:

[0451] The server optimizes the generated AI model based on the feedback it receives. This improves the accuracy of information provided in subsequent instances. The input is feedback data, and the output is the optimized AI model. Specifically, it learns new data based on user selections and adjusts the model's parameters.

[0452] (Application Example 1)

[0453] 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."

[0454] There is a need to improve the accuracy of personalized information delivery and provide users with a more valuable purchasing experience. Traditional methods make it difficult to quickly and effectively utilize collected data and appropriately optimize user profiles, making the presentation of highly accurate information and improvement of the user experience a challenge.

[0455] 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.

[0456] In this invention, the server includes means for collecting user behavior information, means for optimizing an artificial intelligence model generated using the feedback, and means for providing special information based on specific behavioral history. This makes it possible to present optimal information tailored to the user's preferences.

[0457] "User" refers to an individual or group that uses this system.

[0458] "Behavioral information" refers to information such as a user's online and offline purchase history and browsing history.

[0459] A "profile" is a set of data generated based on collected behavioral information, reflecting the user's preferences and behavioral patterns.

[0460] "Personalized information" refers to information such as product recommendations and discount coupons that are generated based on a user's profile and are tailored to their needs.

[0461] "Feedback information" refers to data about users' reactions and actions to the information provided.

[0462] A "generating artificial intelligence model" is a machine learning algorithm that generates personalized information based on collected behavioral and feedback data.

[0463] A "special offer" refers to a special offer or promotion made to a user based on their specific behavioral history.

[0464] The system of this invention collects user behavior information and enables personalized services based on that information. The entire process proceeds smoothly when the server, terminal, and user each fulfill their respective roles.

[0465] The server uses cloud infrastructure to collect diverse behavioral information from both online and offline sources, encrypts it, and stores it. This process is implemented using cloud services such as AWS Lambda and Amazon S3. Based on the collected data, the server generates user profiles using a generative AI model on Amazon SageMaker. These profiles include the user's past purchase history and browsing patterns, forming the basis for generating personalized information.

[0466] The device provides users with personalized information transmitted from the server. For example, it may provide discount coupons for specific products or notifications of recommended products. This information is presented to the user's device, such as a smartphone or smart glasses, as a push notification or display within the app.

[0467] Based on the information provided, users choose actions such as purchasing products. Feedback information regarding the user's choices and actions is sent back to the server from the terminal, and the server uses this to optimize the generated AI model. This improves the accuracy of information provided in the future.

[0468] As a concrete example, consider a case where a user is presented with a new coupon for health food based on their past purchase history. If the user uses this coupon to purchase the product, their behavioral information is fed back, and the server uses a generative AI model to help generate more appropriate offers for other users.

[0469] An example of a prompt message is, "Use purchase history data to generate new promotional ideas for diet foods and design notification messages to attract user interest." This can improve the accuracy and effectiveness of promotions.

[0470] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0471] Step 1:

[0472] The server collects user behavior information. Data such as purchase history from websites and partner stores is collected, and the data is anonymized using AWS Lambda. The input is raw behavioral data, and the output is encrypted behavioral information.

[0473] Step 2:

[0474] The server generates a profile based on collected behavioral information. A generative AI model running on Amazon SageMaker analyzes the data and generates a profile that reflects the user's preferences. The input is encrypted behavioral information, and the output is profile data.

[0475] Step 3:

[0476] The server generates personalized information based on the generated profile data. Using the profile as input, it creates recommended products and discount coupons, and structures them as personalized information. The output is personalized information.

[0477] Step 4:

[0478] The device receives personalized information transmitted from the server. This information is displayed to the user via a smartphone or smart glasses and presented as a push notification. The input is personalized information, and the output is the information displayed on the user interface.

[0479] Step 5:

[0480] The user acts on information provided through the device. For example, they might choose to use a coupon presented for purchasing a product. The input is the information displayed on the device, and the output is the user's chosen action.

[0481] Step 6:

[0482] The device sends feedback information about the user's actions to the server. User selections and interaction data are aggregated and sent back to the server. The input is the user's actions (e.g., using a coupon), and the output is feedback data.

[0483] Step 7:

[0484] The server analyzes feedback data and optimizes the generative AI model. Using Google Cloud AI, it generates new prompts and tunes the model to improve the accuracy of information delivery. The input is feedback data, and the output is the optimized generative AI model.

[0485] 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.

[0486] This invention provides a system that delivers personalized services for users, and by incorporating an emotion engine, it enables even more advanced customization. In this invention, the server, terminal, and user each play their respective roles to realize the overall functionality.

[0487] The server first collects information about users' online and offline behavior. This information includes web browsing history and in-store purchase history, and is securely stored in a database. Next, the server integrates the collected behavioral information to create a detailed profile of each user. Using this profile, the server understands the user's interests and preferences and generates personalized information. In this process, an emotion engine is utilized. The emotion engine can analyze text or audio data to determine the user's emotional state.

[0488] The generated personalized information takes emotional information into account and includes content tailored to the user's current emotions. For example, if the server determines that the user is feeling stressed, it can present information and discounts on relaxation products.

[0489] The terminal's role is to provide users with personalized information supplied from the server. This information is presented through applications and websites, and users can purchase products or use services based on that information.

[0490] The device also collects user responses as feedback information and sends it to the server. The server uses this feedback information to optimize the algorithms of the emotion engine and generative AI model, improving the accuracy and relevance of the information it provides.

[0491] As a concrete example, let's assume a user is experiencing fatigue in their daily life. The server, through its emotion engine, interprets the user's emotional state as stress and suggests products and services that promote relaxation. This allows the user to select products that are appropriate for their state and enjoy a personalized experience.

[0492] The following describes the processing flow.

[0493] Step 1:

[0494] The server continuously collects information about users' online and offline activities. It captures data when users browse websites or make purchases at physical stores and stores it in a database.

[0495] Step 2:

[0496] The server integrates the collected behavioral information and generates a profile for each user. This profile includes past purchase history, browsing patterns, and preferences, and is updated in real time.

[0497] Step 3:

[0498] An emotion engine is used to analyze the user's text messages and voice input to understand their current emotional state. For example, it can recognize emotions such as joy, sadness, and stress from voice tone and text content.

[0499] Step 4:

[0500] The server combines the generated user profile and emotional information to create personalized information. It then creates information such as product recommendations and special offers that reflect the user's emotional state. During this process, adjustments are made based on the user's emotions.

[0501] Step 5:

[0502] The device provides users with personalized information. Through applications and websites, for example, it might present users with discount information on products designed to relieve stress.

[0503] Step 6:

[0504] The device records feedback information about how the user utilized the presented information and services. This includes coupon usage and purchase history.

[0505] Step 7:

[0506] The server collects feedback information and optimizes the generative AI model and emotion engine. This process enables the provision of even more accurate personalized information for future use.

[0507] (Example 2)

[0508] 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."

[0509] In today's consumer society, there is a need to establish methods for providing personalized information that meets the diverse needs and emotions of users. However, conventional systems have the challenge of providing limited information based on users' behavioral history and preferences, making it difficult to provide appropriate information that takes into account the user's emotional state.

[0510] 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.

[0511] In this invention, the server includes means for collecting user behavior information, means for integrating the behavior information and generating a detailed profile, means for analyzing the user's emotional state using an emotion engine, means for generating personalized information using a generative AI model, and means for providing feedback to means for collecting and generating user feedback information and optimizing it. This makes it possible to provide highly accurate information that meets the diverse needs and emotional states of users.

[0512] "Behavioral information" refers to data related to a user's online and offline activities, and is a general term for information including purchase history and browsing information.

[0513] A "profile" is a dataset that shows detailed attributes and preferences of a user, generated based on collected behavioral information.

[0514] An "emotion engine" refers to an algorithm or software that analyzes text and audio data to determine a user's emotional state.

[0515] A "generative AI model" is a system or algorithm that uses artificial intelligence technology to generate personalized information or content.

[0516] "Feedback information" refers to data about the reactions and actions that users have taken in response to the information provided, and is used to optimize and improve the system.

[0517] This invention involves a server, terminal, and user collaborating using their respective hardware and software to provide personalized services. The server is responsible for collecting user behavioral information, including web browsing history and in-store purchase history. A relational database management system (such as MySQL or PostgreSQL) is used to securely store this information in a database.

[0518] The server then integrates this behavioral information to generate a detailed user profile. This profile creation utilizes data mining techniques to recognize user preferences and patterns. Additionally, natural language processing (NLP) techniques are used to leverage an emotion engine to determine the user's emotional state from text or audio data.

[0519] The terminal provides users with personalized information supplied by the server. This information is presented through applications and websites, and users can purchase products or use services based on this information. For example, if a user is feeling fatigued, the system can suggest products or services that promote relaxation. In this case, the server inputs a prompt message into the generative model such as, "Generate suggestions for products and services suitable for a specific user who is feeling fatigued."

[0520] Furthermore, the device collects user responses as feedback information and sends it to the server. The server uses this feedback information to optimize the algorithms of the emotion engine and generative AI model. This optimization is performed using machine learning techniques, which can improve the accuracy and relevance of the information provided.

[0521] In this way, the system becomes capable of providing more accurate, personalized services that respond to the diverse needs and emotional states of users.

[0522] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0523] Step 1:

[0524] The server collects user behavior information. It uses the user's web browsing history and in-store purchase history as input. This information is securely stored in a database on the server. Specifically, web tracking tools and POS systems collect the data.

[0525] Step 2:

[0526] The server integrates collected behavioral information to generate user profiles. The input is behavioral information stored in a database. Data processing involves organizing the information, removing duplicates, and extracting user preferences and past behavioral patterns. The output is the generation of a detailed user profile. Specifically, data mining algorithms are applied to identify user interests.

[0527] Step 3:

[0528] The server uses an emotion engine to analyze the user's emotional state. It takes text or audio data obtained from the user as input. For data processing, it utilizes natural language processing techniques to analyze emotions from the text and audio. The output is an evaluation result indicating the user's current emotional state.

[0529] Step 4:

[0530] The server generates personalized information using a generative AI model based on user profiles and emotional states. The inputs used are profile data and emotional analysis results. For data processing, prompts are input to the generative AI model for the target user, generating content tailored to the user's interests. For example, a prompt such as "Suggest the best product for a specific user seeking relaxation" might be input. The output consists of personalized information and product recommendations.

[0531] Step 5:

[0532] The terminal provides personalized information to the user from the server. It uses content received from the server as input. Data processing involves formatting to match the display format of the user interface. The output is the presentation of information to the user. Specifically, this information is presented to the user through a smartphone app or website.

[0533] Step 6:

[0534] The terminal collects user responses as feedback information and sends it to the server. User behavior data and selected options are used as input. Data processing involves collecting and organizing the feedback data. The output is the provision of feedback information to the server.

[0535] Step 7:

[0536] The server optimizes the generative AI model and emotion engine using feedback information. It uses feedback information received from the terminal as input. As data calculation, it uses machine learning algorithms to make adjustments to improve the model's accuracy. The output is the improved model and engine performance. Specifically, the algorithm parameters are adjusted to improve the accuracy of information provided in subsequent instances.

[0537] (Application Example 2)

[0538] 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."

[0539] In today's world, consumers need to choose the best products and services from a wide range of options, but finding the right ones amidst the vast amount of information is difficult. Furthermore, while it's known that consumers' emotional states significantly influence their purchasing decisions, conventional systems have been unable to provide emotionally balanced recommendations. Therefore, there is a need for a system that can provide personalized services using both consumer behavioral and emotional information.

[0540] 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.

[0541] In this invention, the server includes means for collecting user behavior information, means for integrating behavior information and emotional information to generate a profile, and means equipped with an emotion engine for analyzing emotional states. This enables the provision of personalized products and coupons based on the user's preferences and emotions, allowing consumers to make more appropriate choices.

[0542] "Behavioral information" refers to data about the activities that users engage in both online and offline.

[0543] A "profile" is detailed information about an individual user, generated by integrating behavioral and emotional data.

[0544] "Personalized information" refers to information about products and services that is generated based on a user's profile and tailored to the specific needs and interests of that user.

[0545] A "visualization device" is a device used to present information to a user, and in this context refers to smart glasses, etc.

[0546] "Feedback information" refers to data that shows users' reactions and opinions to the information and suggestions they receive.

[0547] An "emotion engine" is a technology that analyzes text and audio to determine the emotional state of a user.

[0548] "Sale information" refers to special discounts and promotional information regarding products and services.

[0549] To realize this invention, the server first collects user behavior information. This behavior information includes online and offline purchase and browsing history. This information is stored in a database and used for analysis. The server analyzes the stored behavior data using data processing techniques with pandas and scikit-learn and generates profiles for individual users.

[0550] Next, the server uses an emotion engine to analyze emotional information from the user's text and voice data. NLTK and Transformers are utilized for this emotional analysis. The analysis results and profiles are integrated to generate personalized information for the user. This generated information is then provided to the user through visualization devices such as smart glasses.

[0551] The terminal helps users select products and services that match their current emotions based on information received from the server. The terminal uses OpenCV and PyQt to provide visually appealing information.

[0552] For example, if a user is feeling stressed, the server might present special discount information or services related to relaxation products. This allows the user to make purchasing choices that align with their emotional state.

[0553] An example of a prompt message is, "Based on past purchase history and current emotional state, please suggest the most suitable products." In this way, the entire system can provide consumers with an efficient and better purchasing experience.

[0554] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0555] Step 1:

[0556] The server collects information on users' online and offline behavior. This information, including purchase and browsing history, is stored in a database. User behavior data is taken as input, and the organized information is stored in the database as output. Specifically, it utilizes website tracking and sales history systems.

[0557] Step 2:

[0558] The server uses pandas and scikit-learn to analyze behavioral data and generate a profile for each user. This profile reveals the user's purchasing patterns and interests, which form the basis for personalized service delivery. The input is behavioral data retrieved from a database, and the output is user-specific profile information.

[0559] Step 3:

[0560] The server processes the user's text and voice data through an emotion engine and analyzes their emotional state using NLTK and Transformers. The input is voice or text data, and the output is information about the user's emotional state. Specifically, this involves analyzing voice recordings and text messages.

[0561] Step 4:

[0562] The server integrates profile information and emotional information to generate personalized information. This generation process utilizes a generative AI model to suggest optimal products and services based on past purchase history and emotional states. The input is profile information and emotional information, and the output is personalized information provided to the user.

[0563] Step 5:

[0564] The terminal receives personalized information transmitted from the server and presents it to the user through a visualization device such as smart glasses. Specifically, it displays the information on a visual display and provides audio guidance as needed. The input is personalized information from the server, and the output is the presentation of information to the user.

[0565] Step 6:

[0566] Users receive personalized information provided by their devices and use it to select products and utilize services. As a result, user feedback is generated. The input is the displayed information, and the output is user behavior and feedback information.

[0567] Step 7:

[0568] The server collects user feedback information and optimizes the algorithms of the emotion engine and generative AI model. This process improves the accuracy and relevance of the information based on the feedback. The input is user feedback, and the output is the improved algorithm model.

[0569] 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.

[0570] 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 those described above. 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 shown 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.

[0571] 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.

[0572] [Fourth Embodiment]

[0573] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0574] 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.

[0575] 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).

[0576] 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.

[0577] 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.

[0578] 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).

[0579] 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.

[0580] 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.

[0581] 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.

[0582] 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.

[0583] 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.

[0584] 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.

[0585] 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".

[0586] This invention is a system for collecting user behavior information and providing personalized services. The server, terminal, and user each play their respective roles, ensuring the smooth progress of the overall process.

[0587] The servers use distributed digital technologies to collect user behavior information both online and offline. This information includes browsing history on websites and purchase history at partner stores. This data is encrypted and stored securely.

[0588] Next, the server generates a profile for each user based on the collected behavioral information. This profile reflects the user's preferences and behavioral patterns in detail, forming the basis for generating personalized information.

[0589] Personalized information generated on the server is sent to the terminal. The terminal's role is to present this information to the user. For example, information is provided in the form of coupons or product recommendations based on the user's profile. This allows the user to receive information optimized for them.

[0590] Furthermore, feedback information is acquired that reflects how the user interacted with the information and services provided. The device sends the user's responses to the server. The server analyzes this feedback information and optimizes the generated AI model to improve the accuracy of information in the future.

[0591] As a concrete example, suppose a user expresses interest in healthcare products. The server updates the user's profile based on their purchase history and browsing information, generating coupons for health foods and special promotional offers. This information is presented to the user via their device, allowing them to purchase products using it. Through this entire process, users receive information that directly addresses their personal needs, resulting in a richer experience.

[0592] The following describes the processing flow.

[0593] Step 1:

[0594] The server uses distributed digital technology to collect user behavior information. Specifically, it captures historical data when users browse websites or make purchases in stores and stores it securely stores the data.

[0595] Step 2:

[0596] The server generates individual user profiles from collected behavioral data. These profiles include user preferences, purchase history, and browsing patterns, and are updated in real time with new behavioral information.

[0597] Step 3:

[0598] The AI ​​on the server generates personalized information based on the user profile. For example, it might refer to past purchase data to create discount coupons for specific products.

[0599] Step 4:

[0600] The device provides users with personalized information generated by the server. Through apps and web interfaces, users can view information that matches their personal interests and past behavior.

[0601] Step 5:

[0602] The device records how the user reacts to the information and services presented. For example, it collects information on whether the user actually used a coupon.

[0603] Step 6:

[0604] The server receives feedback information sent from the terminal and optimizes the information generation process through a generation AI. This ensures that future information delivery is even more aligned with user needs.

[0605] (Example 1)

[0606] 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".

[0607] Based on user behavior data, there is a need to build efficient systems to securely provide personalized services and to appropriately deliver personalized information to users. However, conventional systems have been insufficient in the secure collection and analysis of behavior data, and in the generation and provision of personalized information based on user preferences. As a result, improvements in the user experience have been limited, and challenges remain in providing optimal information.

[0608] 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.

[0609] In this invention, the server includes means for encrypting and collecting user behavior information, means for analyzing the behavior information and generating a profile using a generative AI model, and means for creating personalized information based on the profile. This makes it possible to generate and provide safe and appropriate personalized information to the user.

[0610] "User behavior information" refers to the behavioral and contact history associated with individual users, and includes data such as purchase history and browsing information that occurred both online and offline.

[0611] "Encryption" is a process performed to maintain data security, and it refers to converting information into a format that cannot be understood without decryption in order to protect it from unauthorized access.

[0612] A "generative AI model" refers to an algorithm that uses artificial intelligence technology to generate profiles from data, learns and analyzes user behavior and preferences.

[0613] A "profile" is a collection of information that reflects a user's behavioral patterns and preferences, and refers to a data structure that forms the basis for generating personalized information.

[0614] "Personalized information" refers to customized content generated based on a user's profile, including information specific to the user, such as coupons and product recommendations.

[0615] "Feedback information" refers to data that records users' reactions and choices to personalized information and services, and is used to improve the system and enhance its accuracy.

[0616] "Optimization" refers to adjustments and improvements made to enhance the performance and accuracy of a system, and includes improving processes based on user feedback.

[0617] This invention is a system for securely collecting user behavior information and providing personalized information. The system mainly consists of the interaction between a server, a terminal, and a user, and its operation is described in detail below.

[0618] The server uses distributed digital technology to encrypt and collect users' online and offline behavioral information. This behavioral information includes website browsing history and purchase history at partner stores. Specific data processing techniques include browser tracking and POS system data mining. The collected data is stored in a secure database.

[0619] Next, the server uses a high-performance generative AI model to generate a detailed profile of each user based on this behavioral information. This profile helps generate personalized information by analyzing user preferences and patterns through machine learning techniques.

[0620] Next, based on the generated profile, the server creates personalized information and sends it to the terminal. The terminal is responsible for displaying the received information to the user. Personalized information such as coupons and product recommendations are presented to the user through a mobile or web app installed on the terminal. For example, it is possible to provide health-conscious users with discount coupons for health foods identified from their profile.

[0621] Furthermore, the device sends feedback to the server about how the user reacted to the information presented. The server analyzes this feedback and fine-tunes the generating AI model to improve the accuracy of future information provision. An example of a prompt message is, "Recommend the best products based on a specific user's past purchase history."

[0622] This system ensures that users consistently receive valuable information and enhances their personalized experience.

[0623] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0624] Step 1:

[0625] The server collects user behavior information both online and offline. This process tracks web browsing history and in-store purchase history. Specifically, it collects data using browser cookies and in-app tracking tools. The input is user behavior data, and the output is encrypted behavior data. This data is securely stored in a database for use in subsequent processing.

[0626] Step 2:

[0627] The server generates profiles based on collected behavioral data. This process uses a generative AI model to analyze the data and identify user preferences and behavioral patterns. The input is encrypted behavioral data, and the output is a detailed profile for each user. Specifically, machine learning algorithms analyze past purchase history and frequently visited websites to identify user interests.

[0628] Step 3:

[0629] The server creates personalized information based on the generated profile. Using a generative AI model, it generates coupons and product recommendations tailored to the user. The input is the user's profile data, and the output is personalized information. For example, if the profile is determined to be health-conscious, it will generate coupons for suitable health foods.

[0630] Step 4:

[0631] The device presents personalized information received from the server to the user. This information is delivered through notifications and displays in mobile and web applications. The input is personalized information, and the output is the display or notification to the user. Specifically, the device uses push notifications to inform the user of the expiration date of a particular coupon.

[0632] Step 5:

[0633] The device records how the user reacted to the information provided and sends feedback to the server. The input is user reaction data, and the output is feedback data sent to the server. For example, it records whether the user used a coupon they received and sends that information to the server.

[0634] Step 6:

[0635] The server optimizes the generated AI model based on the feedback it receives. This improves the accuracy of information provided in subsequent instances. The input is feedback data, and the output is the optimized AI model. Specifically, it learns new data based on user selections and adjusts the model's parameters.

[0636] (Application Example 1)

[0637] 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".

[0638] There is a need to improve the accuracy of personalized information delivery and provide users with a more valuable purchasing experience. Traditional methods make it difficult to quickly and effectively utilize collected data and appropriately optimize user profiles, making the presentation of highly accurate information and improvement of the user experience a challenge.

[0639] 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.

[0640] In this invention, the server includes means for collecting user behavior information, means for optimizing an artificial intelligence model generated using the feedback, and means for providing special information based on specific behavioral history. This makes it possible to present optimal information tailored to the user's preferences.

[0641] "User" refers to an individual or group that uses this system.

[0642] "Behavioral information" refers to information such as a user's online and offline purchase history and browsing history.

[0643] A "profile" is a set of data generated based on collected behavioral information, reflecting the user's preferences and behavioral patterns.

[0644] "Personalized information" refers to information such as product recommendations and discount coupons that are generated based on a user's profile and are tailored to their needs.

[0645] "Feedback information" refers to data about users' reactions and actions to the information provided.

[0646] A "generating artificial intelligence model" is a machine learning algorithm that generates personalized information based on collected behavioral and feedback data.

[0647] A "special offer" refers to a special offer or promotion made to a user based on their specific behavioral history.

[0648] The system of this invention collects user behavior information and enables personalized services based on that information. The entire process proceeds smoothly when the server, terminal, and user each fulfill their respective roles.

[0649] The server uses cloud infrastructure to collect diverse behavioral information from both online and offline sources, encrypts it, and stores it. This process is implemented using cloud services such as AWS Lambda and Amazon S3. Based on the collected data, the server generates user profiles using a generative AI model on Amazon SageMaker. These profiles include the user's past purchase history and browsing patterns, forming the basis for generating personalized information.

[0650] The device provides users with personalized information transmitted from the server. For example, it may provide discount coupons for specific products or notifications of recommended products. This information is presented to the user's device, such as a smartphone or smart glasses, as a push notification or display within the app.

[0651] Based on the information provided, users choose actions such as purchasing products. Feedback information regarding the user's choices and actions is sent back to the server from the terminal, and the server uses this to optimize the generated AI model. This improves the accuracy of information provided in the future.

[0652] As a concrete example, consider a case where a user is presented with a new coupon for health food based on their past purchase history. If the user uses this coupon to purchase the product, their behavioral information is fed back, and the server uses a generative AI model to help generate more appropriate offers for other users.

[0653] An example of a prompt message is, "Use purchase history data to generate new promotional ideas for diet foods and design notification messages to attract user interest." This can improve the accuracy and effectiveness of promotions.

[0654] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0655] Step 1:

[0656] The server collects user behavior information. Data such as purchase history from websites and partner stores is collected, and the data is anonymized using AWS Lambda. The input is raw behavioral data, and the output is encrypted behavioral information.

[0657] Step 2:

[0658] The server generates a profile based on collected behavioral information. A generative AI model running on Amazon SageMaker analyzes the data and generates a profile that reflects the user's preferences. The input is encrypted behavioral information, and the output is profile data.

[0659] Step 3:

[0660] The server generates personalized information based on the generated profile data. Using the profile as input, it creates recommended products and discount coupons, and structures them as personalized information. The output is personalized information.

[0661] Step 4:

[0662] The device receives personalized information transmitted from the server. This information is displayed to the user via a smartphone or smart glasses and presented as a push notification. The input is personalized information, and the output is the information displayed on the user interface.

[0663] Step 5:

[0664] The user acts on information provided through the device. For example, they might choose to use a coupon presented for purchasing a product. The input is the information displayed on the device, and the output is the user's chosen action.

[0665] Step 6:

[0666] The device sends feedback information about the user's actions to the server. User selections and interaction data are aggregated and sent back to the server. The input is the user's actions (e.g., using a coupon), and the output is feedback data.

[0667] Step 7:

[0668] The server analyzes feedback data and optimizes the generative AI model. Using Google Cloud AI, it generates new prompts and tunes the model to improve the accuracy of information delivery. The input is feedback data, and the output is the optimized generative AI model.

[0669] 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.

[0670] This invention provides a system that delivers personalized services for users, and by incorporating an emotion engine, it enables even more advanced customization. In this invention, the server, terminal, and user each play their respective roles to realize the overall functionality.

[0671] The server first collects information about users' online and offline behavior. This information includes web browsing history and in-store purchase history, and is securely stored in a database. Next, the server integrates the collected behavioral information to create a detailed profile of each user. Using this profile, the server understands the user's interests and preferences and generates personalized information. In this process, an emotion engine is utilized. The emotion engine can analyze text or audio data to determine the user's emotional state.

[0672] The generated personalized information takes emotional information into account and includes content tailored to the user's current emotions. For example, if the server determines that the user is feeling stressed, it can present information and discounts on relaxation products.

[0673] The terminal's role is to provide users with personalized information supplied from the server. This information is presented through applications and websites, and users can purchase products or use services based on that information.

[0674] The device also collects user responses as feedback information and sends it to the server. The server uses this feedback information to optimize the algorithms of the emotion engine and generative AI model, improving the accuracy and relevance of the information it provides.

[0675] As a concrete example, let's assume a user is experiencing fatigue in their daily life. The server, through its emotion engine, interprets the user's emotional state as stress and suggests products and services that promote relaxation. This allows the user to select products that are appropriate for their state and enjoy a personalized experience.

[0676] The following describes the processing flow.

[0677] Step 1:

[0678] The server continuously collects information about users' online and offline activities. It captures data when users browse websites or make purchases at physical stores and stores it in a database.

[0679] Step 2:

[0680] The server integrates the collected behavioral information and generates a profile for each user. This profile includes past purchase history, browsing patterns, and preferences, and is updated in real time.

[0681] Step 3:

[0682] An emotion engine is used to analyze the user's text messages and voice input to understand their current emotional state. For example, it can recognize emotions such as joy, sadness, and stress from voice tone and text content.

[0683] Step 4:

[0684] The server combines the generated user profile and emotional information to create personalized information. It then creates information such as product recommendations and special offers that reflect the user's emotional state. During this process, adjustments are made based on the user's emotions.

[0685] Step 5:

[0686] The device provides users with personalized information. Through applications and websites, for example, it might present users with discount information on products designed to relieve stress.

[0687] Step 6:

[0688] The device records feedback information about how the user utilized the presented information and services. This includes coupon usage and purchase history.

[0689] Step 7:

[0690] The server collects feedback information and optimizes the generative AI model and emotion engine. This process enables the provision of even more accurate personalized information for future use.

[0691] (Example 2)

[0692] 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".

[0693] In today's consumer society, there is a need to establish methods for providing personalized information that meets the diverse needs and emotions of users. However, conventional systems have the challenge of providing limited information based on users' behavioral history and preferences, making it difficult to provide appropriate information that takes into account the user's emotional state.

[0694] 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.

[0695] In this invention, the server includes means for collecting user behavior information, means for integrating the behavior information and generating a detailed profile, means for analyzing the user's emotional state using an emotion engine, means for generating personalized information using a generative AI model, and means for providing feedback to means for collecting and generating user feedback information and optimizing it. This makes it possible to provide highly accurate information that meets the diverse needs and emotional states of users.

[0696] "Behavioral information" refers to data related to a user's online and offline activities, and is a general term for information including purchase history and browsing information.

[0697] A "profile" is a dataset that shows detailed attributes and preferences of a user, generated based on collected behavioral information.

[0698] An "emotion engine" refers to an algorithm or software that analyzes text and audio data to determine a user's emotional state.

[0699] A "generative AI model" is a system or algorithm that uses artificial intelligence technology to generate personalized information or content.

[0700] "Feedback information" refers to data about the reactions and actions that users have taken in response to the information provided, and is used to optimize and improve the system.

[0701] This invention involves a server, terminal, and user collaborating using their respective hardware and software to provide personalized services. The server is responsible for collecting user behavioral information, including web browsing history and in-store purchase history. A relational database management system (such as MySQL or PostgreSQL) is used to securely store this information in a database.

[0702] The server then integrates this behavioral information to generate a detailed user profile. This profile creation utilizes data mining techniques to recognize user preferences and patterns. Additionally, natural language processing (NLP) techniques are used to leverage an emotion engine to determine the user's emotional state from text or audio data.

[0703] The terminal provides users with personalized information supplied by the server. This information is presented through applications and websites, and users can purchase products or use services based on this information. For example, if a user is feeling fatigued, the system can suggest products or services that promote relaxation. In this case, the server inputs a prompt message into the generative model such as, "Generate suggestions for products and services suitable for a specific user who is feeling fatigued."

[0704] Furthermore, the device collects user responses as feedback information and sends it to the server. The server uses this feedback information to optimize the algorithms of the emotion engine and generative AI model. This optimization is performed using machine learning techniques, which can improve the accuracy and relevance of the information provided.

[0705] In this way, the system becomes capable of providing more accurate, personalized services that respond to the diverse needs and emotional states of users.

[0706] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0707] Step 1:

[0708] The server collects user behavior information. It uses the user's web browsing history and in-store purchase history as input. This information is securely stored in a database on the server. Specifically, web tracking tools and POS systems collect the data.

[0709] Step 2:

[0710] The server integrates collected behavioral information to generate user profiles. The input is behavioral information stored in a database. Data processing involves organizing the information, removing duplicates, and extracting user preferences and past behavioral patterns. The output is the generation of a detailed user profile. Specifically, data mining algorithms are applied to identify user interests.

[0711] Step 3:

[0712] The server uses an emotion engine to analyze the user's emotional state. It takes text or audio data obtained from the user as input. For data processing, it utilizes natural language processing techniques to analyze emotions from the text and audio. The output is an evaluation result indicating the user's current emotional state.

[0713] Step 4:

[0714] The server generates personalized information using a generative AI model based on user profiles and emotional states. The inputs used are profile data and emotional analysis results. For data processing, prompts are input to the generative AI model for the target user, generating content tailored to the user's interests. For example, a prompt such as "Suggest the best product for a specific user seeking relaxation" might be input. The output consists of personalized information and product recommendations.

[0715] Step 5:

[0716] The terminal provides personalized information to the user from the server. It uses content received from the server as input. Data processing involves formatting to match the display format of the user interface. The output is the presentation of information to the user. Specifically, this information is presented to the user through a smartphone app or website.

[0717] Step 6:

[0718] The terminal collects user responses as feedback information and sends it to the server. User behavior data and selected options are used as input. Data processing involves collecting and organizing the feedback data. The output is the provision of feedback information to the server.

[0719] Step 7:

[0720] The server optimizes the generative AI model and emotion engine using feedback information. It uses feedback information received from the terminal as input. As data calculation, it uses machine learning algorithms to make adjustments to improve the model's accuracy. The output is the improved model and engine performance. Specifically, the algorithm parameters are adjusted to improve the accuracy of information provided in subsequent instances.

[0721] (Application Example 2)

[0722] 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".

[0723] In today's world, consumers need to choose the best products and services from a wide range of options, but finding the right ones amidst the vast amount of information is difficult. Furthermore, while it's known that consumers' emotional states significantly influence their purchasing decisions, conventional systems have been unable to provide emotionally balanced recommendations. Therefore, there is a need for a system that can provide personalized services using both consumer behavioral and emotional information.

[0724] 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.

[0725] In this invention, the server includes means for collecting user behavior information, means for integrating behavior information and emotional information to generate a profile, and means equipped with an emotion engine for analyzing emotional states. This enables the provision of personalized products and coupons based on the user's preferences and emotions, allowing consumers to make more appropriate choices.

[0726] "Behavioral information" refers to data about the activities that users engage in both online and offline.

[0727] A "profile" is detailed information about an individual user, generated by integrating behavioral and emotional data.

[0728] "Personalized information" refers to information about products and services that is generated based on a user's profile and tailored to the specific needs and interests of that user.

[0729] A "visualization device" is a device used to present information to a user, and in this context refers to smart glasses, etc.

[0730] "Feedback information" refers to data that shows users' reactions and opinions to the information and suggestions they receive.

[0731] An "emotion engine" is a technology that analyzes text and audio to determine the emotional state of a user.

[0732] "Sale information" refers to special discounts and promotional information regarding products and services.

[0733] To realize this invention, the server first collects user behavior information. This behavior information includes online and offline purchase and browsing history. This information is stored in a database and used for analysis. The server analyzes the stored behavior data using data processing techniques with pandas and scikit-learn and generates profiles for individual users.

[0734] Next, the server uses an emotion engine to analyze emotional information from the user's text and voice data. NLTK and Transformers are utilized for this emotional analysis. The analysis results and profiles are integrated to generate personalized information for the user. This generated information is then provided to the user through visualization devices such as smart glasses.

[0735] The terminal helps users select products and services that match their current emotions based on information received from the server. The terminal uses OpenCV and PyQt to provide visually appealing information.

[0736] For example, if a user is feeling stressed, the server might present special discount information or services related to relaxation products. This allows the user to make purchasing choices that align with their emotional state.

[0737] An example of a prompt message is, "Based on past purchase history and current emotional state, please suggest the most suitable products." In this way, the entire system can provide consumers with an efficient and better purchasing experience.

[0738] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0739] Step 1:

[0740] The server collects information on users' online and offline behavior. This information, including purchase and browsing history, is stored in a database. User behavior data is taken as input, and the organized information is stored in the database as output. Specifically, it utilizes website tracking and sales history systems.

[0741] Step 2:

[0742] The server uses pandas and scikit-learn to analyze behavioral data and generate a profile for each user. This profile reveals the user's purchasing patterns and interests, which form the basis for personalized service delivery. The input is behavioral data retrieved from a database, and the output is user-specific profile information.

[0743] Step 3:

[0744] The server processes the user's text and voice data through an emotion engine and analyzes their emotional state using NLTK and Transformers. The input is voice or text data, and the output is information about the user's emotional state. Specifically, this involves analyzing voice recordings and text messages.

[0745] Step 4:

[0746] The server integrates profile information and emotional information to generate personalized information. This generation process utilizes a generative AI model to suggest optimal products and services based on past purchase history and emotional states. The input is profile information and emotional information, and the output is personalized information provided to the user.

[0747] Step 5:

[0748] The terminal receives personalized information transmitted from the server and presents it to the user through a visualization device such as smart glasses. Specifically, it displays the information on a visual display and provides audio guidance as needed. The input is personalized information from the server, and the output is the presentation of information to the user.

[0749] Step 6:

[0750] Users receive personalized information provided by their devices and use it to select products and utilize services. As a result, user feedback is generated. The input is the displayed information, and the output is user behavior and feedback information.

[0751] Step 7:

[0752] The server collects user feedback information and optimizes the algorithms of the emotion engine and generative AI model. This process improves the accuracy and relevance of the information based on the feedback. The input is user feedback, and the output is the improved algorithm model.

[0753] 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.

[0754] 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 those described above. 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 shown 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.

[0755] 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.

[0756] 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.

[0757] 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.

[0758] 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.

[0759] 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.

[0760] 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.

[0761] 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."

[0762] 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.

[0763] 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.

[0764] 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.

[0765] 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.

[0766] 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.

[0767] 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.

[0768] 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.

[0769] 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.

[0770] 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.

[0771] 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.

[0772] 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.

[0773] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0774] The following is further disclosed regarding the embodiments described above.

[0775] (Claim 1)

[0776] Means for collecting user behavior information,

[0777] Means for integrating the aforementioned behavioral information and generating a profile,

[0778] Means for generating personalized information based on the aforementioned profile,

[0779] The means for providing the personalized information,

[0780] A means for collecting user feedback information and providing feedback to the generating means,

[0781] A system that includes this.

[0782] (Claim 2)

[0783] The system according to claim 1, characterized in that the behavioral information includes online and offline purchase history and browsing information.

[0784] (Claim 3)

[0785] The system according to claim 1, characterized in that the personalized information includes coupons and product recommendations based on the user's preferences.

[0786] "Example 1"

[0787] (Claim 1)

[0788] A means of collecting user behavior information in an encrypted form,

[0789] A means for analyzing the aforementioned behavioral information and generating a profile using a generation AI model,

[0790] Means for creating personalized information based on the aforementioned profile,

[0791] A means for transmitting and presenting the personalized information to the user's terminal,

[0792] A means for collecting user feedback information and providing feedback to optimize the generated AI model,

[0793] A system that includes this.

[0794] (Claim 2)

[0795] The system according to claim 1, characterized in that the behavioral information includes online and offline purchase history and browsing information which are securely stored in a database.

[0796] (Claim 3)

[0797] The system according to claim 1, characterized in that the personalized information includes coupons and product recommendations based on the user's behavior patterns.

[0798] "Application Example 1"

[0799] (Claim 1)

[0800] Means for collecting user behavior information,

[0801] Means for integrating the aforementioned behavioral information and generating a profile,

[0802] Means for generating personalized information based on the aforementioned profile,

[0803] The means for providing the personalized information,

[0804] A means for collecting user feedback information on the information provided and providing feedback to the generating means,

[0805] A means for optimizing the artificial intelligence model generated using the aforementioned feedback,

[0806] A system that includes this.

[0807] (Claim 2)

[0808] The system according to claim 1, characterized in that the behavioral information includes online and offline purchase history and browsing history.

[0809] (Claim 3)

[0810] The system according to claim 1, characterized in that the personalized information includes discount coupons and product recommendations based on the user's preferences, and provides special offers based on specific behavioral history.

[0811] "Example 2 of combining an emotion engine"

[0812] (Claim 1)

[0813] Means for collecting user behavior information,

[0814] A means for integrating the aforementioned behavioral information and generating a detailed profile,

[0815] A means of analyzing a user's emotional state using an emotion engine,

[0816] means for generating personalized information based on the aforementioned profile and emotional state,

[0817] A means of generating personalized information using a generative AI model,

[0818] The means for providing the personalized information,

[0819] A means for collecting user feedback information and providing feedback to the generating means for optimization,

[0820] A system that includes this.

[0821] (Claim 2)

[0822] The system according to claim 1, characterized in that the behavioral information includes online and offline purchase history and browsing information.

[0823] (Claim 3)

[0824] The system according to claim 1, characterized in that the personalized information includes product and service recommendations based on the user's feelings.

[0825] "Application example 2 when combining with an emotional engine"

[0826] (Claim 1)

[0827] Means for collecting user behavior information,

[0828] Means for integrating the aforementioned behavioral information and generating a profile,

[0829] Means for generating personalized information based on the aforementioned profile and emotional information,

[0830] Means for providing the individualized information through a visualization device,

[0831] A means for collecting user feedback information and providing feedback to the generating means,

[0832] A means equipped with an emotion engine that analyzes emotional states,

[0833] A means of presenting sales information that responds to the user's emotions,

[0834] A system that includes this.

[0835] (Claim 2)

[0836] The system according to claim 1, characterized in that the behavioral information includes online and offline purchase history and browsing information.

[0837] (Claim 3)

[0838] The system according to claim 1, characterized in that the personalized information includes coupons and product recommendations based on the user's preferences and emotions. [Explanation of Symbols]

[0839] 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. Means for collecting user behavior information, Means for integrating the aforementioned behavioral information and generating a profile, Means for generating personalized information based on the aforementioned profile, The means for providing the personalized information, A means for collecting user feedback information and providing feedback to the generating means, A system that includes this.

2. The system according to claim 1, characterized in that the behavioral information includes online and offline purchase history and browsing information.

3. The system according to claim 1, characterized in that the personalized information includes coupons and product recommendations based on the user's preferences.

Images