system

Abstract

We provide the system. [Solution] A means of pre-installing a generative AI application on the terminal, means for collecting user behavior data on the aforementioned terminal, Means for transmitting the collected data to a server, The server includes means for analyzing user behavior data integrated with multiple service data, A means for generating recommendation information for users based on analysis results, A means for transmitting the generated recommendation information to the terminal, A means of providing the aforementioned analysis results to multiple services and using them for advertising targeting, A system that includes this.

Description

Technical Field

[0004] , , , ,

[0005] , , , , , ,

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

[0006] A "device" is an electronic device that is directly operated by the user, and includes smartphones, tablets, and other similar devices.

[0007] A "generative AI application" is software that utilizes artificial intelligence to generate content and services based on user input and behavioral history.

[0008] "User behavior data" refers to data related to user actions on their devices, such as text input, clicks, and browsing time.

[0009] A "server" is a computing system used to collect, store, and analyze data from multiple terminals via a network.

[0010] "Service data" refers to data collected from a variety of services (for example, search engines, social media, electronic payment systems, etc.).

[0011] "Analysis results" refer to information obtained by analyzing collected data using AI or machine learning algorithms.

[0012] "Recommendation information" refers to suggestions of content and services that are considered optimal for the user based on analysis results.

[0013] "Push notifications" are a technology that allows a server to send messages and information to a device in real time.

[0014] "Ad targeting" is a technology used to effectively display advertisements to specific user segments. [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]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

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

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

[0018] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), etc.

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

[0020] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disk (e.g., hard disk), or magnetic tape, 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] The system of the present invention performs the following actions through user operation: pre-installation of generative AI applications, collection and transmission of user behavior data to a server, analysis of integrated data, generation and distribution of recommendation information, and advertising targeting. The details are described below.

[0037] Device reset and application pre-installation

[0038] The device comes pre-installed with generative AI applications during initial setup. This allows users to use generative AI applications immediately after initial setup. These applications include, for example, AI assistants and content generation tools.

[0039] Collection of user behavior data

[0040] When a user uses a generative AI application on their device, the application collects user behavior data. This includes text input, clicks, browsing time, and metadata for each action. This data is recorded in real time through a data collection SDK on the device.

[0041] Data transmission and storage

[0042] The device periodically sends collected user behavior data to the server. This data is encrypted and sent to the server via a secure channel. The server stores the received data in an appropriate database and performs data formatting and cleaning as needed.

[0043] Analysis of integrated data

[0044] The server analyzes user behavior data integrated with data from multiple services. This analysis is performed using AI and machine learning algorithms designed by data scientists and engineers. The goal of the analysis is to reveal user interests and behavioral trends and generate optimal recommendation information based on them.

[0045] Generation and distribution of recommendation information

[0046] Based on the analysis results, the server generates recommendation information for the user. For example, it can suggest relevant content or new services based on articles the user has recently read or products they have purchased. The generated recommendation information is sent to the device as a push notification and displayed in real time to attract the user's attention.

[0047] Ad targeting

[0048] The server provides analysis results to multiple services (e.g., advertising networks and electronic payment services). This allows service providers to display personalized ads and promotions to each user. Improved ad targeting accuracy enables ad delivery that better fits user interests.

[0049] User usage examples

[0050] For example, consider a scenario where a user uses an AI assistant app to manage their daily tasks. The user asks the assistant, "Tell me my schedule for tomorrow." The device records this input and sends it to a server. The server integrates and analyzes this data with other user behavior data to generate recommendations for future task management. It then suggests these recommendations to the user by pushing notifications to their device, including links to the latest task management apps and related blog posts.

[0051] The above describes a specific embodiment of the system of the present invention. Through this system, users can receive personalized services and content, and the accuracy of advertising targeting is also improved.

[0052] The following describes the processing flow.

[0053] Step 1:

[0054] When the device undergoes initial setup, generative AI applications are pre-installed. This allows users to immediately use these applications from the moment they first use the device.

[0055] Step 2:

[0056] The user launches a generative AI application and performs text input or touch operations. For example, the user might type "Tell me tomorrow's weather" into the AI ​​assistant.

[0057] Step 3:

[0058] The device collects user input and touch operations as behavioral data. This behavioral data includes entered text, timing of operations, and usage time.

[0059] Step 4:

[0060] The device sends collected behavioral data to the server. The data is encrypted during transmission and sent through a secure communication channel.

[0061] Step 5:

[0062] The server saves the received behavioral data to data storage, where it performs data formatting and cleaning. This converts the data into a unified format.

[0063] Step 6:

[0064] The server integrates data stored on it with data from other services (for example, online shopping purchase history or social media posts).

[0065] Step 7:

[0066] The server analyzes the integrated data. Here, machine learning algorithms and AI are used to analyze user interests and behavioral patterns, identifying user preferences and interests.

[0067] Step 8:

[0068] The server generates optimal recommendation information for the user based on the analysis results. For example, it might generate news articles or new product information in genres the user has been searching for frequently recently.

[0069] Step 9:

[0070] The server sends the generated recommendation information to the device via push notification. This allows users to receive new information in real time.

[0071] Step 10:

[0072] Users check the push notifications they receive and browse and use content and services that interest them. This action is also collected as behavioral data and used to generate subsequent recommendations.

[0073] Step 11:

[0074] The server provides the analysis results to other service providers (e.g., advertising networks and electronic payment services). This allows each service to utilize the analysis results for ad targeting and deliver more effective ads.

[0075] The above outlines the specific processing steps of this system. This process allows users to receive personalized services and content, and enables service providers to achieve highly accurate advertising targeting.

[0076] (Example 1)

[0077] 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."

[0078] Traditional systems require users to individually install applications when setting up a new device. Furthermore, the collection and analysis of user behavior data, and the generation and distribution of recommendation information based on those results, are often not performed smoothly, resulting in insufficient accuracy in ad targeting. Therefore, improving the user experience and achieving effective ad targeting are key challenges.

[0079] 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.

[0080] In this invention, the server includes means for pre-installing a generative AI application on the terminal, means for collecting user behavior data, means for transmitting the collected data to the server, means for analyzing user behavior data integrated with multiple service data, means for generating recommendation information for the user based on the analysis results, means for transmitting the generated recommendation information to the terminal, means for providing the analysis results to multiple services for use in advertising targeting, and means for transmitting the data collected on the terminal to the server via a secure channel and storing it in an encrypted state. As a result, users can use the generative AI application from the initial setup stage, and the collected data is securely transmitted and stored, making it possible to provide users with appropriate and personalized services and advertisements.

[0081] A "terminal" is an electronic device provided for use by a user, capable of running applications and collecting data.

[0082] A "generative AI application" is a software application that uses artificial intelligence to generate text and content.

[0083] "User behavior data" refers to data about the operations and actions users take when using an application, including text input, clicks, and browsing time.

[0084] A "server" is a computer system that stores, processes, and manages data over a network.

[0085] "Recommendation information" refers to information about recommended content and services generated based on a user's past behavioral data.

[0086] A "push notification" is a real-time notification message sent to a user's device.

[0087] "Ad targeting" is a method of displaying the most relevant advertisements to individual users based on analyzed user data.

[0088] A "data collection SDK" is part of a software development kit, consisting of a set of tools and libraries that allow applications to collect user behavior data.

[0089] A "secure channel" is a communication path that uses encryption technology to ensure that data is transmitted safely.

[0090] "Data formatting and cleaning" refers to the process of standardizing the format of collected data and removing unnecessary information.

[0091] "AI and machine learning algorithms" refer to artificial intelligence and machine learning technologies and methods used to extract patterns and insights from large amounts of data.

[0092] The system of the present invention performs the following actions through user operation: pre-installation of generative AI applications, collection and transmission of user behavior data to a server, analysis of integrated data, generation and distribution of recommendation information, and advertising targeting. The details are described below.

[0093] Device reset and application pre-installation

[0094] During initial setup, the device comes pre-installed with a selection of generative AI applications. This allows users to immediately use AI assistants and content generation tools after the device's initial setup. For example, an AI assistant and a text generation tool may be pre-installed. The device's initial setup wizard will launch, and users can choose from pre-installed generative AI applications.

[0095] Collection of user behavior data

[0096] When a user uses a generative AI application, the application collects user behavior data. This data includes text input, click actions, browsing time, and in-app navigation patterns. The device records this data in real time through a data collection SDK. For example, if a user types "Tell me the weather forecast" into an AI assistant, that text and subsequent activity are recorded.

[0097] Data transmission and storage

[0098] The device sends collected user behavior data to the server at regular intervals. Secure channels such as TLS are used for transmission, and the data is encrypted. The server stores the received data in an appropriate database and performs data formatting and cleaning as needed. For example, the device might send data to the server several times a day in batch processing.

[0099] Analysis of integrated data

[0100] The server analyzes user behavior data integrated with data from multiple services. This analysis uses AI and machine learning algorithms designed by data scientists and engineers. The goal of the analysis is to reveal user interests and behavioral trends. For example, the server analyzes a user's browsing history and finds that the user tends to prefer certain genres of content.

[0101] Generation and distribution of recommendation information

[0102] The server generates recommendation information for the user based on the analysis results. This recommendation information includes new suggestions based on content and services the user has previously been interested in. The generated recommendation information is sent to the device as a push notification and displayed to the user in real time. For example, a notification might show new articles related to articles the user has recently read.

[0103] Ad targeting

[0104] The server provides the analysis results to external services such as advertising networks and electronic payment services. These external services then use this data to display personalized ads and promotions to individual users. This process improves the accuracy of ad targeting, displaying ads that are a better fit to the user's interests. For example, ads for related products may be displayed based on products the user has recently purchased.

[0105] Examples of prompt statements

[0106] For example, consider a case where a user asks an AI assistant to "tell me tomorrow's schedule." A concrete example of the prompt in this case would be as follows:

[0107] "Tell me your schedule for tomorrow."

[0108] The device records this input and periodically sends the data to the server. The server analyzes the data and generates recommendations related to the next task management task. These recommendations, such as "new task management apps" or "links to helpful blog posts," are then pushed to the device. Based on this information, the user can install new apps or read articles.

[0109] The above describes a specific embodiment of the system of the present invention. Through this system, users can enjoy personalized services and content, and the accuracy of advertising targeting is also improved.

[0110] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0111] Step 1: Initialize the device and pre-install applications.

[0112] During initial setup, the device comes pre-installed with pre-selected generative AI applications. This allows users to immediately utilize AI assistants and content generation tools after initial setup. For example, when a user completes the initial setup wizard, the AI ​​assistant app is automatically installed. The first input is turning on the device and starting the initial setup. The output is that generative AI applications become available for use.

[0113] Step 2: Collecting user behavior data

[0114] When a user uses a generative AI application, the application collects user behavior data. This includes text input, click actions, and browsing time. Specifically, if a user inputs "Tell me the weather forecast" into the AI ​​assistant, that text and subsequent actions are collected. The device uses a data collection SDK to record behavior data in real time. The input is the user's actions, and the output is the recorded behavior data.

[0115] Step 3: Data transmission and storage

[0116] The terminal sends user behavior data collected at regular intervals to the server. Secure channels such as TLS are used for transmission, and the data is encrypted. The server stores the received data in a database and formats and cleans the data as needed. Specifically, the terminal sends collected data to the server in batches at a fixed time each day, and the server stores the received data in a standardized format. The input is the data sent from the terminal, and the output is organized and cleaned behavior data.

[0117] Step 4: Analysis of integrated data

[0118] The server integrates and analyzes received user behavior data with data from multiple services. This analysis utilizes AI and machine learning algorithms. This process involves models designed by data scientists analyzing user behavior patterns and interests. For example, the server analyzes a user's past browsing history and uses that to identify new content that the user might be interested in. The input is the integrated data, and the output is the analysis result.

[0119] Step 5: Generating and distributing recommendation information

[0120] The server generates recommendation information for the user based on the analysis results. This recommendation information includes suggestions based on content and services the user has previously been interested in. These suggestions are sent to the device as push notifications, for example, in the form of links to new articles or products. Specifically, new articles related to articles the user has recently read are recommended. The input is the analysis results, and the output is the generated recommendation information.

[0121] Step 6: Ad Targeting

[0122] The server provides the results of its user behavior analysis to external advertising networks and electronic payment services. This allows external services to display personalized ads and promotions to users. Specifically, after a user purchases a particular product, ads for related products are displayed. The input is the analysis results data, and the output is the targeting information provided to external services.

[0123] Through these steps, users can enjoy personalized services and the accuracy of ad targeting will improve.

[0124] (Application Example 1)

[0125] 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."

[0126] In modern e-commerce sites, the accuracy of user recommendations and advertising targeting is a challenge. There is a need for systems that can provide more personalized recommendations and advertisements by effectively collecting and appropriately analyzing user behavior data. Furthermore, there is room for improvement in how recommendation information is presented in a way that is more likely to interest users.

[0127] 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.

[0128] In this invention, the server includes means for pre-installing a generative AI application on a terminal, means for collecting user behavior data on the terminal, means for transmitting the collected data to the server, means for analyzing user behavior data integrated with multiple service data on the server, means for generating recommendation information for the user based on the analysis results, means for transmitting the generated recommendation information to the terminal, means for providing the analysis results to multiple services and using them for advertising targeting, means for generating recommendation information based on the user's purchase history and browsing history in an e-commerce site application installed on the terminal, and means for providing the generated recommendation information as a real-time push notification. This enables highly accurate recommendation information and advertising targeting based on the effective collection and analysis of user behavior data.

[0129] A "terminal" refers to an electronic device operated by a user, on which a generative AI application is installed.

[0130] A "generative AI application" is an application that utilizes a generative AI model to generate content based on user behavior data.

[0131] "User behavior data" refers to data about operations and actions performed by users on their devices, including text input, click history, purchase history, and browsing history.

[0132] A "server" is a computing system that analyzes collected user behavior data and performs the necessary processing for creating recommendation information and targeting advertisements.

[0133] "Multiple service data" refers to data provided from different services that is integrated and analyzed with user behavior data.

[0134] "Analysis" is the process of analyzing user behavior data integrated with data from multiple services to reveal user interests and behavioral patterns.

[0135] "Recommendation information" refers to suggested information provided to users based on analysis results, and includes suggestions for related products and services.

[0136] "Push notifications" are a technology that sends information to a device in real time and are used to attract the user's attention.

[0137] "Ad targeting" is a technology that displays effective advertisements based on user behavior data, and is a means of providing personalized advertising.

[0138] "Purchase history" refers to a record of products that a user has previously purchased from an online shopping site.

[0139] "Browsing history" refers to a record of the products a user has viewed on an e-commerce website.

[0140] An "e-commerce site application" is an application installed on a smartphone that users use to search for, browse, and purchase products.

[0141] This invention is a system that provides individually optimized recommendation information and advertising targeting by pre-installing a generative AI application on a terminal and collecting and analyzing user behavior data. The specific configuration and implementation method of the system are described below.

[0142] Program generation

[0143] The server includes a set of programs for collecting user behavior data, sending the data to the server, analyzing the integrated data, generating recommendation information, and performing advertising targeting. These programs are often implemented using programming languages ​​such as Python or Java®.

[0144] Explanation of the process

[0145] The server uses the following hardware and software configuration to collect and analyze data.

[0146] 1. Initial setup of the device:

[0147] The device comes pre-installed with a generative AI application during initial setup. This allows users to start using the application immediately after initializing the device.

[0148] 2. Collection of user behavior data:

[0149] The device collects behavioral data when users utilize generative AI applications. This data includes text input, click history, purchase history, and browsing history. The data is recorded in real time through a data collection software development kit (SDK) on the device.

[0150] 3. Data transmission and storage:

[0151] The device sends collected user behavior data to the server at regular intervals. The data is encrypted and sent to the server via a secure communication channel. The server stores the received data in an appropriate database and performs data formatting and cleaning as needed.

[0152] 4. Analysis of integrated data:

[0153] The server analyzes user behavior data integrated with data from multiple services. It uses AI algorithms and machine learning models designed by data scientists and engineers to reveal user interests and behavioral trends. This analysis utilizes libraries such as Python's Pandas and Scikit-learn.

[0154] 5. Generating recommendation information:

[0155] Based on the analysis results, the server generates recommendation information for the user. For example, it suggests related products based on the categories of items the user has recently purchased. This information is provided to the user via push notifications or in-app messages.

[0156] 6. Ad targeting:

[0157] The server provides analysis results to multiple services and uses them for ad targeting. This ensures that the most relevant ads and promotions are displayed to each user.

[0158] Specific example

[0159] For example, if a user frequently browses electronic devices on an e-commerce application, the server can send push notifications recommending new products within that category. The following example prompt message is used by the server for this purpose.

[0160] Example of a prompt:

[0161] "Please recommend electronic devices to user 123 who has been frequently browsing electronic devices recently. The following is user behavior data for this purpose."

[0162] In this way, by implementing the present invention, the accuracy of recommendation information and advertising targeting for users can be significantly improved.

[0163] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0164] Step 1:

[0165] Initial setup of the device

[0166] The device comes pre-installed with a generative AI application at the time of shipment. Once the user completes the initial setup of the device, this application becomes ready to launch. This allows the user to use the application immediately after the initial setup.

[0167] Input: Initial device setup

[0168] Output: A terminal with a generative AI application installed.

[0169] Step 2:

[0170] Collection of user behavior data

[0171] When a user interacts with a generative AI application, the application collects user behavior data in real time, such as text input, click history, purchase history, and browsing history. This data is recorded using a data collection SDK on the device.

[0172] Input: User actions (text input, clicks, purchases, browsing)

[0173] Output: Collected user behavior data

[0174] Step 3:

[0175] Data transmission and storage

[0176] The device sends collected user behavior data to the server at regular intervals. The data is encrypted and sent to the server via a secure channel such as HTTPS. The server stores the received data in a database and performs data formatting and cleaning as needed.

[0177] Input: Collected user behavior data

[0178] Output: User behavior data stored on the server

[0179] Step 4:

[0180] Analysis of integrated data

[0181] The server integrates user behavior data with data from multiple services. This analysis utilizes AI algorithms and machine learning models designed by data scientists and engineers. Libraries such as Python's Pandas and Scikit-learn are used to reveal user interests and behavioral trends.

[0182] Input: Integrated user behavior data

[0183] Output: Analysis results (user interests and behavioral trends)

[0184] Step 5:

[0185] Recommendation information generation

[0186] Based on the analysis results, the server generates personalized recommendations for each user. For example, related products are suggested based on the categories of items the user has recently purchased or viewed. This information is generated in real time and may be provided in the form of push notifications.

[0187] Input: Analysis results

[0188] Output: Generated recommendation information

[0189] Step 6:

[0190] Providing recommendation information via push notifications

[0191] The device pushes the generated recommendation information to the user. This allows the user to receive new recommendations without having to open the application.

[0192] Input: Generated recommendation information

[0193] Output: Recommendation information pushed to the user.

[0194] Step 7:

[0195] Ad targeting

[0196] Based on the analysis results, the server provides personalized advertising and promotional information to multiple services. This ensures that the most relevant ads are displayed to each user, maximizing the effectiveness of ad targeting.

[0197] Input: Analysis results

[0198] Output: Advertising information provided to the service

[0199] 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.

[0200] The system of the present invention pre-installs generative AI applications through user operation, collects and transmits user behavior data and emotional data to a server, analyzes integrated data, generates and delivers recommendation information, and performs advertising targeting. The details are described below.

[0201] Device reset and application pre-installation

[0202] The device comes pre-installed with generative AI applications during initial setup. This allows users to immediately use these applications from the moment they first use the device. These applications include, for example, AI assistants and content generation tools. Furthermore, an emotion engine is integrated into the device, enabling the collection of user emotion data.

[0203] Collection of user behavior data and emotional data

[0204] When a user uses a generative AI application on their device, the application collects user behavior data. This behavior data includes text input, clicks, and browsing time. Furthermore, the emotion engine analyzes the user's text input and voice data to collect emotion data. This also results in data based on the user's emotional state.

[0205] Data transmission and storage

[0206] The device sends collected behavioral and emotional data to the server. The data is encrypted during transmission and sent through a secure communication channel. The server stores the received data in an appropriate database and performs data formatting and cleaning. This converts the data into a unified format.

[0207] Analysis of integrated data

[0208] The server analyzes user behavior and sentiment data integrated with multiple service data sets. This analysis is performed using AI and machine learning algorithms designed by data scientists and engineers. The goal of the analysis is to reveal users' interests, behavioral patterns, and real-time emotional states, and to generate optimal recommendation information based on this information.

[0209] Generation and distribution of recommendation information

[0210] Based on the analysis results, the server generates optimal recommendation information for the user. For example, if the user is feeling stressed, it can suggest relaxation content, and if they are excited, it can suggest active content. The generated recommendation information is sent to the device as a push notification and displayed in real time to attract the user's attention.

[0211] Ad targeting

[0212] The server provides analysis results to multiple services (e.g., advertising networks and electronic payment services). This allows service providers to display personalized ads and promotions to each user. Improved ad targeting accuracy enables ad delivery that better fits user interests.

[0213] User usage examples

[0214] For example, consider a scenario where a user uses an AI assistant app to manage their daily tasks. The user asks the assistant, "Tell me my schedule for tomorrow." The device records this input and sends it to the server. The emotion engine identifies the user's emotions from the text and tone of voice used in their input, and also sends the results to the server. The server integrates and analyzes the user's emotion data with other behavioral data to generate recommendations for their next task management. It then pushes links to the latest task management apps and related blog posts to the device, suggesting them to the user. If the user is feeling stressed, information to help them relax is also provided.

[0215] The above describes a specific embodiment of the system of the present invention. Through this system, users can receive personalized services and content, and the accuracy of advertising targeting is also improved. By introducing an emotion engine, it is possible to provide more appropriate recommendations according to the user's emotional state.

[0216] The following describes the processing flow.

[0217] Step 1:

[0218] During the initial setup of the device, generative AI applications and an emotion engine are pre-installed. This allows users to immediately use these applications from the moment they first use the device.

[0219] Step 2:

[0220] The user launches a generative AI application and performs actions such as text input, voice input, and touch operations. For example, the user might type "Tell me tomorrow's weather" into the AI ​​assistant.

[0221] Step 3:

[0222] The device collects user input and actions as behavioral data. This behavioral data includes entered text, timing of actions, and usage time.

[0223] Step 4:

[0224] The emotion engine analyzes the user's text input, voice data, facial expression data, etc., to identify the user's emotional state. For example, it can determine whether the user's current emotion is "stress" or "excitement" from the text they input or the audio of their speech.

[0225] Step 5:

[0226] The device sends collected behavioral and emotional data to the server. The data is encrypted during transmission and sent through a secure communication channel.

[0227] Step 6:

[0228] The server stores the received behavioral and emotional data in data storage, and then formats and cleans the data. This converts the data into a unified format.

[0229] Step 7:

[0230] The server integrates data stored on it with data from other services (for example, online shopping purchase history or social media posts).

[0231] Step 8:

[0232] The server analyzes the integrated data. Here, machine learning algorithms and AI are used to analyze users' interests, behavioral patterns, and real-time emotional states to identify user preferences and interests.

[0233] Step 9:

[0234] The server generates optimal recommendation information for the user based on the analysis results. For example, if the user is feeling stressed, it suggests relaxation clips; if they are excited, it suggests active event information.

[0235] Step 10:

[0236] The server sends the generated recommendation information to the device via push notification. This allows users to receive new information in real time.

[0237] Step 11:

[0238] Users check the push notifications they receive and browse and use content and services that interest them. This activity is also collected as behavioral and sentiment data and used to generate subsequent recommendations.

[0239] Step 12:

[0240] The server provides the analysis results to other service providers (e.g., advertising networks and electronic payment services). This allows each service to utilize the analysis results for ad targeting and deliver more effective ads.

[0241] The above outlines the specific processing steps of this system. This process allows users to receive personalized services and content, and enables service providers to achieve highly accurate ad targeting. The introduction of an emotion engine makes it possible to provide more appropriate recommendations based on the user's emotional state.

[0242] (Example 2)

[0243] 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".

[0244] Traditional recommendation and advertising targeting systems analyze user behavior data, including browsing history, to provide recommendations and advertisements. However, they have failed to provide highly accurate recommendations and advertising targeting that take emotional states into account. This is because it is difficult to optimally select content and advertisements according to the user's emotions.

[0245] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for pre-installing a generative AI application on a terminal, means for collecting user behavior data and emotional data on the terminal, means for transmitting the collected data to the server, means for analyzing user behavior data and emotional data integrated with multiple information data on the server, means for generating recommendation information for the user based on the analysis results, means for transmitting the generated recommendation information to the terminal, and means for providing the analysis results to multiple information provision services and using them for advertising targeting. This makes it possible to provide highly accurate recommendation information and advertising targeting according to the user's emotional state.

[0246] A "device" is an electronic device that a user can directly operate, and includes personal computers, smartphones, tablets, and other similar devices.

[0247] "Generative AI applications" are software that utilizes artificial intelligence to generate content based on user input, and include AI assistants and content generation tools.

[0248] "User behavior data" refers to data related to operations and actions performed by users on their devices, including text input, clicks, and browsing time.

[0249] "Emotional data" refers to emotion-related data extracted from user input and voice, and includes information that indicates the user's emotional state (such as joy, anger, sadness, etc.).

[0250] A "server" is a computer system that provides services to terminals via a network, and has the functions of receiving, storing, and analyzing data.

[0251] "Information data" refers to various types of data obtained from servers and other data sources, including user behavior data and sentiment data.

[0252] "Analysis" is the process of finding patterns based on collected data, and it is carried out using AI and machine learning algorithms.

[0253] "Recommendation information" refers to recommended content and suggestions generated by the server based on the user's interests and behavior, and includes information that is sent to the user via push notifications.

[0254] "Ad targeting" is a method of selecting and displaying the most suitable advertisements to users based on analytical data, enabling personalized ad delivery.

[0255] The system of this invention pre-installs a generative AI application on a terminal, collects and analyzes user behavior data and emotional data, and generates and delivers optimal recommendation information to the user based on that data. Furthermore, to improve the accuracy of advertising targeting, the analysis results are provided to multiple information provision services.

[0256] Device reset and application pre-installation

[0257] The device undergoes initial setup upon shipment or first boot-up, and a pre-installation script is executed to install generative AI applications into the system. These applications include, for example, an AI assistant and content generation tools, allowing users to use them immediately from the moment they first use the device. Furthermore, an emotion engine is integrated into the device, ready to collect user emotion data.

[0258] Collection of user behavior data and emotional data

[0259] When a user uses a generative AI application on their device, the application collects user activity logs (text input, clicks, browsing time, etc.) and stores them in a local database. Simultaneously, an emotion engine operates, analyzing the user's text input and voice data in real time. This also collects emotion data indicating the user's emotional state (joy, anger, sadness, etc.).

[0260] Data transmission and storage

[0261] The terminal prepares the collected behavioral and emotional data in batch processing, compresses and encrypts it, and then sends it to the server. A secure communication protocol (e.g., HTTPS) is used in this transmission process. The server stores the received data in an appropriate database (e.g., SQL database, NoSQL database) and performs data formatting and cleaning using an ETL (Extract, Transform, Load) process.

[0262] Analysis of integrated data

[0263] The server analyzes user behavior and sentiment data integrated with multiple data sets. This analysis utilizes AI and machine learning algorithms designed by data scientists and engineers. The goal of the analysis is to reveal users' interests, behavioral patterns, and real-time emotional states, and to generate optimal recommendation information based on this information.

[0264] Generation and distribution of recommendation information

[0265] Based on the analysis results, the server generates optimal recommendation information for the user. For example, if the user is feeling stressed, it suggests relaxation content; if they are excited, it suggests active content. The generated recommendation information is sent to the device in real time as a push notification and displayed to the user.

[0266] Ad targeting

[0267] The server provides analysis results to multiple information providers for use in advertising targeting. This allows service providers to display personalized ads and promotions to each user. Improved accuracy in advertising targeting enables the delivery of ads that better fit user interests.

[0268] User usage examples

[0269] For example, consider a scenario where a user uses an AI assistant app to manage their daily tasks. The user asks the assistant, "Tell me my schedule for tomorrow." The device records this input and sends it to the server. The emotion engine identifies the user's emotions from the text and tone of voice used in their input, and also sends the results to the server. The server integrates and analyzes the user's emotion data with other behavioral data to generate recommendations for their next task management. It then pushes links to the latest task management apps and related blog posts to the device, suggesting them to the user. If the system determines that the user is stressed, it also provides information to help them relax.

[0270] Example of a prompt

[0271] "Assuming the user is in an emotionally unsettled state, please generate recommendations that the AI ​​assistant would make in that situation."

[0272] As described above, the system of the present invention can provide appropriate recommendation information and improve the accuracy of advertising targeting by collecting and analyzing user behavior data and emotional data.

[0273] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0274] Step 1:

[0275] Device initialization and pre-installation of generative AI applications

[0276] Upon initial startup, the device performs an initial setup and installs generative AI applications (e.g., AI assistant, content generation tool, etc.) into the system via a pre-installation script. The input is a device in its factory default state, and the output is a usable device with generative AI applications and an emotion engine installed.

[0277] Step 2:

[0278] Collection of user behavior data and emotional data

[0279] When a user interacts with a generative AI application on their device, the application collects user behavior data (text input, clicks, browsing time, etc.) and stores it in a local database. Simultaneously, the emotion engine analyzes the user's text input and voice data in real time and extracts emotion data. The input consists of user behavior and voice / text data, and the output consists of behavior data and emotion data stored in the local database.

[0280] Step 3:

[0281] Data Preparation and Transmission

[0282] The terminal prepares the collected behavioral data and sentiment data through batch processing, compresses and encrypts the data. Then, it uses a secure communication protocol (e.g., HTTPS) to send the data to the server. As input, there are behavioral data and sentiment data on the local database, and as output, securely encrypted data is sent to the server.

[0283] Step 4:

[0284] Data Storage and Shaping

[0285] The server stores the received data in an appropriate database (e.g., SQL database, NoSQL database) and executes an ETL (Extract, Transform, Load) process to shape and clean the data. As input, there is encrypted data, and as output, clean data converted to a unified format is stored in the database.

[0286] Step 5:

[0287] Analysis of Integrated Data

[0288] The server analyzes multiple information data and integrated user behavioral data and sentiment data. AI and machine learning algorithms are used in this analysis to reveal the user's interests, behavioral patterns, and emotional states. As input, there is integrated user data and information data, and as output, analysis results are obtained.

[0289] Step 6:

[0290] Generation of Recommendation Information

[0291] The server generates optimal recommendation information for the user based on the analysis results. For example, if the user is feeling stressed, it suggests relaxation content; if they are excited, it suggests active content. The input is the analysis results, and the output is the recommendation information suggested to the user.

[0292] Step 7:

[0293] Recommendation information distribution

[0294] The generated recommendation information is sent to the device as a push notification. The user receives this information in real time. The input is the recommendation information, and the output is the push notification displayed on the user's device.

[0295] Step 8:

[0296] Executing ad targeting

[0297] The server provides analysis results to multiple information providers for use in advertising targeting. This allows service providers to display personalized ads and promotions. The input is the analysis results, and the output is targeted ads delivered to the user.

[0298] (Application Example 2)

[0299] 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".

[0300] Traditional e-commerce sites have struggled to effectively utilize user behavioral and emotional data to provide personalized product recommendations in real time. Furthermore, improving the accuracy of advertising targeting based on collected data has also been challenging. This invention aims to solve these problems and provide a system that enables more appropriate and effective product recommendations and advertising to users.

[0301] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting user behavior data and emotional data, means for encrypting the collected data and transmitting it to the server, means for analyzing user behavior data and emotional data integrated with multiple service data, means for generating personalized product recommendation information based on the analysis results, means for pushing the generated recommendation information to the terminal in real time, and means for providing the analysis results to multiple services and using them for advertising targeting. This makes it possible to accurately capture user behavior and emotions and provide personalized product recommendations and advertisements at the appropriate time.

[0302] A "device" is an electronic device designed for use by users, and includes smartphones, tablets, and other similar devices.

[0303] A "generative AI application" is a software application that uses artificial intelligence technology to provide diverse services to users, and has the ability to generate objects, generate content, or provide assistant functions.

[0304] "User behavior data" refers to data that shows a user's operation history and behavioral patterns, and includes text input, clicks, biometric information, and browsing time.

[0305] "Emotional data" refers to data indicating the emotional state of a user, which is information extracted from the tone of voice and the content of text.

[0306] "Server" refers to a computer system that stores, processes, and distributes data on a network.

[0307] "Data encryption" refers to the technology of converting data into a form that cannot be decoded by a third party, ensuring the secure transmission of data.

[0308] "Multiple service data" refers to an aggregate of data collected from different services, which centrally manages the data provided by each service.

[0309] "Recommendation information" refers to information on products or content proposed to a user based on the user's behavior and emotions.

[0310] "Push notification" is a notification function that sends information from a server to a terminal in real time to prompt the user's attention.

[0311] "Advertising targeting" is a method of displaying individually optimized advertisements based on an analysis of user characteristics and behavior.

[0312] The system of the present invention performs pre-installation of a generative AI application through user operations, collection of user behavior data and emotional data, analysis of integrated data, generation and distribution of recommendation information, and advertising targeting. Details thereof will be described below.

[0313] Terminal initialization and pre-installation of an application

[0314] The device comes pre-installed with generative AI applications during initial setup. This allows users to immediately use these applications from the moment they first use the device. These applications include, for example, AI assistants and content generation tools. Furthermore, an emotion engine is integrated into the device, enabling the collection of user emotion data.

[0315] Collection of user behavior data and emotional data

[0316] When a user uses a generative AI application on their device, the application collects user behavioral and emotional data. This behavioral data includes text input, clicks, and browsing time. Furthermore, the emotion engine analyzes the user's text input and voice data to collect emotional data. This also results in data based on the user's emotional state.

[0317] Data transmission and storage

[0318] The device encrypts the collected behavioral and emotional data and sends it to the server. The data is encrypted during transmission and transmitted through a secure communication channel. The server stores the received data in an appropriate database and performs data formatting and cleaning. This converts the data into a unified format.

[0319] Analysis of integrated data

[0320] The server analyzes user behavior and sentiment data integrated with multiple service data sets. This analysis is performed using AI and machine learning algorithms designed by data scientists and engineers. The goal of the analysis is to reveal users' interests, behavioral patterns, and real-time emotional states, and to generate optimal recommendation information based on this information.

[0321] Generation and distribution of recommendation information

[0322] Based on the analysis results, the server generates optimal product recommendations for the user. For example, if the user is feeling stressed, it can suggest relaxation products; if they are excited, it can suggest active products. The generated recommendations are sent to the device as real-time push notifications and displayed immediately to attract the user's attention.

[0323] Ad targeting

[0324] The server provides analysis results to multiple services (e.g., advertising networks and electronic payment services). This allows service providers to display personalized ads and promotions to each user. Improved ad targeting accuracy enables ad delivery that better fits user interests.

[0325] User usage examples

[0326] For example, consider a scenario where a user is browsing an online shopping site using an AI shopping assistant app. The user types, "I'm looking into product A." The device records this input and sends it to the server. The emotion engine identifies the user's emotions from the text and tone of voice used in their input, and also sends the results to the server. The server integrates and analyzes the user's emotion data with other behavioral data to generate recommendations for their next purchase. It then pushes the latest product information and links to related promotions to the device, suggesting them to the user. If the user is excited, information on active products is also provided simultaneously.

[0327] Examples of prompt statements

[0328] Here are some specific examples of prompt statements to input into a generative AI model:

[0329] If a user shows interest in product A, analyze and recommend the following products:

[0330] User input: I am researching product A.

[0331] User's emotion: Excitement

[0332] Product Catalog: ["Product A", "Product B", "Product C"]

[0333] The above describes a specific embodiment of the system of the present invention. Through this system, users can receive personalized services and content, and the accuracy of advertising targeting can also be improved. By introducing an emotion engine, it is possible to provide more appropriate recommendations according to the user's emotional state.

[0334] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0335] Step 1:

[0336] The device comes pre-installed with a generative AI application. The installed application automatically launches during the user's initial setup, ensuring it's ready when the user begins using the device. Here, the input is the device's initial setup, and the output is the state in which the AI ​​application is available for use.

[0337] Step 2:

[0338] When a user begins using a generative AI application on their device, the application collects user behavioral and emotional data. This collection includes behavioral data such as text input, clicks, and browsing time, as well as emotional data derived from voice tone and keyboard typing speed. Here, input is the user's actions, and output is the collected data.

[0339] Step 3:

[0340] The device encrypts the collected behavioral and emotional data and transmits it to the server via a secure communication channel. A data encryption algorithm is used in this process. The input here is the collected data, and the output is the encrypted data.

[0341] Step 4:

[0342] The server stores the received data in the appropriate database and performs data formatting and cleaning. This process includes standardizing the data format and handling missing data values. The input here is encrypted data, and the output is formatted and cleaned data.

[0343] Step 5:

[0344] The server analyzes user behavior and sentiment data integrated with multiple service data sets. AI and machine learning algorithms are used for the analysis to reveal user interests, behavioral patterns, and real-time emotional states. The input here consists of formatted and cleaned data and existing service data, while the output is the analysis results.

[0345] Step 6:

[0346] The server generates personalized product recommendations based on the analysis results. For example, if the user is stressed, it suggests relaxation-related products; if they are agitated, it suggests active products. A generative AI model is used in this process. The input here is the analysis results, and the output is personalized recommendations.

[0347] Step 7:

[0348] The server pushes the generated recommendation information to the device in real time. A push notification protocol is used to ensure that the information reaches the user immediately. The input here is the recommendation information, and the output is the notification to the device.

[0349] Step 8:

[0350] The device displays received push notifications to the user. These notifications contain relevant product links and promotional information, designed for easy user access. Here, the input is the push notification, and the output is the display on the user interface.

[0351] Step 9:

[0352] The server provides analysis results to multiple services (ad networks, electronic payment services, etc.) for use in ad targeting. This allows each service provider to implement personalized ads and promotions for each user. The input here is the analysis results, and the output is personalized ads.

[0353] 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.

[0354] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0355] 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.

[0356] [Second Embodiment]

[0357] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0358] 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.

[0359] 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).

[0360] 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.

[0361] 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.

[0362] 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).

[0363] 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.

[0364] 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.

[0365] 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.

[0366] 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.

[0367] 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.

[0368] 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".

[0369] The system of the present invention performs the following actions through user operation: pre-installation of generative AI applications, collection and transmission of user behavior data to a server, analysis of integrated data, generation and distribution of recommendation information, and advertising targeting. The details are described below.

[0370] Device reset and application pre-installation

[0371] The device comes pre-installed with generative AI applications during initial setup. This allows users to use generative AI applications immediately after initial setup. These applications include, for example, AI assistants and content generation tools.

[0372] Collection of user behavior data

[0373] When a user uses a generative AI application on their device, the application collects user behavior data. This includes text input, clicks, browsing time, and metadata for each action. This data is recorded in real time through a data collection SDK on the device.

[0374] Data transmission and storage

[0375] The device periodically sends collected user behavior data to the server. This data is encrypted and sent to the server via a secure channel. The server stores the received data in an appropriate database and performs data formatting and cleaning as needed.

[0376] Analysis of integrated data

[0377] The server analyzes user behavior data integrated with data from multiple services. This analysis is performed using AI and machine learning algorithms designed by data scientists and engineers. The goal of the analysis is to reveal user interests and behavioral trends and generate optimal recommendation information based on them.

[0378] Generation and distribution of recommendation information

[0379] Based on the analysis results, the server generates recommendation information for the user. For example, it can suggest relevant content or new services based on articles the user has recently read or products they have purchased. The generated recommendation information is sent to the device as a push notification and displayed in real time to attract the user's attention.

[0380] Ad targeting

[0381] The server provides analysis results to multiple services (e.g., advertising networks and electronic payment services). This allows service providers to display personalized ads and promotions to each user. Improved ad targeting accuracy enables ad delivery that better fits user interests.

[0382] User usage examples

[0383] For example, consider a scenario where a user uses an AI assistant app to manage their daily tasks. The user asks the assistant, "Tell me my schedule for tomorrow." The device records this input and sends it to a server. The server integrates and analyzes this data with other user behavior data to generate recommendations for future task management. It then suggests these recommendations to the user by pushing notifications to their device, including links to the latest task management apps and related blog posts.

[0384] The above describes a specific embodiment of the system of the present invention. Through this system, users can receive personalized services and content, and the accuracy of advertising targeting is also improved.

[0385] The following describes the processing flow.

[0386] Step 1:

[0387] When the device undergoes initial setup, generative AI applications are pre-installed. This allows users to immediately use these applications from the moment they first use the device.

[0388] Step 2:

[0389] The user launches a generative AI application and performs text input or touch operations. For example, the user might type "Tell me tomorrow's weather" into the AI ​​assistant.

[0390] Step 3:

[0391] The device collects user input and touch operations as behavioral data. This behavioral data includes entered text, timing of operations, and usage time.

[0392] Step 4:

[0393] The device sends collected behavioral data to the server. The data is encrypted during transmission and sent through a secure communication channel.

[0394] Step 5:

[0395] The server saves the received behavioral data to data storage, where it performs data formatting and cleaning. This converts the data into a unified format.

[0396] Step 6:

[0397] The server integrates data stored on it with data from other services (for example, online shopping purchase history or social media posts).

[0398] Step 7:

[0399] The server analyzes the integrated data. Here, machine learning algorithms and AI are used to analyze user interests and behavioral patterns, identifying user preferences and interests.

[0400] Step 8:

[0401] The server generates optimal recommendation information for the user based on the analysis results. For example, it might generate news articles or new product information in genres the user has been searching for frequently recently.

[0402] Step 9:

[0403] The server sends the generated recommendation information to the device via push notification. This allows users to receive new information in real time.

[0404] Step 10:

[0405] Users check the push notifications they receive and browse and use content and services that interest them. This action is also collected as behavioral data and used to generate subsequent recommendations.

[0406] Step 11:

[0407] The server provides the analysis results to other service providers (e.g., advertising networks and electronic payment services). This allows each service to utilize the analysis results for ad targeting and deliver more effective ads.

[0408] The above outlines the specific processing steps of this system. This process allows users to receive personalized services and content, and enables service providers to achieve highly accurate advertising targeting.

[0409] (Example 1)

[0410] 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".

[0411] Traditional systems require users to individually install applications when setting up a new device. Furthermore, the collection and analysis of user behavior data, and the generation and distribution of recommendation information based on those results, are often not performed smoothly, resulting in insufficient accuracy in ad targeting. Therefore, improving the user experience and achieving effective ad targeting are key challenges.

[0412] 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.

[0413] In this invention, the server includes means for pre-installing a generative AI application on the terminal, means for collecting user behavior data, means for transmitting the collected data to the server, means for analyzing user behavior data integrated with multiple service data, means for generating recommendation information for the user based on the analysis results, means for transmitting the generated recommendation information to the terminal, means for providing the analysis results to multiple services for use in advertising targeting, and means for transmitting the data collected on the terminal to the server via a secure channel and storing it in an encrypted state. As a result, users can use the generative AI application from the initial setup stage, and the collected data is securely transmitted and stored, making it possible to provide users with appropriate and personalized services and advertisements.

[0414] A "terminal" is an electronic device provided for use by a user, capable of running applications and collecting data.

[0415] A "generative AI application" is a software application that uses artificial intelligence to generate text and content.

[0416] "User behavior data" refers to data about the operations and actions users take when using an application, including text input, clicks, and browsing time.

[0417] A "server" is a computer system that stores, processes, and manages data over a network.

[0418] "Recommendation information" refers to information about recommended content and services generated based on a user's past behavioral data.

[0419] A "push notification" is a real-time notification message sent to a user's device.

[0420] "Ad targeting" is a method of displaying the most relevant advertisements to individual users based on analyzed user data.

[0421] A "data collection SDK" is part of a software development kit, consisting of a set of tools and libraries that allow applications to collect user behavior data.

[0422] A "secure channel" is a communication path that uses encryption technology to ensure that data is transmitted safely.

[0423] "Data formatting and cleaning" refers to the process of standardizing the format of collected data and removing unnecessary information.

[0424] "AI and machine learning algorithms" refer to artificial intelligence and machine learning technologies and methods used to extract patterns and insights from large amounts of data.

[0425] The system of the present invention performs the following actions through user operation: pre-installation of generative AI applications, collection and transmission of user behavior data to a server, analysis of integrated data, generation and distribution of recommendation information, and advertising targeting. The details are described below.

[0426] Device reset and application pre-installation

[0427] During initial setup, the device comes pre-installed with a selection of generative AI applications. This allows users to immediately use AI assistants and content generation tools after the device's initial setup. For example, an AI assistant and a text generation tool may be pre-installed. The device's initial setup wizard will launch, and users can choose from pre-installed generative AI applications.

[0428] Collection of user behavior data

[0429] When a user uses a generative AI application, the application collects user behavior data. This data includes text input, click actions, browsing time, and in-app navigation patterns. The device records this data in real time through a data collection SDK. For example, if a user types "Tell me the weather forecast" into an AI assistant, that text and subsequent activity are recorded.

[0430] Data transmission and storage

[0431] The device sends collected user behavior data to the server at regular intervals. Secure channels such as TLS are used for transmission, and the data is encrypted. The server stores the received data in an appropriate database and performs data formatting and cleaning as needed. For example, the device might send data to the server several times a day in batch processing.

[0432] Analysis of integrated data

[0433] The server analyzes user behavior data integrated with data from multiple services. This analysis uses AI and machine learning algorithms designed by data scientists and engineers. The goal of the analysis is to reveal user interests and behavioral trends. For example, the server analyzes a user's browsing history and finds that the user tends to prefer certain genres of content.

[0434] Generation and distribution of recommendation information

[0435] The server generates recommendation information for the user based on the analysis results. This recommendation information includes new suggestions based on content and services the user has previously been interested in. The generated recommendation information is sent to the device as a push notification and displayed to the user in real time. For example, a notification might show new articles related to articles the user has recently read.

[0436] Ad targeting

[0437] The server provides the analysis results to external services such as advertising networks and electronic payment services. These external services then use this data to display personalized ads and promotions to individual users. This process improves the accuracy of ad targeting, displaying ads that are a better fit to the user's interests. For example, ads for related products may be displayed based on products the user has recently purchased.

[0438] Examples of prompt statements

[0439] For example, consider a case where a user asks an AI assistant to "tell me tomorrow's schedule." A concrete example of the prompt in this case would be as follows:

[0440] "Tell me your schedule for tomorrow."

[0441] The device records this input and periodically sends the data to the server. The server analyzes the data and generates recommendations related to the next task management task. These recommendations, such as "new task management apps" or "links to helpful blog posts," are then pushed to the device. Based on this information, the user can install new apps or read articles.

[0442] The above describes a specific embodiment of the system of the present invention. Through this system, users can enjoy personalized services and content, and the accuracy of advertising targeting is also improved.

[0443] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0444] Step 1: Initialize the device and pre-install applications.

[0445] During initial setup, the device comes pre-installed with pre-selected generative AI applications. This allows users to immediately utilize AI assistants and content generation tools after initial setup. For example, when a user completes the initial setup wizard, the AI ​​assistant app is automatically installed. The first input is turning on the device and starting the initial setup. The output is that generative AI applications become available for use.

[0446] Step 2: Collecting user behavior data

[0447] When a user uses a generative AI application, the application collects user behavior data. This includes text input, click actions, and browsing time. Specifically, if a user inputs "Tell me the weather forecast" into the AI ​​assistant, that text and subsequent actions are collected. The device uses a data collection SDK to record behavior data in real time. The input is the user's actions, and the output is the recorded behavior data.

[0448] Step 3: Data transmission and storage

[0449] The terminal sends user behavior data collected at regular intervals to the server. Secure channels such as TLS are used for transmission, and the data is encrypted. The server stores the received data in a database and formats and cleans the data as needed. Specifically, the terminal sends collected data to the server in batches at a fixed time each day, and the server stores the received data in a standardized format. The input is the data sent from the terminal, and the output is organized and cleaned behavior data.

[0450] Step 4: Analysis of integrated data

[0451] The server integrates and analyzes received user behavior data with data from multiple services. This analysis utilizes AI and machine learning algorithms. This process involves models designed by data scientists analyzing user behavior patterns and interests. For example, the server analyzes a user's past browsing history and uses that to identify new content that the user might be interested in. The input is the integrated data, and the output is the analysis result.

[0452] Step 5: Generating and distributing recommendation information

[0453] The server generates recommendation information for the user based on the analysis results. This recommendation information includes suggestions based on content and services the user has previously been interested in. These suggestions are sent to the device as push notifications, for example, in the form of links to new articles or products. Specifically, new articles related to articles the user has recently read are recommended. The input is the analysis results, and the output is the generated recommendation information.

[0454] Step 6: Ad Targeting

[0455] The server provides the results of its user behavior analysis to external advertising networks and electronic payment services. This allows external services to display personalized ads and promotions to users. Specifically, after a user purchases a particular product, ads for related products are displayed. The input is the analysis results data, and the output is the targeting information provided to external services.

[0456] Through these steps, users can enjoy personalized services and the accuracy of ad targeting will improve.

[0457] (Application Example 1)

[0458] 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."

[0459] In modern e-commerce sites, the accuracy of user recommendations and advertising targeting is a challenge. There is a need for systems that can provide more personalized recommendations and advertisements by effectively collecting and appropriately analyzing user behavior data. Furthermore, there is room for improvement in how recommendation information is presented in a way that is more likely to interest users.

[0460] 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.

[0461] In this invention, the server includes means for pre-installing a generative AI application on a terminal, means for collecting user behavior data on the terminal, means for transmitting the collected data to the server, means for analyzing user behavior data integrated with multiple service data on the server, means for generating recommendation information for the user based on the analysis results, means for transmitting the generated recommendation information to the terminal, means for providing the analysis results to multiple services and using them for advertising targeting, means for generating recommendation information based on the user's purchase history and browsing history in an e-commerce site application installed on the terminal, and means for providing the generated recommendation information as a real-time push notification. This enables highly accurate recommendation information and advertising targeting based on the effective collection and analysis of user behavior data.

[0462] A "terminal" refers to an electronic device operated by a user, on which a generative AI application is installed.

[0463] A "generative AI application" is an application that utilizes a generative AI model to generate content based on user behavior data.

[0464] "User behavior data" refers to data about operations and actions performed by users on their devices, including text input, click history, purchase history, and browsing history.

[0465] A "server" is a computing system that analyzes collected user behavior data and performs the necessary processing for creating recommendation information and targeting advertisements.

[0466] "Multiple service data" refers to data provided from different services that is integrated and analyzed with user behavior data.

[0467] "Analysis" is the process of analyzing user behavior data integrated with data from multiple services to reveal user interests and behavioral patterns.

[0468] "Recommendation information" refers to suggested information provided to users based on analysis results, and includes suggestions for related products and services.

[0469] "Push notifications" are a technology that sends information to a device in real time and are used to attract the user's attention.

[0470] "Ad targeting" is a technology that displays effective advertisements based on user behavior data, and is a means of providing personalized advertising.

[0471] "Purchase history" refers to a record of products that a user has previously purchased from an online shopping site.

[0472] "Browsing history" refers to a record of the products a user has viewed on an e-commerce website.

[0473] An "e-commerce site application" is an application installed on a smartphone that users use to search for, browse, and purchase products.

[0474] This invention is a system that provides individually optimized recommendation information and advertising targeting by pre-installing a generative AI application on a terminal and collecting and analyzing user behavior data. The specific configuration and implementation method of the system are described below.

[0475] Program generation

[0476] The server includes a set of programs for collecting user behavior data, sending the data to the server, analyzing the integrated data, generating recommendation information, and performing advertising targeting. These programs are often implemented using programming languages ​​such as Python or Java.

[0477] Explanation of the process

[0478] The server uses the following hardware and software configuration to collect and analyze data.

[0479] 1. Initial setup of the device:

[0480] The device comes pre-installed with a generative AI application during initial setup. This allows users to start using the application immediately after initializing the device.

[0481] 2. Collection of user behavior data:

[0482] The device collects behavioral data when users utilize generative AI applications. This data includes text input, click history, purchase history, and browsing history. The data is recorded in real time through a data collection software development kit (SDK) on the device.

[0483] 3. Data transmission and storage:

[0484] The device sends collected user behavior data to the server at regular intervals. The data is encrypted and sent to the server via a secure communication channel. The server stores the received data in an appropriate database and performs data formatting and cleaning as needed.

[0485] 4. Analysis of integrated data:

[0486] The server analyzes user behavior data integrated with data from multiple services. It uses AI algorithms and machine learning models designed by data scientists and engineers to reveal user interests and behavioral trends. This analysis utilizes libraries such as Python's Pandas and Scikit-learn.

[0487] 5. Generating recommendation information:

[0488] Based on the analysis results, the server generates recommendation information for the user. For example, it suggests related products based on the categories of items the user has recently purchased. This information is provided to the user via push notifications or in-app messages.

[0489] 6. Ad targeting:

[0490] The server provides analysis results to multiple services and uses them for ad targeting. This ensures that the most relevant ads and promotions are displayed to each user.

[0491] Specific example

[0492] For example, if a user frequently browses electronic devices on an e-commerce application, the server can send push notifications recommending new products within that category. The following example prompt message is used by the server for this purpose.

[0493] Example of a prompt:

[0494] "Please recommend electronic devices to user 123 who has been frequently browsing electronic devices recently. The following is user behavior data for this purpose."

[0495] In this way, by implementing the present invention, the accuracy of recommendation information and advertising targeting for users can be significantly improved.

[0496] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0497] Step 1:

[0498] Initial setup of the device

[0499] The device comes pre-installed with a generative AI application at the time of shipment. Once the user completes the initial setup of the device, this application becomes ready to launch. This allows the user to use the application immediately after the initial setup.

[0500] Input: Initial device setup

[0501] Output: A terminal with a generative AI application installed.

[0502] Step 2:

[0503] Collection of user behavior data

[0504] When a user interacts with a generative AI application, the application collects user behavior data in real time, such as text input, click history, purchase history, and browsing history. This data is recorded using a data collection SDK on the device.

[0505] Input: User actions (text input, clicks, purchases, browsing)

[0506] Output: Collected user behavior data

[0507] Step 3:

[0508] Data transmission and storage

[0509] The device sends collected user behavior data to the server at regular intervals. The data is encrypted and sent to the server via a secure channel such as HTTPS. The server stores the received data in a database and performs data formatting and cleaning as needed.

[0510] Input: Collected user behavior data

[0511] Output: User behavior data stored on the server

[0512] Step 4:

[0513] Analysis of integrated data

[0514] The server integrates user behavior data with data from multiple services. This analysis utilizes AI algorithms and machine learning models designed by data scientists and engineers. Libraries such as Python's Pandas and Scikit-learn are used to reveal user interests and behavioral trends.

[0515] Input: Integrated user behavior data

[0516] Output: Analysis results (user interests and behavioral trends)

[0517] Step 5:

[0518] Recommendation information generation

[0519] Based on the analysis results, the server generates personalized recommendations for each user. For example, related products are suggested based on the categories of items the user has recently purchased or viewed. This information is generated in real time and may be provided in the form of push notifications.

[0520] Input: Analysis results

[0521] Output: Generated recommendation information

[0522] Step 6:

[0523] Providing recommendation information via push notifications

[0524] The device pushes the generated recommendation information to the user. This allows the user to receive new recommendations without having to open the application.

[0525] Input: Generated recommendation information

[0526] Output: Recommendation information pushed to the user.

[0527] Step 7:

[0528] Ad targeting

[0529] Based on the analysis results, the server provides personalized advertising and promotional information to multiple services. This ensures that the most relevant ads are displayed to each user, maximizing the effectiveness of ad targeting.

[0530] Input: Analysis results

[0531] Output: Advertising information provided to the service

[0532] 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.

[0533] The system of the present invention pre-installs generative AI applications through user operation, collects and transmits user behavior data and emotional data to a server, analyzes integrated data, generates and delivers recommendation information, and performs advertising targeting. The details are described below.

[0534] Device reset and application pre-installation

[0535] The device comes pre-installed with generative AI applications during initial setup. This allows users to immediately use these applications from the moment they first use the device. These applications include, for example, AI assistants and content generation tools. Furthermore, an emotion engine is integrated into the device, enabling the collection of user emotion data.

[0536] Collection of user behavior data and emotional data

[0537] When a user uses a generative AI application on their device, the application collects user behavior data. This behavior data includes text input, clicks, and browsing time. Furthermore, the emotion engine analyzes the user's text input and voice data to collect emotion data. This also results in data based on the user's emotional state.

[0538] Data transmission and storage

[0539] The device sends collected behavioral and emotional data to the server. The data is encrypted during transmission and sent through a secure communication channel. The server stores the received data in an appropriate database and performs data formatting and cleaning. This converts the data into a unified format.

[0540] Analysis of integrated data

[0541] The server analyzes user behavior and sentiment data integrated with multiple service data sets. This analysis is performed using AI and machine learning algorithms designed by data scientists and engineers. The goal of the analysis is to reveal users' interests, behavioral patterns, and real-time emotional states, and to generate optimal recommendation information based on this information.

[0542] Generation and distribution of recommendation information

[0543] Based on the analysis results, the server generates optimal recommendation information for the user. For example, if the user is feeling stressed, it can suggest relaxation content, and if they are excited, it can suggest active content. The generated recommendation information is sent to the device as a push notification and displayed in real time to attract the user's attention.

[0544] Ad targeting

[0545] The server provides analysis results to multiple services (e.g., advertising networks and electronic payment services). This allows service providers to display personalized ads and promotions to each user. Improved ad targeting accuracy enables ad delivery that better fits user interests.

[0546] User usage examples

[0547] For example, consider a scenario where a user uses an AI assistant app to manage their daily tasks. The user asks the assistant, "Tell me my schedule for tomorrow." The device records this input and sends it to the server. The emotion engine identifies the user's emotions from the text and tone of voice used in their input, and also sends the results to the server. The server integrates and analyzes the user's emotion data with other behavioral data to generate recommendations for their next task management. It then pushes links to the latest task management apps and related blog posts to the device, suggesting them to the user. If the user is feeling stressed, information to help them relax is also provided.

[0548] The above describes a specific embodiment of the system of the present invention. Through this system, users can receive personalized services and content, and the accuracy of advertising targeting is also improved. By introducing an emotion engine, it is possible to provide more appropriate recommendations according to the user's emotional state.

[0549] The following describes the processing flow.

[0550] Step 1:

[0551] During the initial setup of the device, generative AI applications and an emotion engine are pre-installed. This allows users to immediately use these applications from the moment they first use the device.

[0552] Step 2:

[0553] The user launches a generative AI application and performs actions such as text input, voice input, and touch operations. For example, the user might type "Tell me tomorrow's weather" into the AI ​​assistant.

[0554] Step 3:

[0555] The device collects user input and actions as behavioral data. This behavioral data includes entered text, timing of actions, and usage time.

[0556] Step 4:

[0557] The emotion engine analyzes the user's text input, voice data, facial expression data, etc., to identify the user's emotional state. For example, it can determine whether the user's current emotion is "stress" or "excitement" from the text they input or the audio of their speech.

[0558] Step 5:

[0559] The device sends collected behavioral and emotional data to the server. The data is encrypted during transmission and sent through a secure communication channel.

[0560] Step 6:

[0561] The server stores the received behavioral and emotional data in data storage, and then formats and cleans the data. This converts the data into a unified format.

[0562] Step 7:

[0563] The server integrates data stored on it with data from other services (for example, online shopping purchase history or social media posts).

[0564] Step 8:

[0565] The server analyzes the integrated data. Here, machine learning algorithms and AI are used to analyze users' interests, behavioral patterns, and real-time emotional states to identify user preferences and interests.

[0566] Step 9:

[0567] The server generates optimal recommendation information for the user based on the analysis results. For example, if the user is feeling stressed, it suggests relaxation clips; if they are excited, it suggests active event information.

[0568] Step 10:

[0569] The server sends the generated recommendation information to the device via push notification. This allows users to receive new information in real time.

[0570] Step 11:

[0571] Users check the push notifications they receive and browse and use content and services that interest them. This activity is also collected as behavioral and sentiment data and used to generate subsequent recommendations.

[0572] Step 12:

[0573] The server provides the analysis results to other service providers (e.g., advertising networks and electronic payment services). This allows each service to utilize the analysis results for ad targeting and deliver more effective ads.

[0574] The above outlines the specific processing steps of this system. This process allows users to receive personalized services and content, and enables service providers to achieve highly accurate ad targeting. The introduction of an emotion engine makes it possible to provide more appropriate recommendations based on the user's emotional state.

[0575] (Example 2)

[0576] 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".

[0577] Traditional recommendation and advertising targeting systems analyze user behavior data, including browsing history, to provide recommendations and advertisements. However, they have failed to provide highly accurate recommendations and advertising targeting that take emotional states into account. This is because it is difficult to optimally select content and advertisements according to the user's emotions.

[0578] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for pre-installing a generative AI application on a terminal, means for collecting user behavior data and emotional data on the terminal, means for transmitting the collected data to the server, means for analyzing user behavior data and emotional data integrated with multiple information data on the server, means for generating recommendation information for the user based on the analysis results, means for transmitting the generated recommendation information to the terminal, and means for providing the analysis results to multiple information provision services and using them for advertising targeting. This makes it possible to provide highly accurate recommendation information and advertising targeting according to the user's emotional state.

[0579] A "device" is an electronic device that a user can directly operate, and includes personal computers, smartphones, tablets, and other similar devices.

[0580] "Generative AI applications" are software that utilizes artificial intelligence to generate content based on user input, and include AI assistants and content generation tools.

[0581] "User behavior data" refers to data related to operations and actions performed by users on their devices, including text input, clicks, and browsing time.

[0582] "Emotional data" refers to emotion-related data extracted from user input and voice, and includes information that indicates the user's emotional state (such as joy, anger, sadness, etc.).

[0583] A "server" is a computer system that provides services to terminals via a network, and has the functions of receiving, storing, and analyzing data.

[0584] "Information data" refers to various types of data obtained from servers and other data sources, including user behavior data and sentiment data.

[0585] "Analysis" is the process of finding patterns based on collected data, and it is carried out using AI and machine learning algorithms.

[0586] "Recommendation information" refers to recommended content and suggestions generated by the server based on the user's interests and behavior, and includes information that is sent to the user via push notifications.

[0587] "Ad targeting" is a method of selecting and displaying the most suitable advertisements to users based on analytical data, enabling personalized ad delivery.

[0588] The system of this invention pre-installs a generative AI application on a terminal, collects and analyzes user behavior data and emotional data, and generates and delivers optimal recommendation information to the user based on that data. Furthermore, to improve the accuracy of advertising targeting, the analysis results are provided to multiple information provision services.

[0589] Device reset and application pre-installation

[0590] The device undergoes initial setup upon shipment or first boot-up, and a pre-installation script is executed to install generative AI applications into the system. These applications include, for example, an AI assistant and content generation tools, allowing users to use them immediately from the moment they first use the device. Furthermore, an emotion engine is integrated into the device, ready to collect user emotion data.

[0591] Collection of user behavior data and emotional data

[0592] When a user uses a generative AI application on their device, the application collects user activity logs (text input, clicks, browsing time, etc.) and stores them in a local database. Simultaneously, an emotion engine operates, analyzing the user's text input and voice data in real time. This also collects emotion data indicating the user's emotional state (joy, anger, sadness, etc.).

[0593] Data transmission and storage

[0594] The terminal prepares the collected behavioral and emotional data in batch processing, compresses and encrypts it, and then sends it to the server. A secure communication protocol (e.g., HTTPS) is used in this transmission process. The server stores the received data in an appropriate database (e.g., SQL database, NoSQL database) and performs data formatting and cleaning using an ETL (Extract, Transform, Load) process.

[0595] Analysis of integrated data

[0596] The server analyzes user behavior and sentiment data integrated with multiple data sets. This analysis utilizes AI and machine learning algorithms designed by data scientists and engineers. The goal of the analysis is to reveal users' interests, behavioral patterns, and real-time emotional states, and to generate optimal recommendation information based on this information.

[0597] Generation and distribution of recommendation information

[0598] Based on the analysis results, the server generates optimal recommendation information for the user. For example, if the user is feeling stressed, it suggests relaxation content; if they are excited, it suggests active content. The generated recommendation information is sent to the device in real time as a push notification and displayed to the user.

[0599] Ad targeting

[0600] The server provides analysis results to multiple information providers for use in advertising targeting. This allows service providers to display personalized ads and promotions to each user. Improved accuracy in advertising targeting enables the delivery of ads that better fit user interests.

[0601] User usage examples

[0602] For example, consider a scenario where a user uses an AI assistant app to manage their daily tasks. The user asks the assistant, "Tell me my schedule for tomorrow." The device records this input and sends it to the server. The emotion engine identifies the user's emotions from the text and tone of voice used in their input, and also sends the results to the server. The server integrates and analyzes the user's emotion data with other behavioral data to generate recommendations for their next task management. It then pushes links to the latest task management apps and related blog posts to the device, suggesting them to the user. If the system determines that the user is stressed, it also provides information to help them relax.

[0603] Example of a prompt

[0604] "Assuming the user is in an emotionally unsettled state, please generate recommendations that the AI ​​assistant would make in that situation."

[0605] As described above, the system of the present invention can provide appropriate recommendation information and improve the accuracy of advertising targeting by collecting and analyzing user behavior data and emotional data.

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

[0607] Step 1:

[0608] Device initialization and pre-installation of generative AI applications

[0609] Upon initial startup, the device performs an initial setup and installs generative AI applications (e.g., AI assistant, content generation tool, etc.) into the system via a pre-installation script. The input is a device in its factory default state, and the output is a usable device with generative AI applications and an emotion engine installed.

[0610] Step 2:

[0611] Collection of user behavior data and emotional data

[0612] When a user interacts with a generative AI application on their device, the application collects user behavior data (text input, clicks, browsing time, etc.) and stores it in a local database. Simultaneously, the emotion engine analyzes the user's text input and voice data in real time and extracts emotion data. The input consists of user behavior and voice / text data, and the output consists of behavior data and emotion data stored in the local database.

[0613] Step 3:

[0614] Data preparation and transmission

[0615] The terminal prepares the collected behavioral and sentimental data in batch processing, compressing and encrypting the data. It then sends the data to the server using a secure communication protocol (e.g., HTTPS). The input consists of behavioral and sentimental data in a local database, and the output is securely encrypted data sent to the server.

[0616] Step 4:

[0617] Data storage and formatting

[0618] The server stores the received data in an appropriate database (e.g., SQL database, NoSQL database) and performs an ETL (Extract, Transform, Load) process to format and clean the data. The input is encrypted data, and the output is clean data converted to a unified format, which is then stored in the database.

[0619] Step 5:

[0620] Analysis of integrated data

[0621] The server analyzes user behavior data and sentiment data integrated with multiple pieces of informational data. This analysis utilizes AI and machine learning algorithms to reveal user interests, behavioral patterns, and emotional states. The input consists of integrated user data and informational data, and the output is the analysis results.

[0622] Step 6:

[0623] Recommendation information generation

[0624] The server generates optimal recommendation information for the user based on the analysis results. For example, if the user is feeling stressed, it suggests relaxation content; if they are excited, it suggests active content. The input is the analysis results, and the output is the recommendation information suggested to the user.

[0625] Step 7:

[0626] Recommendation information distribution

[0627] The generated recommendation information is sent to the device as a push notification. The user receives this information in real time. The input is the recommendation information, and the output is the push notification displayed on the user's device.

[0628] Step 8:

[0629] Executing ad targeting

[0630] The server provides analysis results to multiple information providers for use in advertising targeting. This allows service providers to display personalized ads and promotions. The input is the analysis results, and the output is targeted ads delivered to the user.

[0631] (Application Example 2)

[0632] 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."

[0633] Traditional e-commerce sites have struggled to effectively utilize user behavioral and emotional data to provide personalized product recommendations in real time. Furthermore, improving the accuracy of advertising targeting based on collected data has also been challenging. This invention aims to solve these problems and provide a system that enables more appropriate and effective product recommendations and advertising to users.

[0634] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting user behavior data and emotional data, means for encrypting the collected data and transmitting it to the server, means for analyzing user behavior data and emotional data integrated with multiple service data, means for generating personalized product recommendation information based on the analysis results, means for pushing the generated recommendation information to the terminal in real time, and means for providing the analysis results to multiple services and using them for advertising targeting. This makes it possible to accurately capture user behavior and emotions and provide personalized product recommendations and advertisements at the appropriate time.

[0635] A "device" is an electronic device designed for use by users, and includes smartphones, tablets, and other similar devices.

[0636] A "generative AI application" is a software application that uses artificial intelligence technology to provide diverse services to users, and has the ability to generate objects, generate content, or provide assistant functions.

[0637] "User behavior data" refers to data that shows a user's operation history and behavioral patterns, and includes text input, clicks, biometric information, and browsing time.

[0638] "Emotional data" refers to data that indicates a user's emotional state, and is information extracted from voice tone and text content.

[0639] A "server" is a computer system that stores, processes, and distributes data over a network.

[0640] "Data encryption" refers to the technology of converting data into a format that cannot be deciphered by third parties, thereby ensuring the secure transmission of data.

[0641] "Multiple service data" refers to a collection of data gathered from different services, and involves centrally managing the data provided by each service.

[0642] "Recommendation information" refers to information about products and content that is suggested to users based on their behavior and emotions.

[0643] "Push notifications" are a notification function that sends information from a server to a device in real time to alert the user.

[0644] "Ad targeting" is a method of displaying individually optimized advertisements based on user characteristics and behavioral analysis.

[0645] The system of the present invention pre-installs generative AI applications through user operation, collects user behavior data and emotional data, analyzes integrated data, generates and delivers recommendation information, and performs advertising targeting. The details are described below.

[0646] Device reset and application pre-installation

[0647] The device comes pre-installed with generative AI applications during initial setup. This allows users to immediately use these applications from the moment they first use the device. These applications include, for example, AI assistants and content generation tools. Furthermore, an emotion engine is integrated into the device, enabling the collection of user emotion data.

[0648] Collection of user behavior data and emotional data

[0649] When a user uses a generative AI application on their device, the application collects user behavioral and emotional data. This behavioral data includes text input, clicks, and browsing time. Furthermore, the emotion engine analyzes the user's text input and voice data to collect emotional data. This also results in data based on the user's emotional state.

[0650] Data transmission and storage

[0651] The device encrypts the collected behavioral and emotional data and sends it to the server. The data is encrypted during transmission and transmitted through a secure communication channel. The server stores the received data in an appropriate database and performs data formatting and cleaning. This converts the data into a unified format.

[0652] Analysis of integrated data

[0653] The server analyzes user behavior and sentiment data integrated with multiple service data sets. This analysis is performed using AI and machine learning algorithms designed by data scientists and engineers. The goal of the analysis is to reveal users' interests, behavioral patterns, and real-time emotional states, and to generate optimal recommendation information based on this information.

[0654] Generation and distribution of recommendation information

[0655] Based on the analysis results, the server generates optimal product recommendations for the user. For example, if the user is feeling stressed, it can suggest relaxation products; if they are excited, it can suggest active products. The generated recommendations are sent to the device as real-time push notifications and displayed immediately to attract the user's attention.

[0656] Ad targeting

[0657] The server provides analysis results to multiple services (e.g., advertising networks and electronic payment services). This allows service providers to display personalized ads and promotions to each user. Improved ad targeting accuracy enables ad delivery that better fits user interests.

[0658] User usage examples

[0659] For example, consider a scenario where a user is browsing an online shopping site using an AI shopping assistant app. The user types, "I'm looking into product A." The device records this input and sends it to the server. The emotion engine identifies the user's emotions from the text and tone of voice used in their input, and also sends the results to the server. The server integrates and analyzes the user's emotion data with other behavioral data to generate recommendations for their next purchase. It then pushes the latest product information and links to related promotions to the device, suggesting them to the user. If the user is excited, information on active products is also provided simultaneously.

[0660] Examples of prompt statements

[0661] Here are some specific examples of prompt statements to input into a generative AI model:

[0662] If a user shows interest in product A, analyze and recommend the following products:

[0663] User input: I am researching product A.

[0664] User's emotion: Excitement

[0665] Product Catalog: ["Product A", "Product B", "Product C"]

[0666] The above describes a specific embodiment of the system of the present invention. Through this system, users can receive personalized services and content, and the accuracy of advertising targeting can also be improved. By introducing an emotion engine, it is possible to provide more appropriate recommendations according to the user's emotional state.

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

[0668] Step 1:

[0669] The device comes pre-installed with a generative AI application. The installed application automatically launches during the user's initial setup, ensuring it's ready when the user begins using the device. Here, the input is the device's initial setup, and the output is the state in which the AI ​​application is available for use.

[0670] Step 2:

[0671] When a user begins using a generative AI application on their device, the application collects user behavioral and emotional data. This collection includes behavioral data such as text input, clicks, and browsing time, as well as emotional data derived from voice tone and keyboard typing speed. Here, input is the user's actions, and output is the collected data.

[0672] Step 3:

[0673] The device encrypts the collected behavioral and emotional data and transmits it to the server via a secure communication channel. A data encryption algorithm is used in this process. The input here is the collected data, and the output is the encrypted data.

[0674] Step 4:

[0675] The server stores the received data in the appropriate database and performs data formatting and cleaning. This process includes standardizing the data format and handling missing data values. The input here is encrypted data, and the output is formatted and cleaned data.

[0676] Step 5:

[0677] The server analyzes user behavior and sentiment data integrated with multiple service data sets. AI and machine learning algorithms are used for the analysis to reveal user interests, behavioral patterns, and real-time emotional states. The input here consists of formatted and cleaned data and existing service data, while the output is the analysis results.

[0678] Step 6:

[0679] The server generates personalized product recommendations based on the analysis results. For example, if the user is stressed, it suggests relaxation-related products; if they are agitated, it suggests active products. A generative AI model is used in this process. The input here is the analysis results, and the output is personalized recommendations.

[0680] Step 7:

[0681] The server pushes the generated recommendation information to the device in real time. A push notification protocol is used to ensure that the information reaches the user immediately. The input here is the recommendation information, and the output is the notification to the device.

[0682] Step 8:

[0683] The device displays received push notifications to the user. These notifications contain relevant product links and promotional information, designed for easy user access. Here, the input is the push notification, and the output is the display on the user interface.

[0684] Step 9:

[0685] The server provides analysis results to multiple services (ad networks, electronic payment services, etc.) for use in ad targeting. This allows each service provider to implement personalized ads and promotions for each user. The input here is the analysis results, and the output is personalized ads.

[0686] 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.

[0687] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0688] 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.

[0689] [Third Embodiment]

[0690] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0691] 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.

[0692] 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).

[0693] 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.

[0694] 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.

[0695] 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).

[0696] 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.

[0697] 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.

[0698] 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.

[0699] 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.

[0700] 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.

[0701] 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".

[0702] The system of the present invention performs the following actions through user operation: pre-installation of generative AI applications, collection and transmission of user behavior data to a server, analysis of integrated data, generation and distribution of recommendation information, and advertising targeting. The details are described below.

[0703] Device reset and application pre-installation

[0704] The device comes pre-installed with generative AI applications during initial setup. This allows users to use generative AI applications immediately after initial setup. These applications include, for example, AI assistants and content generation tools.

[0705] Collection of user behavior data

[0706] When a user uses a generative AI application on their device, the application collects user behavior data. This includes text input, clicks, browsing time, and metadata for each action. This data is recorded in real time through a data collection SDK on the device.

[0707] Data transmission and storage

[0708] The device periodically sends collected user behavior data to the server. This data is encrypted and sent to the server via a secure channel. The server stores the received data in an appropriate database and performs data formatting and cleaning as needed.

[0709] Analysis of integrated data

[0710] The server analyzes user behavior data integrated with data from multiple services. This analysis is performed using AI and machine learning algorithms designed by data scientists and engineers. The goal of the analysis is to reveal user interests and behavioral trends and generate optimal recommendation information based on them.

[0711] Generation and distribution of recommendation information

[0712] Based on the analysis results, the server generates recommendation information for the user. For example, it can suggest relevant content or new services based on articles the user has recently read or products they have purchased. The generated recommendation information is sent to the device as a push notification and displayed in real time to attract the user's attention.

[0713] Ad targeting

[0714] The server provides analysis results to multiple services (e.g., advertising networks and electronic payment services). This allows service providers to display personalized ads and promotions to each user. Improved ad targeting accuracy enables ad delivery that better fits user interests.

[0715] User usage examples

[0716] For example, consider a scenario where a user uses an AI assistant app to manage their daily tasks. The user asks the assistant, "Tell me my schedule for tomorrow." The device records this input and sends it to a server. The server integrates and analyzes this data with other user behavior data to generate recommendations for future task management. It then suggests these recommendations to the user by pushing notifications to their device, including links to the latest task management apps and related blog posts.

[0717] The above describes a specific embodiment of the system of the present invention. Through this system, users can receive personalized services and content, and the accuracy of advertising targeting is also improved.

[0718] The following describes the processing flow.

[0719] Step 1:

[0720] When the device undergoes initial setup, generative AI applications are pre-installed. This allows users to immediately use these applications from the moment they first use the device.

[0721] Step 2:

[0722] The user launches a generative AI application and performs text input or touch operations. For example, the user might type "Tell me tomorrow's weather" into the AI ​​assistant.

[0723] Step 3:

[0724] The device collects user input and touch operations as behavioral data. This behavioral data includes entered text, timing of operations, and usage time.

[0725] Step 4:

[0726] The device sends collected behavioral data to the server. The data is encrypted during transmission and sent through a secure communication channel.

[0727] Step 5:

[0728] The server saves the received behavioral data to data storage, where it performs data formatting and cleaning. This converts the data into a unified format.

[0729] Step 6:

[0730] The server integrates data stored on it with data from other services (for example, online shopping purchase history or social media posts).

[0731] Step 7:

[0732] The server analyzes the integrated data. Here, machine learning algorithms and AI are used to analyze user interests and behavioral patterns, identifying user preferences and interests.

[0733] Step 8:

[0734] The server generates optimal recommendation information for the user based on the analysis results. For example, it might generate news articles or new product information in genres the user has been searching for frequently recently.

[0735] Step 9:

[0736] The server sends the generated recommendation information to the device via push notification. This allows users to receive new information in real time.

[0737] Step 10:

[0738] Users check the push notifications they receive and browse and use content and services that interest them. This action is also collected as behavioral data and used to generate subsequent recommendations.

[0739] Step 11:

[0740] The server provides the analysis results to other service providers (e.g., advertising networks and electronic payment services). This allows each service to utilize the analysis results for ad targeting and deliver more effective ads.

[0741] The above outlines the specific processing steps of this system. This process allows users to receive personalized services and content, and enables service providers to achieve highly accurate advertising targeting.

[0742] (Example 1)

[0743] 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."

[0744] Traditional systems require users to individually install applications when setting up a new device. Furthermore, the collection and analysis of user behavior data, and the generation and distribution of recommendation information based on those results, are often not performed smoothly, resulting in insufficient accuracy in ad targeting. Therefore, improving the user experience and achieving effective ad targeting are key challenges.

[0745] 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.

[0746] In this invention, the server includes means for pre-installing a generative AI application on the terminal, means for collecting user behavior data, means for transmitting the collected data to the server, means for analyzing user behavior data integrated with multiple service data, means for generating recommendation information for the user based on the analysis results, means for transmitting the generated recommendation information to the terminal, means for providing the analysis results to multiple services for use in advertising targeting, and means for transmitting the data collected on the terminal to the server via a secure channel and storing it in an encrypted state. As a result, users can use the generative AI application from the initial setup stage, and the collected data is securely transmitted and stored, making it possible to provide users with appropriate and personalized services and advertisements.

[0747] A "terminal" is an electronic device provided for use by a user, capable of running applications and collecting data.

[0748] A "generative AI application" is a software application that uses artificial intelligence to generate text and content.

[0749] "User behavior data" refers to data about the operations and actions users take when using an application, including text input, clicks, and browsing time.

[0750] A "server" is a computer system that stores, processes, and manages data over a network.

[0751] "Recommendation information" refers to information about recommended content and services generated based on a user's past behavioral data.

[0752] A "push notification" is a real-time notification message sent to a user's device.

[0753] "Ad targeting" is a method of displaying the most relevant advertisements to individual users based on analyzed user data.

[0754] A "data collection SDK" is part of a software development kit, consisting of a set of tools and libraries that allow applications to collect user behavior data.

[0755] A "secure channel" is a communication path that uses encryption technology to ensure that data is transmitted safely.

[0756] "Data formatting and cleaning" refers to the process of standardizing the format of collected data and removing unnecessary information.

[0757] "AI and machine learning algorithms" refer to artificial intelligence and machine learning technologies and methods used to extract patterns and insights from large amounts of data.

[0758] The system of the present invention performs the following actions through user operation: pre-installation of generative AI applications, collection and transmission of user behavior data to a server, analysis of integrated data, generation and distribution of recommendation information, and advertising targeting. The details are described below.

[0759] Device reset and application pre-installation

[0760] During initial setup, the device comes pre-installed with a selection of generative AI applications. This allows users to immediately use AI assistants and content generation tools after the device's initial setup. For example, an AI assistant and a text generation tool may be pre-installed. The device's initial setup wizard will launch, and users can choose from pre-installed generative AI applications.

[0761] Collection of user behavior data

[0762] When a user uses a generative AI application, the application collects user behavior data. This data includes text input, click actions, browsing time, and in-app navigation patterns. The device records this data in real time through a data collection SDK. For example, if a user types "Tell me the weather forecast" into an AI assistant, that text and subsequent activity are recorded.

[0763] Data transmission and storage

[0764] The device sends collected user behavior data to the server at regular intervals. Secure channels such as TLS are used for transmission, and the data is encrypted. The server stores the received data in an appropriate database and performs data formatting and cleaning as needed. For example, the device might send data to the server several times a day in batch processing.

[0765] Analysis of integrated data

[0766] The server analyzes user behavior data integrated with data from multiple services. This analysis uses AI and machine learning algorithms designed by data scientists and engineers. The goal of the analysis is to reveal user interests and behavioral trends. For example, the server analyzes a user's browsing history and finds that the user tends to prefer certain genres of content.

[0767] Generation and distribution of recommendation information

[0768] The server generates recommendation information for the user based on the analysis results. This recommendation information includes new suggestions based on content and services the user has previously been interested in. The generated recommendation information is sent to the device as a push notification and displayed to the user in real time. For example, a notification might show new articles related to articles the user has recently read.

[0769] Ad targeting

[0770] The server provides the analysis results to external services such as advertising networks and electronic payment services. These external services then use this data to display personalized ads and promotions to individual users. This process improves the accuracy of ad targeting, displaying ads that are a better fit to the user's interests. For example, ads for related products may be displayed based on products the user has recently purchased.

[0771] Examples of prompt statements

[0772] For example, consider a case where a user asks an AI assistant to "tell me tomorrow's schedule." A concrete example of the prompt in this case would be as follows:

[0773] "Tell me your schedule for tomorrow."

[0774] The device records this input and periodically sends the data to the server. The server analyzes the data and generates recommendations related to the next task management task. These recommendations, such as "new task management apps" or "links to helpful blog posts," are then pushed to the device. Based on this information, the user can install new apps or read articles.

[0775] The above describes a specific embodiment of the system of the present invention. Through this system, users can enjoy personalized services and content, and the accuracy of advertising targeting is also improved.

[0776] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0777] Step 1: Initialize the device and pre-install applications.

[0778] During initial setup, the device comes pre-installed with pre-selected generative AI applications. This allows users to immediately utilize AI assistants and content generation tools after initial setup. For example, when a user completes the initial setup wizard, the AI ​​assistant app is automatically installed. The first input is turning on the device and starting the initial setup. The output is that generative AI applications become available for use.

[0779] Step 2: Collecting user behavior data

[0780] When a user uses a generative AI application, the application collects user behavior data. This includes text input, click actions, and browsing time. Specifically, if a user inputs "Tell me the weather forecast" into the AI ​​assistant, that text and subsequent actions are collected. The device uses a data collection SDK to record behavior data in real time. The input is the user's actions, and the output is the recorded behavior data.

[0781] Step 3: Data transmission and storage

[0782] The terminal sends user behavior data collected at regular intervals to the server. Secure channels such as TLS are used for transmission, and the data is encrypted. The server stores the received data in a database and formats and cleans the data as needed. Specifically, the terminal sends collected data to the server in batches at a fixed time each day, and the server stores the received data in a standardized format. The input is the data sent from the terminal, and the output is organized and cleaned behavior data.

[0783] Step 4: Analysis of integrated data

[0784] The server integrates and analyzes received user behavior data with data from multiple services. This analysis utilizes AI and machine learning algorithms. This process involves models designed by data scientists analyzing user behavior patterns and interests. For example, the server analyzes a user's past browsing history and uses that to identify new content that the user might be interested in. The input is the integrated data, and the output is the analysis result.

[0785] Step 5: Generating and distributing recommendation information

[0786] The server generates recommendation information for the user based on the analysis results. This recommendation information includes suggestions based on content and services the user has previously been interested in. These suggestions are sent to the device as push notifications, for example, in the form of links to new articles or products. Specifically, new articles related to articles the user has recently read are recommended. The input is the analysis results, and the output is the generated recommendation information.

[0787] Step 6: Ad Targeting

[0788] The server provides the results of its user behavior analysis to external advertising networks and electronic payment services. This allows external services to display personalized ads and promotions to users. Specifically, after a user purchases a particular product, ads for related products are displayed. The input is the analysis results data, and the output is the targeting information provided to external services.

[0789] Through these steps, users can enjoy personalized services and the accuracy of ad targeting will improve.

[0790] (Application Example 1)

[0791] 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."

[0792] In modern e-commerce sites, the accuracy of user recommendations and advertising targeting is a challenge. There is a need for systems that can provide more personalized recommendations and advertisements by effectively collecting and appropriately analyzing user behavior data. Furthermore, there is room for improvement in how recommendation information is presented in a way that is more likely to interest users.

[0793] 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.

[0794] In this invention, the server includes means for pre-installing a generative AI application on a terminal, means for collecting user behavior data on the terminal, means for transmitting the collected data to the server, means for analyzing user behavior data integrated with multiple service data on the server, means for generating recommendation information for the user based on the analysis results, means for transmitting the generated recommendation information to the terminal, means for providing the analysis results to multiple services and using them for advertising targeting, means for generating recommendation information based on the user's purchase history and browsing history in an e-commerce site application installed on the terminal, and means for providing the generated recommendation information as a real-time push notification. This enables highly accurate recommendation information and advertising targeting based on the effective collection and analysis of user behavior data.

[0795] A "terminal" refers to an electronic device operated by a user, on which a generative AI application is installed.

[0796] A "generative AI application" is an application that utilizes a generative AI model to generate content based on user behavior data.

[0797] "User behavior data" refers to data about operations and actions performed by users on their devices, including text input, click history, purchase history, and browsing history.

[0798] A "server" is a computing system that analyzes collected user behavior data and performs the necessary processing for creating recommendation information and targeting advertisements.

[0799] "Multiple service data" refers to data provided from different services that is integrated and analyzed with user behavior data.

[0800] "Analysis" is the process of analyzing user behavior data integrated with data from multiple services to reveal user interests and behavioral patterns.

[0801] "Recommendation information" refers to suggested information provided to users based on analysis results, and includes suggestions for related products and services.

[0802] "Push notifications" are a technology that sends information to a device in real time and are used to attract the user's attention.

[0803] "Ad targeting" is a technology that displays effective advertisements based on user behavior data, and is a means of providing personalized advertising.

[0804] "Purchase history" refers to a record of products that a user has previously purchased from an online shopping site.

[0805] "Browsing history" refers to a record of the products a user has viewed on an e-commerce website.

[0806] An "e-commerce site application" is an application installed on a smartphone that users use to search for, browse, and purchase products.

[0807] This invention is a system that provides individually optimized recommendation information and advertising targeting by pre-installing a generative AI application on a terminal and collecting and analyzing user behavior data. The specific configuration and implementation method of the system are described below.

[0808] Program generation

[0809] The server includes a set of programs for collecting user behavior data, sending the data to the server, analyzing the integrated data, generating recommendation information, and performing advertising targeting. These programs are often implemented using programming languages ​​such as Python or Java.

[0810] Explanation of the process

[0811] The server uses the following hardware and software configuration to collect and analyze data.

[0812] 1. Initial setup of the device:

[0813] The device comes pre-installed with a generative AI application during initial setup. This allows users to start using the application immediately after initializing the device.

[0814] 2. Collection of user behavior data:

[0815] The device collects behavioral data when users utilize generative AI applications. This data includes text input, click history, purchase history, and browsing history. The data is recorded in real time through a data collection software development kit (SDK) on the device.

[0816] 3. Data transmission and storage:

[0817] The device sends collected user behavior data to the server at regular intervals. The data is encrypted and sent to the server via a secure communication channel. The server stores the received data in an appropriate database and performs data formatting and cleaning as needed.

[0818] 4. Analysis of integrated data:

[0819] The server analyzes user behavior data integrated with data from multiple services. It uses AI algorithms and machine learning models designed by data scientists and engineers to reveal user interests and behavioral trends. This analysis utilizes libraries such as Python's Pandas and Scikit-learn.

[0820] 5. Generating recommendation information:

[0821] Based on the analysis results, the server generates recommendation information for the user. For example, it suggests related products based on the categories of items the user has recently purchased. This information is provided to the user via push notifications or in-app messages.

[0822] 6. Ad targeting:

[0823] The server provides analysis results to multiple services and uses them for ad targeting. This ensures that the most relevant ads and promotions are displayed to each user.

[0824] Specific example

[0825] For example, if a user frequently browses electronic devices on an e-commerce application, the server can send push notifications recommending new products within that category. The following example prompt message is used by the server for this purpose.

[0826] Example of a prompt:

[0827] "Please recommend electronic devices to user 123 who has been frequently browsing electronic devices recently. The following is user behavior data for this purpose."

[0828] In this way, by implementing the present invention, the accuracy of recommendation information and advertising targeting for users can be significantly improved.

[0829] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0830] Step 1:

[0831] Initial setup of the device

[0832] The device comes pre-installed with a generative AI application at the time of shipment. Once the user completes the initial setup of the device, this application becomes ready to launch. This allows the user to use the application immediately after the initial setup.

[0833] Input: Initial device setup

[0834] Output: A terminal with a generative AI application installed.

[0835] Step 2:

[0836] Collection of user behavior data

[0837] When a user interacts with a generative AI application, the application collects user behavior data in real time, such as text input, click history, purchase history, and browsing history. This data is recorded using a data collection SDK on the device.

[0838] Input: User actions (text input, clicks, purchases, browsing)

[0839] Output: Collected user behavior data

[0840] Step 3:

[0841] Data transmission and storage

[0842] The device sends collected user behavior data to the server at regular intervals. The data is encrypted and sent to the server via a secure channel such as HTTPS. The server stores the received data in a database and performs data formatting and cleaning as needed.

[0843] Input: Collected user behavior data

[0844] Output: User behavior data stored on the server

[0845] Step 4:

[0846] Analysis of integrated data

[0847] The server integrates user behavior data with data from multiple services. This analysis utilizes AI algorithms and machine learning models designed by data scientists and engineers. Libraries such as Python's Pandas and Scikit-learn are used to reveal user interests and behavioral trends.

[0848] Input: Integrated user behavior data

[0849] Output: Analysis results (user interests and behavioral trends)

[0850] Step 5:

[0851] Recommendation information generation

[0852] Based on the analysis results, the server generates personalized recommendations for each user. For example, related products are suggested based on the categories of items the user has recently purchased or viewed. This information is generated in real time and may be provided in the form of push notifications.

[0853] Input: Analysis results

[0854] Output: Generated recommendation information

[0855] Step 6:

[0856] Providing recommendation information via push notifications

[0857] The device pushes the generated recommendation information to the user. This allows the user to receive new recommendations without having to open the application.

[0858] Input: Generated recommendation information

[0859] Output: Recommendation information pushed to the user.

[0860] Step 7:

[0861] Ad targeting

[0862] Based on the analysis results, the server provides personalized advertising and promotional information to multiple services. This ensures that the most relevant ads are displayed to each user, maximizing the effectiveness of ad targeting.

[0863] Input: Analysis results

[0864] Output: Advertising information provided to the service

[0865] 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.

[0866] The system of the present invention pre-installs generative AI applications through user operation, collects and transmits user behavior data and emotional data to a server, analyzes integrated data, generates and delivers recommendation information, and performs advertising targeting. The details are described below.

[0867] Device reset and application pre-installation

[0868] The device comes pre-installed with generative AI applications during initial setup. This allows users to immediately use these applications from the moment they first use the device. These applications include, for example, AI assistants and content generation tools. Furthermore, an emotion engine is integrated into the device, enabling the collection of user emotion data.

[0869] Collection of user behavior data and emotional data

[0870] When a user uses a generative AI application on their device, the application collects user behavior data. This behavior data includes text input, clicks, and browsing time. Furthermore, the emotion engine analyzes the user's text input and voice data to collect emotion data. This also results in data based on the user's emotional state.

[0871] Data transmission and storage

[0872] The device sends collected behavioral and emotional data to the server. The data is encrypted during transmission and sent through a secure communication channel. The server stores the received data in an appropriate database and performs data formatting and cleaning. This converts the data into a unified format.

[0873] Analysis of integrated data

[0874] The server analyzes user behavior and sentiment data integrated with multiple service data sets. This analysis is performed using AI and machine learning algorithms designed by data scientists and engineers. The goal of the analysis is to reveal users' interests, behavioral patterns, and real-time emotional states, and to generate optimal recommendation information based on this information.

[0875] Generation and distribution of recommendation information

[0876] Based on the analysis results, the server generates optimal recommendation information for the user. For example, if the user is feeling stressed, it can suggest relaxation content, and if they are excited, it can suggest active content. The generated recommendation information is sent to the device as a push notification and displayed in real time to attract the user's attention.

[0877] Ad targeting

[0878] The server provides analysis results to multiple services (e.g., advertising networks and electronic payment services). This allows service providers to display personalized ads and promotions to each user. Improved ad targeting accuracy enables ad delivery that better fits user interests.

[0879] User usage examples

[0880] For example, consider a scenario where a user uses an AI assistant app to manage their daily tasks. The user asks the assistant, "Tell me my schedule for tomorrow." The device records this input and sends it to the server. The emotion engine identifies the user's emotions from the text and tone of voice used in their input, and also sends the results to the server. The server integrates and analyzes the user's emotion data with other behavioral data to generate recommendations for their next task management. It then pushes links to the latest task management apps and related blog posts to the device, suggesting them to the user. If the user is feeling stressed, information to help them relax is also provided.

[0881] The above describes a specific embodiment of the system of the present invention. Through this system, users can receive personalized services and content, and the accuracy of advertising targeting is also improved. By introducing an emotion engine, it is possible to provide more appropriate recommendations according to the user's emotional state.

[0882] The following describes the processing flow.

[0883] Step 1:

[0884] During the initial setup of the device, generative AI applications and an emotion engine are pre-installed. This allows users to immediately use these applications from the moment they first use the device.

[0885] Step 2:

[0886] The user launches a generative AI application and performs actions such as text input, voice input, and touch operations. For example, the user might type "Tell me tomorrow's weather" into the AI ​​assistant.

[0887] Step 3:

[0888] The device collects user input and actions as behavioral data. This behavioral data includes entered text, timing of actions, and usage time.

[0889] Step 4:

[0890] The emotion engine analyzes the user's text input, voice data, facial expression data, etc., to identify the user's emotional state. For example, it can determine whether the user's current emotion is "stress" or "excitement" from the text they input or the audio of their speech.

[0891] Step 5:

[0892] The device sends collected behavioral and emotional data to the server. The data is encrypted during transmission and sent through a secure communication channel.

[0893] Step 6:

[0894] The server stores the received behavioral and emotional data in data storage, and then formats and cleans the data. This converts the data into a unified format.

[0895] Step 7:

[0896] The server integrates data stored on it with data from other services (for example, online shopping purchase history or social media posts).

[0897] Step 8:

[0898] The server analyzes the integrated data. Here, machine learning algorithms and AI are used to analyze users' interests, behavioral patterns, and real-time emotional states to identify user preferences and interests.

[0899] Step 9:

[0900] The server generates optimal recommendation information for the user based on the analysis results. For example, if the user is feeling stressed, it suggests relaxation clips; if they are excited, it suggests active event information.

[0901] Step 10:

[0902] The server sends the generated recommendation information to the device via push notification. This allows users to receive new information in real time.

[0903] Step 11:

[0904] Users check the push notifications they receive and browse and use content and services that interest them. This activity is also collected as behavioral and sentiment data and used to generate subsequent recommendations.

[0905] Step 12:

[0906] The server provides the analysis results to other service providers (e.g., advertising networks and electronic payment services). This allows each service to utilize the analysis results for ad targeting and deliver more effective ads.

[0907] The above outlines the specific processing steps of this system. This process allows users to receive personalized services and content, and enables service providers to achieve highly accurate ad targeting. The introduction of an emotion engine makes it possible to provide more appropriate recommendations based on the user's emotional state.

[0908] (Example 2)

[0909] 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."

[0910] Traditional recommendation and advertising targeting systems analyze user behavior data, including browsing history, to provide recommendations and advertisements. However, they have failed to provide highly accurate recommendations and advertising targeting that take emotional states into account. This is because it is difficult to optimally select content and advertisements according to the user's emotions.

[0911] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for pre-installing a generative AI application on a terminal, means for collecting user behavior data and emotional data on the terminal, means for transmitting the collected data to the server, means for analyzing user behavior data and emotional data integrated with multiple information data on the server, means for generating recommendation information for the user based on the analysis results, means for transmitting the generated recommendation information to the terminal, and means for providing the analysis results to multiple information provision services and using them for advertising targeting. This makes it possible to provide highly accurate recommendation information and advertising targeting according to the user's emotional state.

[0912] A "device" is an electronic device that a user can directly operate, and includes personal computers, smartphones, tablets, and other similar devices.

[0913] "Generative AI applications" are software that utilizes artificial intelligence to generate content based on user input, and include AI assistants and content generation tools.

[0914] "User behavior data" refers to data related to operations and actions performed by users on their devices, including text input, clicks, and browsing time.

[0915] "Emotional data" refers to emotion-related data extracted from user input and voice, and includes information that indicates the user's emotional state (such as joy, anger, sadness, etc.).

[0916] A "server" is a computer system that provides services to terminals via a network, and has the functions of receiving, storing, and analyzing data.

[0917] "Information data" refers to various types of data obtained from servers and other data sources, including user behavior data and sentiment data.

[0918] "Analysis" is the process of finding patterns based on collected data, and it is carried out using AI and machine learning algorithms.

[0919] "Recommendation information" refers to recommended content and suggestions generated by the server based on the user's interests and behavior, and includes information that is sent to the user via push notifications.

[0920] "Ad targeting" is a method of selecting and displaying the most suitable advertisements to users based on analytical data, enabling personalized ad delivery.

[0921] The system of this invention pre-installs a generative AI application on a terminal, collects and analyzes user behavior data and emotional data, and generates and delivers optimal recommendation information to the user based on that data. Furthermore, to improve the accuracy of advertising targeting, the analysis results are provided to multiple information provision services.

[0922] Device reset and application pre-installation

[0923] The device undergoes initial setup upon shipment or first boot-up, and a pre-installation script is executed to install generative AI applications into the system. These applications include, for example, an AI assistant and content generation tools, allowing users to use them immediately from the moment they first use the device. Furthermore, an emotion engine is integrated into the device, ready to collect user emotion data.

[0924] Collection of user behavior data and emotional data

[0925] When a user uses a generative AI application on their device, the application collects user activity logs (text input, clicks, browsing time, etc.) and stores them in a local database. Simultaneously, an emotion engine operates, analyzing the user's text input and voice data in real time. This also collects emotion data indicating the user's emotional state (joy, anger, sadness, etc.).

[0926] Data transmission and storage

[0927] The terminal prepares the collected behavioral and emotional data in batch processing, compresses and encrypts it, and then sends it to the server. A secure communication protocol (e.g., HTTPS) is used in this transmission process. The server stores the received data in an appropriate database (e.g., SQL database, NoSQL database) and performs data formatting and cleaning using an ETL (Extract, Transform, Load) process.

[0928] Analysis of integrated data

[0929] The server analyzes user behavior and sentiment data integrated with multiple data sets. This analysis utilizes AI and machine learning algorithms designed by data scientists and engineers. The goal of the analysis is to reveal users' interests, behavioral patterns, and real-time emotional states, and to generate optimal recommendation information based on this information.

[0930] Generation and distribution of recommendation information

[0931] Based on the analysis results, the server generates optimal recommendation information for the user. For example, if the user is feeling stressed, it suggests relaxation content; if they are excited, it suggests active content. The generated recommendation information is sent to the device in real time as a push notification and displayed to the user.

[0932] Ad targeting

[0933] The server provides analysis results to multiple information providers for use in advertising targeting. This allows service providers to display personalized ads and promotions to each user. Improved accuracy in advertising targeting enables the delivery of ads that better fit user interests.

[0934] User usage examples

[0935] For example, consider a scenario where a user uses an AI assistant app to manage their daily tasks. The user asks the assistant, "Tell me my schedule for tomorrow." The device records this input and sends it to the server. The emotion engine identifies the user's emotions from the text and tone of voice used in their input, and also sends the results to the server. The server integrates and analyzes the user's emotion data with other behavioral data to generate recommendations for their next task management. It then pushes links to the latest task management apps and related blog posts to the device, suggesting them to the user. If the system determines that the user is stressed, it also provides information to help them relax.

[0936] Example of a prompt

[0937] "Assuming the user is in an emotionally unsettled state, please generate recommendations that the AI ​​assistant would make in that situation."

[0938] As described above, the system of the present invention can provide appropriate recommendation information and improve the accuracy of advertising targeting by collecting and analyzing user behavior data and emotional data.

[0939] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0940] Step 1:

[0941] Device initialization and pre-installation of generative AI applications

[0942] Upon initial startup, the device performs an initial setup and installs generative AI applications (e.g., AI assistant, content generation tool, etc.) into the system via a pre-installation script. The input is a device in its factory default state, and the output is a usable device with generative AI applications and an emotion engine installed.

[0943] Step 2:

[0944] Collection of user behavior data and emotional data

[0945] When a user interacts with a generative AI application on their device, the application collects user behavior data (text input, clicks, browsing time, etc.) and stores it in a local database. Simultaneously, the emotion engine analyzes the user's text input and voice data in real time and extracts emotion data. The input consists of user behavior and voice / text data, and the output consists of behavior data and emotion data stored in the local database.

[0946] Step 3:

[0947] Data preparation and transmission

[0948] The terminal prepares the collected behavioral and sentimental data in batch processing, compressing and encrypting the data. It then sends the data to the server using a secure communication protocol (e.g., HTTPS). The input consists of behavioral and sentimental data in a local database, and the output is securely encrypted data sent to the server.

[0949] Step 4:

[0950] Data storage and formatting

[0951] The server stores the received data in an appropriate database (e.g., SQL database, NoSQL database) and performs an ETL (Extract, Transform, Load) process to format and clean the data. The input is encrypted data, and the output is clean data converted to a unified format, which is then stored in the database.

[0952] Step 5:

[0953] Analysis of integrated data

[0954] The server analyzes user behavior data and sentiment data integrated with multiple pieces of informational data. This analysis utilizes AI and machine learning algorithms to reveal user interests, behavioral patterns, and emotional states. The input consists of integrated user data and informational data, and the output is the analysis results.

[0955] Step 6:

[0956] Recommendation information generation

[0957] The server generates optimal recommendation information for the user based on the analysis results. For example, if the user is feeling stressed, it suggests relaxation content; if they are excited, it suggests active content. The input is the analysis results, and the output is the recommendation information suggested to the user.

[0958] Step 7:

[0959] Recommendation information distribution

[0960] The generated recommendation information is sent to the device as a push notification. The user receives this information in real time. The input is the recommendation information, and the output is the push notification displayed on the user's device.

[0961] Step 8:

[0962] Executing ad targeting

[0963] The server provides analysis results to multiple information providers for use in advertising targeting. This allows service providers to display personalized ads and promotions. The input is the analysis results, and the output is targeted ads delivered to the user.

[0964] (Application Example 2)

[0965] 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."

[0966] Traditional e-commerce sites have struggled to effectively utilize user behavioral and emotional data to provide personalized product recommendations in real time. Furthermore, improving the accuracy of advertising targeting based on collected data has also been challenging. This invention aims to solve these problems and provide a system that enables more appropriate and effective product recommendations and advertising to users.

[0967] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting user behavior data and emotional data, means for encrypting the collected data and transmitting it to the server, means for analyzing user behavior data and emotional data integrated with multiple service data, means for generating personalized product recommendation information based on the analysis results, means for pushing the generated recommendation information to the terminal in real time, and means for providing the analysis results to multiple services and using them for advertising targeting. This makes it possible to accurately capture user behavior and emotions and provide personalized product recommendations and advertisements at the appropriate time.

[0968] A "device" is an electronic device designed for use by users, and includes smartphones, tablets, and other similar devices.

[0969] A "generative AI application" is a software application that uses artificial intelligence technology to provide diverse services to users, and has the ability to generate objects, generate content, or provide assistant functions.

[0970] "User behavior data" refers to data that shows a user's operation history and behavioral patterns, and includes text input, clicks, biometric information, and browsing time.

[0971] "Emotional data" refers to data that indicates a user's emotional state, and is information extracted from voice tone and text content.

[0972] A "server" is a computer system that stores, processes, and distributes data over a network.

[0973] "Data encryption" refers to the technology of converting data into a format that cannot be deciphered by third parties, thereby ensuring the secure transmission of data.

[0974] "Multiple service data" refers to a collection of data gathered from different services, and involves centrally managing the data provided by each service.

[0975] "Recommendation information" refers to information about products and content that is suggested to users based on their behavior and emotions.

[0976] "Push notifications" are a notification function that sends information from a server to a device in real time to alert the user.

[0977] "Ad targeting" is a method of displaying individually optimized advertisements based on user characteristics and behavioral analysis.

[0978] The system of the present invention pre-installs generative AI applications through user operation, collects user behavior data and emotional data, analyzes integrated data, generates and delivers recommendation information, and performs advertising targeting. The details are described below.

[0979] Device reset and application pre-installation

[0980] The device comes pre-installed with generative AI applications during initial setup. This allows users to immediately use these applications from the moment they first use the device. These applications include, for example, AI assistants and content generation tools. Furthermore, an emotion engine is integrated into the device, enabling the collection of user emotion data.

[0981] Collection of user behavior data and emotional data

[0982] When a user uses a generative AI application on their device, the application collects user behavioral and emotional data. This behavioral data includes text input, clicks, and browsing time. Furthermore, the emotion engine analyzes the user's text input and voice data to collect emotional data. This also results in data based on the user's emotional state.

[0983] Data transmission and storage

[0984] The device encrypts the collected behavioral and emotional data and sends it to the server. The data is encrypted during transmission and transmitted through a secure communication channel. The server stores the received data in an appropriate database and performs data formatting and cleaning. This converts the data into a unified format.

[0985] Analysis of integrated data

[0986] The server analyzes user behavior and sentiment data integrated with multiple service data sets. This analysis is performed using AI and machine learning algorithms designed by data scientists and engineers. The goal of the analysis is to reveal users' interests, behavioral patterns, and real-time emotional states, and to generate optimal recommendation information based on this information.

[0987] Generation and distribution of recommendation information

[0988] Based on the analysis results, the server generates optimal product recommendations for the user. For example, if the user is feeling stressed, it can suggest relaxation products; if they are excited, it can suggest active products. The generated recommendations are sent to the device as real-time push notifications and displayed immediately to attract the user's attention.

[0989] Ad targeting

[0990] The server provides analysis results to multiple services (e.g., advertising networks and electronic payment services). This allows service providers to display personalized ads and promotions to each user. Improved ad targeting accuracy enables ad delivery that better fits user interests.

[0991] User usage examples

[0992] For example, consider a scenario where a user is browsing an online shopping site using an AI shopping assistant app. The user types, "I'm looking into product A." The device records this input and sends it to the server. The emotion engine identifies the user's emotions from the text and tone of voice used in their input, and also sends the results to the server. The server integrates and analyzes the user's emotion data with other behavioral data to generate recommendations for their next purchase. It then pushes the latest product information and links to related promotions to the device, suggesting them to the user. If the user is excited, information on active products is also provided simultaneously.

[0993] Examples of prompt statements

[0994] Here are some specific examples of prompt statements to input into a generative AI model:

[0995] If a user shows interest in product A, analyze and recommend the following products:

[0996] User input: I am researching product A.

[0997] User's emotion: Excitement

[0998] Product Catalog: ["Product A", "Product B", "Product C"]

[0999] The above describes a specific embodiment of the system of the present invention. Through this system, users can receive personalized services and content, and the accuracy of advertising targeting can also be improved. By introducing an emotion engine, it is possible to provide more appropriate recommendations according to the user's emotional state.

[1000] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1001] Step 1:

[1002] The device comes pre-installed with a generative AI application. The installed application automatically launches during the user's initial setup, ensuring it's ready when the user begins using the device. Here, the input is the device's initial setup, and the output is the state in which the AI ​​application is available for use.

[1003] Step 2:

[1004] When a user begins using a generative AI application on their device, the application collects user behavioral and emotional data. This collection includes behavioral data such as text input, clicks, and browsing time, as well as emotional data derived from voice tone and keyboard typing speed. Here, input is the user's actions, and output is the collected data.

[1005] Step 3:

[1006] The device encrypts the collected behavioral and emotional data and transmits it to the server via a secure communication channel. A data encryption algorithm is used in this process. The input here is the collected data, and the output is the encrypted data.

[1007] Step 4:

[1008] The server stores the received data in the appropriate database and performs data formatting and cleaning. This process includes standardizing the data format and handling missing data values. The input here is encrypted data, and the output is formatted and cleaned data.

[1009] Step 5:

[1010] The server analyzes user behavior and sentiment data integrated with multiple service data sets. AI and machine learning algorithms are used for the analysis to reveal user interests, behavioral patterns, and real-time emotional states. The input here consists of formatted and cleaned data and existing service data, while the output is the analysis results.

[1011] Step 6:

[1012] The server generates personalized product recommendations based on the analysis results. For example, if the user is stressed, it suggests relaxation-related products; if they are agitated, it suggests active products. A generative AI model is used in this process. The input here is the analysis results, and the output is personalized recommendations.

[1013] Step 7:

[1014] The server pushes the generated recommendation information to the device in real time. A push notification protocol is used to ensure that the information reaches the user immediately. The input here is the recommendation information, and the output is the notification to the device.

[1015] Step 8:

[1016] The device displays received push notifications to the user. These notifications contain relevant product links and promotional information, designed for easy user access. Here, the input is the push notification, and the output is the display on the user interface.

[1017] Step 9:

[1018] The server provides analysis results to multiple services (ad networks, electronic payment services, etc.) for use in ad targeting. This allows each service provider to implement personalized ads and promotions for each user. The input here is the analysis results, and the output is personalized ads.

[1019] 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.

[1020] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1021] 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.

[1022] [Fourth Embodiment]

[1023] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1024] 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.

[1025] 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).

[1026] 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.

[1027] 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.

[1028] 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).

[1029] 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.

[1030] 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.

[1031] 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.

[1032] 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.

[1033] 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.

[1034] 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.

[1035] 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".

[1036] The system of the present invention performs the following actions through user operation: pre-installation of generative AI applications, collection and transmission of user behavior data to a server, analysis of integrated data, generation and distribution of recommendation information, and advertising targeting. The details are described below.

[1037] Device reset and application pre-installation

[1038] The device comes pre-installed with generative AI applications during initial setup. This allows users to use generative AI applications immediately after initial setup. These applications include, for example, AI assistants and content generation tools.

[1039] Collection of user behavior data

[1040] When a user uses a generative AI application on their device, the application collects user behavior data. This includes text input, clicks, browsing time, and metadata for each action. This data is recorded in real time through a data collection SDK on the device.

[1041] Data transmission and storage

[1042] The device periodically sends collected user behavior data to the server. This data is encrypted and sent to the server via a secure channel. The server stores the received data in an appropriate database and performs data formatting and cleaning as needed.

[1043] Analysis of integrated data

[1044] The server analyzes user behavior data integrated with data from multiple services. This analysis is performed using AI and machine learning algorithms designed by data scientists and engineers. The goal of the analysis is to reveal user interests and behavioral trends and generate optimal recommendation information based on them.

[1045] Generation and distribution of recommendation information

[1046] Based on the analysis results, the server generates recommendation information for the user. For example, it can suggest relevant content or new services based on articles the user has recently read or products they have purchased. The generated recommendation information is sent to the device as a push notification and displayed in real time to attract the user's attention.

[1047] Ad targeting

[1048] The server provides analysis results to multiple services (e.g., advertising networks and electronic payment services). This allows service providers to display personalized ads and promotions to each user. Improved ad targeting accuracy enables ad delivery that better fits user interests.

[1049] User usage examples

[1050] For example, consider a scenario where a user uses an AI assistant app to manage their daily tasks. The user asks the assistant, "Tell me my schedule for tomorrow." The device records this input and sends it to a server. The server integrates and analyzes this data with other user behavior data to generate recommendations for future task management. It then suggests these recommendations to the user by pushing notifications to their device, including links to the latest task management apps and related blog posts.

[1051] The above describes a specific embodiment of the system of the present invention. Through this system, users can receive personalized services and content, and the accuracy of advertising targeting is also improved.

[1052] The following describes the processing flow.

[1053] Step 1:

[1054] When the device undergoes initial setup, generative AI applications are pre-installed. This allows users to immediately use these applications from the moment they first use the device.

[1055] Step 2:

[1056] The user launches a generative AI application and performs text input or touch operations. For example, the user might type "Tell me tomorrow's weather" into the AI ​​assistant.

[1057] Step 3:

[1058] The device collects user input and touch operations as behavioral data. This behavioral data includes entered text, timing of operations, and usage time.

[1059] Step 4:

[1060] The device sends collected behavioral data to the server. The data is encrypted during transmission and sent through a secure communication channel.

[1061] Step 5:

[1062] The server saves the received behavioral data to data storage, where it performs data formatting and cleaning. This converts the data into a unified format.

[1063] Step 6:

[1064] The server integrates data stored on it with data from other services (for example, online shopping purchase history or social media posts).

[1065] Step 7:

[1066] The server analyzes the integrated data. Here, machine learning algorithms and AI are used to analyze user interests and behavioral patterns, identifying user preferences and interests.

[1067] Step 8:

[1068] The server generates optimal recommendation information for the user based on the analysis results. For example, it might generate news articles or new product information in genres the user has been searching for frequently recently.

[1069] Step 9:

[1070] The server sends the generated recommendation information to the device via push notification. This allows users to receive new information in real time.

[1071] Step 10:

[1072] Users check the push notifications they receive and browse and use content and services that interest them. This action is also collected as behavioral data and used to generate subsequent recommendations.

[1073] Step 11:

[1074] The server provides the analysis results to other service providers (e.g., advertising networks and electronic payment services). This allows each service to utilize the analysis results for ad targeting and deliver more effective ads.

[1075] The above outlines the specific processing steps of this system. This process allows users to receive personalized services and content, and enables service providers to achieve highly accurate advertising targeting.

[1076] (Example 1)

[1077] 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".

[1078] Traditional systems require users to individually install applications when setting up a new device. Furthermore, the collection and analysis of user behavior data, and the generation and distribution of recommendation information based on those results, are often not performed smoothly, resulting in insufficient accuracy in ad targeting. Therefore, improving the user experience and achieving effective ad targeting are key challenges.

[1079] 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.

[1080] In this invention, the server includes means for pre-installing a generative AI application on the terminal, means for collecting user behavior data, means for transmitting the collected data to the server, means for analyzing user behavior data integrated with multiple service data, means for generating recommendation information for the user based on the analysis results, means for transmitting the generated recommendation information to the terminal, means for providing the analysis results to multiple services for use in advertising targeting, and means for transmitting the data collected on the terminal to the server via a secure channel and storing it in an encrypted state. As a result, users can use the generative AI application from the initial setup stage, and the collected data is securely transmitted and stored, making it possible to provide users with appropriate and personalized services and advertisements.

[1081] A "terminal" is an electronic device provided for use by a user, capable of running applications and collecting data.

[1082] A "generative AI application" is a software application that uses artificial intelligence to generate text and content.

[1083] "User behavior data" refers to data about the operations and actions users take when using an application, including text input, clicks, and browsing time.

[1084] A "server" is a computer system that stores, processes, and manages data over a network.

[1085] "Recommendation information" refers to information about recommended content and services generated based on a user's past behavioral data.

[1086] A "push notification" is a real-time notification message sent to a user's device.

[1087] "Ad targeting" is a method of displaying the most relevant advertisements to individual users based on analyzed user data.

[1088] A "data collection SDK" is part of a software development kit, consisting of a set of tools and libraries that allow applications to collect user behavior data.

[1089] A "secure channel" is a communication path that uses encryption technology to ensure that data is transmitted safely.

[1090] "Data formatting and cleaning" refers to the process of standardizing the format of collected data and removing unnecessary information.

[1091] "AI and machine learning algorithms" refer to artificial intelligence and machine learning technologies and methods used to extract patterns and insights from large amounts of data.

[1092] The system of the present invention performs the following actions through user operation: pre-installation of generative AI applications, collection and transmission of user behavior data to a server, analysis of integrated data, generation and distribution of recommendation information, and advertising targeting. The details are described below.

[1093] Device reset and application pre-installation

[1094] During initial setup, the device comes pre-installed with a selection of generative AI applications. This allows users to immediately use AI assistants and content generation tools after the device's initial setup. For example, an AI assistant and a text generation tool may be pre-installed. The device's initial setup wizard will launch, and users can choose from pre-installed generative AI applications.

[1095] Collection of user behavior data

[1096] When a user uses a generative AI application, the application collects user behavior data. This data includes text input, click actions, browsing time, and in-app navigation patterns. The device records this data in real time through a data collection SDK. For example, if a user types "Tell me the weather forecast" into an AI assistant, that text and subsequent activity are recorded.

[1097] Data transmission and storage

[1098] The device sends collected user behavior data to the server at regular intervals. Secure channels such as TLS are used for transmission, and the data is encrypted. The server stores the received data in an appropriate database and performs data formatting and cleaning as needed. For example, the device might send data to the server several times a day in batch processing.

[1099] Analysis of integrated data

[1100] The server analyzes user behavior data integrated with data from multiple services. This analysis uses AI and machine learning algorithms designed by data scientists and engineers. The goal of the analysis is to reveal user interests and behavioral trends. For example, the server analyzes a user's browsing history and finds that the user tends to prefer certain genres of content.

[1101] Generation and distribution of recommendation information

[1102] The server generates recommendation information for the user based on the analysis results. This recommendation information includes new suggestions based on content and services the user has previously been interested in. The generated recommendation information is sent to the device as a push notification and displayed to the user in real time. For example, a notification might show new articles related to articles the user has recently read.

[1103] Ad targeting

[1104] The server provides the analysis results to external services such as advertising networks and electronic payment services. These external services then use this data to display personalized ads and promotions to individual users. This process improves the accuracy of ad targeting, displaying ads that are a better fit to the user's interests. For example, ads for related products may be displayed based on products the user has recently purchased.

[1105] Examples of prompt statements

[1106] For example, consider a case where a user asks an AI assistant to "tell me tomorrow's schedule." A concrete example of the prompt in this case would be as follows:

[1107] "Tell me your schedule for tomorrow."

[1108] The device records this input and periodically sends the data to the server. The server analyzes the data and generates recommendations related to the next task management task. These recommendations, such as "new task management apps" or "links to helpful blog posts," are then pushed to the device. Based on this information, the user can install new apps or read articles.

[1109] The above describes a specific embodiment of the system of the present invention. Through this system, users can enjoy personalized services and content, and the accuracy of advertising targeting is also improved.

[1110] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1111] Step 1: Initialize the device and pre-install applications.

[1112] During initial setup, the device comes pre-installed with pre-selected generative AI applications. This allows users to immediately utilize AI assistants and content generation tools after initial setup. For example, when a user completes the initial setup wizard, the AI ​​assistant app is automatically installed. The first input is turning on the device and starting the initial setup. The output is that generative AI applications become available for use.

[1113] Step 2: Collecting user behavior data

[1114] When a user uses a generative AI application, the application collects user behavior data. This includes text input, click actions, and browsing time. Specifically, if a user inputs "Tell me the weather forecast" into the AI ​​assistant, that text and subsequent actions are collected. The device uses a data collection SDK to record behavior data in real time. The input is the user's actions, and the output is the recorded behavior data.

[1115] Step 3: Data transmission and storage

[1116] The terminal sends user behavior data collected at regular intervals to the server. Secure channels such as TLS are used for transmission, and the data is encrypted. The server stores the received data in a database and formats and cleans the data as needed. Specifically, the terminal sends collected data to the server in batches at a fixed time each day, and the server stores the received data in a standardized format. The input is the data sent from the terminal, and the output is organized and cleaned behavior data.

[1117] Step 4: Analysis of integrated data

[1118] The server integrates and analyzes received user behavior data with data from multiple services. This analysis utilizes AI and machine learning algorithms. This process involves models designed by data scientists analyzing user behavior patterns and interests. For example, the server analyzes a user's past browsing history and uses that to identify new content that the user might be interested in. The input is the integrated data, and the output is the analysis result.

[1119] Step 5: Generating and distributing recommendation information

[1120] The server generates recommendation information for the user based on the analysis results. This recommendation information includes suggestions based on content and services the user has previously been interested in. These suggestions are sent to the device as push notifications, for example, in the form of links to new articles or products. Specifically, new articles related to articles the user has recently read are recommended. The input is the analysis results, and the output is the generated recommendation information.

[1121] Step 6: Ad Targeting

[1122] The server provides the results of its user behavior analysis to external advertising networks and electronic payment services. This allows external services to display personalized ads and promotions to users. Specifically, after a user purchases a particular product, ads for related products are displayed. The input is the analysis results data, and the output is the targeting information provided to external services.

[1123] Through these steps, users can enjoy personalized services and the accuracy of ad targeting will improve.

[1124] (Application Example 1)

[1125] 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".

[1126] In modern e-commerce sites, the accuracy of user recommendations and advertising targeting is a challenge. There is a need for systems that can provide more personalized recommendations and advertisements by effectively collecting and appropriately analyzing user behavior data. Furthermore, there is room for improvement in how recommendation information is presented in a way that is more likely to interest users.

[1127] 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.

[1128] In this invention, the server includes means for pre-installing a generative AI application on a terminal, means for collecting user behavior data on the terminal, means for transmitting the collected data to the server, means for analyzing user behavior data integrated with multiple service data on the server, means for generating recommendation information for the user based on the analysis results, means for transmitting the generated recommendation information to the terminal, means for providing the analysis results to multiple services and using them for advertising targeting, means for generating recommendation information based on the user's purchase history and browsing history in an e-commerce site application installed on the terminal, and means for providing the generated recommendation information as a real-time push notification. This enables highly accurate recommendation information and advertising targeting based on the effective collection and analysis of user behavior data.

[1129] A "terminal" refers to an electronic device operated by a user, on which a generative AI application is installed.

[1130] A "generative AI application" is an application that utilizes a generative AI model to generate content based on user behavior data.

[1131] "User behavior data" refers to data about operations and actions performed by users on their devices, including text input, click history, purchase history, and browsing history.

[1132] A "server" is a computing system that analyzes collected user behavior data and performs the necessary processing for creating recommendation information and targeting advertisements.

[1133] "Multiple service data" refers to data provided from different services that is integrated and analyzed with user behavior data.

[1134] "Analysis" is the process of analyzing user behavior data integrated with data from multiple services to reveal user interests and behavioral patterns.

[1135] "Recommendation information" refers to suggested information provided to users based on analysis results, and includes suggestions for related products and services.

[1136] "Push notifications" are a technology that sends information to a device in real time and are used to attract the user's attention.

[1137] "Ad targeting" is a technology that displays effective advertisements based on user behavior data, and is a means of providing personalized advertising.

[1138] "Purchase history" refers to a record of products that a user has previously purchased from an online shopping site.

[1139] "Browsing history" refers to a record of the products a user has viewed on an e-commerce website.

[1140] An "e-commerce site application" is an application installed on a smartphone that users use to search for, browse, and purchase products.

[1141] This invention is a system that provides individually optimized recommendation information and advertising targeting by pre-installing a generative AI application on a terminal and collecting and analyzing user behavior data. The specific configuration and implementation method of the system are described below.

[1142] Program generation

[1143] The server includes a set of programs for collecting user behavior data, sending the data to the server, analyzing the integrated data, generating recommendation information, and performing advertising targeting. These programs are often implemented using programming languages ​​such as Python or Java.

[1144] Explanation of the process

[1145] The server uses the following hardware and software configuration to collect and analyze data.

[1146] 1. Initial setup of the device:

[1147] The device comes pre-installed with a generative AI application during initial setup. This allows users to start using the application immediately after initializing the device.

[1148] 2. Collection of user behavior data:

[1149] The device collects behavioral data when users utilize generative AI applications. This data includes text input, click history, purchase history, and browsing history. The data is recorded in real time through a data collection software development kit (SDK) on the device.

[1150] 3. Data transmission and storage:

[1151] The device sends collected user behavior data to the server at regular intervals. The data is encrypted and sent to the server via a secure communication channel. The server stores the received data in an appropriate database and performs data formatting and cleaning as needed.

[1152] 4. Analysis of integrated data:

[1153] The server analyzes user behavior data integrated with data from multiple services. It uses AI algorithms and machine learning models designed by data scientists and engineers to reveal user interests and behavioral trends. This analysis utilizes libraries such as Python's Pandas and Scikit-learn.

[1154] 5. Generating recommendation information:

[1155] Based on the analysis results, the server generates recommendation information for the user. For example, it suggests related products based on the categories of items the user has recently purchased. This information is provided to the user via push notifications or in-app messages.

[1156] 6. Ad targeting:

[1157] The server provides analysis results to multiple services and uses them for ad targeting. This ensures that the most relevant ads and promotions are displayed to each user.

[1158] Specific example

[1159] For example, if a user frequently browses electronic devices on an e-commerce application, the server can send push notifications recommending new products within that category. The following example prompt message is used by the server for this purpose.

[1160] Example of a prompt:

[1161] "Please recommend electronic devices to user 123 who has been frequently browsing electronic devices recently. The following is user behavior data for this purpose."

[1162] In this way, by implementing the present invention, the accuracy of recommendation information and advertising targeting for users can be significantly improved.

[1163] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1164] Step 1:

[1165] Initial setup of the device

[1166] The device comes pre-installed with a generative AI application at the time of shipment. Once the user completes the initial setup of the device, this application becomes ready to launch. This allows the user to use the application immediately after the initial setup.

[1167] Input: Initial device setup

[1168] Output: A terminal with a generative AI application installed.

[1169] Step 2:

[1170] Collection of user behavior data

[1171] When a user interacts with a generative AI application, the application collects user behavior data in real time, such as text input, click history, purchase history, and browsing history. This data is recorded using a data collection SDK on the device.

[1172] Input: User actions (text input, clicks, purchases, browsing)

[1173] Output: Collected user behavior data

[1174] Step 3:

[1175] Data transmission and storage

[1176] The device sends collected user behavior data to the server at regular intervals. The data is encrypted and sent to the server via a secure channel such as HTTPS. The server stores the received data in a database and performs data formatting and cleaning as needed.

[1177] Input: Collected user behavior data

[1178] Output: User behavior data stored on the server

[1179] Step 4:

[1180] Analysis of integrated data

[1181] The server integrates user behavior data with data from multiple services. This analysis utilizes AI algorithms and machine learning models designed by data scientists and engineers. Libraries such as Python's Pandas and Scikit-learn are used to reveal user interests and behavioral trends.

[1182] Input: Integrated user behavior data

[1183] Output: Analysis results (user interests and behavioral trends)

[1184] Step 5:

[1185] Recommendation information generation

[1186] Based on the analysis results, the server generates personalized recommendations for each user. For example, related products are suggested based on the categories of items the user has recently purchased or viewed. This information is generated in real time and may be provided in the form of push notifications.

[1187] Input: Analysis results

[1188] Output: Generated recommendation information

[1189] Step 6:

[1190] Providing recommendation information via push notifications

[1191] The device pushes the generated recommendation information to the user. This allows the user to receive new recommendations without having to open the application.

[1192] Input: Generated recommendation information

[1193] Output: Recommendation information pushed to the user.

[1194] Step 7:

[1195] Ad targeting

[1196] Based on the analysis results, the server provides personalized advertising and promotional information to multiple services. This ensures that the most relevant ads are displayed to each user, maximizing the effectiveness of ad targeting.

[1197] Input: Analysis results

[1198] Output: Advertising information provided to the service

[1199] 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.

[1200] The system of the present invention pre-installs generative AI applications through user operation, collects and transmits user behavior data and emotional data to a server, analyzes integrated data, generates and delivers recommendation information, and performs advertising targeting. The details are described below.

[1201] Device reset and application pre-installation

[1202] The device comes pre-installed with generative AI applications during initial setup. This allows users to immediately use these applications from the moment they first use the device. These applications include, for example, AI assistants and content generation tools. Furthermore, an emotion engine is integrated into the device, enabling the collection of user emotion data.

[1203] Collection of user behavior data and emotional data

[1204] When a user uses a generative AI application on their device, the application collects user behavior data. This behavior data includes text input, clicks, and browsing time. Furthermore, the emotion engine analyzes the user's text input and voice data to collect emotion data. This also results in data based on the user's emotional state.

[1205] Data transmission and storage

[1206] The device sends collected behavioral and emotional data to the server. The data is encrypted during transmission and sent through a secure communication channel. The server stores the received data in an appropriate database and performs data formatting and cleaning. This converts the data into a unified format.

[1207] Analysis of integrated data

[1208] The server analyzes user behavior and sentiment data integrated with multiple service data sets. This analysis is performed using AI and machine learning algorithms designed by data scientists and engineers. The goal of the analysis is to reveal users' interests, behavioral patterns, and real-time emotional states, and to generate optimal recommendation information based on this information.

[1209] Generation and distribution of recommendation information

[1210] Based on the analysis results, the server generates optimal recommendation information for the user. For example, if the user is feeling stressed, it can suggest relaxation content, and if they are excited, it can suggest active content. The generated recommendation information is sent to the device as a push notification and displayed in real time to attract the user's attention.

[1211] Ad targeting

[1212] The server provides analysis results to multiple services (e.g., advertising networks and electronic payment services). This allows service providers to display personalized ads and promotions to each user. Improved ad targeting accuracy enables ad delivery that better fits user interests.

[1213] User usage examples

[1214] For example, consider a scenario where a user uses an AI assistant app to manage their daily tasks. The user asks the assistant, "Tell me my schedule for tomorrow." The device records this input and sends it to the server. The emotion engine identifies the user's emotions from the text and tone of voice used in their input, and also sends the results to the server. The server integrates and analyzes the user's emotion data with other behavioral data to generate recommendations for their next task management. It then pushes links to the latest task management apps and related blog posts to the device, suggesting them to the user. If the user is feeling stressed, information to help them relax is also provided.

[1215] The above describes a specific embodiment of the system of the present invention. Through this system, users can receive personalized services and content, and the accuracy of advertising targeting is also improved. By introducing an emotion engine, it is possible to provide more appropriate recommendations according to the user's emotional state.

[1216] The following describes the processing flow.

[1217] Step 1:

[1218] During the initial setup of the device, generative AI applications and an emotion engine are pre-installed. This allows users to immediately use these applications from the moment they first use the device.

[1219] Step 2:

[1220] The user launches a generative AI application and performs actions such as text input, voice input, and touch operations. For example, the user might type "Tell me tomorrow's weather" into the AI ​​assistant.

[1221] Step 3:

[1222] The device collects user input and actions as behavioral data. This behavioral data includes entered text, timing of actions, and usage time.

[1223] Step 4:

[1224] The emotion engine analyzes the user's text input, voice data, facial expression data, etc., to identify the user's emotional state. For example, it can determine whether the user's current emotion is "stress" or "excitement" from the text they input or the audio of their speech.

[1225] Step 5:

[1226] The device sends collected behavioral and emotional data to the server. The data is encrypted during transmission and sent through a secure communication channel.

[1227] Step 6:

[1228] The server stores the received behavioral and emotional data in data storage, and then formats and cleans the data. This converts the data into a unified format.

[1229] Step 7:

[1230] The server integrates data stored on it with data from other services (for example, online shopping purchase history or social media posts).

[1231] Step 8:

[1232] The server analyzes the integrated data. Here, machine learning algorithms and AI are used to analyze users' interests, behavioral patterns, and real-time emotional states to identify user preferences and interests.

[1233] Step 9:

[1234] The server generates optimal recommendation information for the user based on the analysis results. For example, if the user is feeling stressed, it suggests relaxation clips; if they are excited, it suggests active event information.

[1235] Step 10:

[1236] The server sends the generated recommendation information to the device via push notification. This allows users to receive new information in real time.

[1237] Step 11:

[1238] Users check the push notifications they receive and browse and use content and services that interest them. This activity is also collected as behavioral and sentiment data and used to generate subsequent recommendations.

[1239] Step 12:

[1240] The server provides the analysis results to other service providers (e.g., advertising networks and electronic payment services). This allows each service to utilize the analysis results for ad targeting and deliver more effective ads.

[1241] The above outlines the specific processing steps of this system. This process allows users to receive personalized services and content, and enables service providers to achieve highly accurate ad targeting. The introduction of an emotion engine makes it possible to provide more appropriate recommendations based on the user's emotional state.

[1242] (Example 2)

[1243] 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".

[1244] Traditional recommendation and advertising targeting systems analyze user behavior data, including browsing history, to provide recommendations and advertisements. However, they have failed to provide highly accurate recommendations and advertising targeting that take emotional states into account. This is because it is difficult to optimally select content and advertisements according to the user's emotions.

[1245] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for pre-installing a generative AI application on a terminal, means for collecting user behavior data and emotional data on the terminal, means for transmitting the collected data to the server, means for analyzing user behavior data and emotional data integrated with multiple information data on the server, means for generating recommendation information for the user based on the analysis results, means for transmitting the generated recommendation information to the terminal, and means for providing the analysis results to multiple information provision services and using them for advertising targeting. This makes it possible to provide highly accurate recommendation information and advertising targeting according to the user's emotional state.

[1246] A "device" is an electronic device that a user can directly operate, and includes personal computers, smartphones, tablets, and other similar devices.

[1247] "Generative AI applications" are software that utilizes artificial intelligence to generate content based on user input, and include AI assistants and content generation tools.

[1248] "User behavior data" refers to data related to operations and actions performed by users on their devices, including text input, clicks, and browsing time.

[1249] "Emotional data" refers to emotion-related data extracted from user input and voice, and includes information that indicates the user's emotional state (such as joy, anger, sadness, etc.).

[1250] A "server" is a computer system that provides services to terminals via a network, and has the functions of receiving, storing, and analyzing data.

[1251] "Information data" refers to various types of data obtained from servers and other data sources, including user behavior data and sentiment data.

[1252] "Analysis" is the process of finding patterns based on collected data, and it is carried out using AI and machine learning algorithms.

[1253] "Recommendation information" refers to recommended content and suggestions generated by the server based on the user's interests and behavior, and includes information that is sent to the user via push notifications.

[1254] "Ad targeting" is a method of selecting and displaying the most suitable advertisements to users based on analytical data, enabling personalized ad delivery.

[1255] The system of this invention pre-installs a generative AI application on a terminal, collects and analyzes user behavior data and emotional data, and generates and delivers optimal recommendation information to the user based on that data. Furthermore, to improve the accuracy of advertising targeting, the analysis results are provided to multiple information provision services.

[1256] Device reset and application pre-installation

[1257] The device undergoes initial setup upon shipment or first boot-up, and a pre-installation script is executed to install generative AI applications into the system. These applications include, for example, an AI assistant and content generation tools, allowing users to use them immediately from the moment they first use the device. Furthermore, an emotion engine is integrated into the device, ready to collect user emotion data.

[1258] Collection of user behavior data and emotional data

[1259] When a user uses a generative AI application on their device, the application collects user activity logs (text input, clicks, browsing time, etc.) and stores them in a local database. Simultaneously, an emotion engine operates, analyzing the user's text input and voice data in real time. This also collects emotion data indicating the user's emotional state (joy, anger, sadness, etc.).

[1260] Data transmission and storage

[1261] The terminal prepares the collected behavioral and emotional data in batch processing, compresses and encrypts it, and then sends it to the server. A secure communication protocol (e.g., HTTPS) is used in this transmission process. The server stores the received data in an appropriate database (e.g., SQL database, NoSQL database) and performs data formatting and cleaning using an ETL (Extract, Transform, Load) process.

[1262] Analysis of integrated data

[1263] The server analyzes user behavior and sentiment data integrated with multiple data sets. This analysis utilizes AI and machine learning algorithms designed by data scientists and engineers. The goal of the analysis is to reveal users' interests, behavioral patterns, and real-time emotional states, and to generate optimal recommendation information based on this information.

[1264] Generation and distribution of recommendation information

[1265] Based on the analysis results, the server generates optimal recommendation information for the user. For example, if the user is feeling stressed, it suggests relaxation content; if they are excited, it suggests active content. The generated recommendation information is sent to the device in real time as a push notification and displayed to the user.

[1266] Ad targeting

[1267] The server provides analysis results to multiple information providers for use in advertising targeting. This allows service providers to display personalized ads and promotions to each user. Improved accuracy in advertising targeting enables the delivery of ads that better fit user interests.

[1268] User usage examples

[1269] For example, consider a scenario where a user uses an AI assistant app to manage their daily tasks. The user asks the assistant, "Tell me my schedule for tomorrow." The device records this input and sends it to the server. The emotion engine identifies the user's emotions from the text and tone of voice used in their input, and also sends the results to the server. The server integrates and analyzes the user's emotion data with other behavioral data to generate recommendations for their next task management. It then pushes links to the latest task management apps and related blog posts to the device, suggesting them to the user. If the system determines that the user is stressed, it also provides information to help them relax.

[1270] Example of a prompt

[1271] "Assuming the user is in an emotionally unsettled state, please generate recommendations that the AI ​​assistant would make in that situation."

[1272] As described above, the system of the present invention can provide appropriate recommendation information and improve the accuracy of advertising targeting by collecting and analyzing user behavior data and emotional data.

[1273] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1274] Step 1:

[1275] Device initialization and pre-installation of generative AI applications

[1276] Upon initial startup, the device performs an initial setup and installs generative AI applications (e.g., AI assistant, content generation tool, etc.) into the system via a pre-installation script. The input is a device in its factory default state, and the output is a usable device with generative AI applications and an emotion engine installed.

[1277] Step 2:

[1278] Collection of user behavior data and emotional data

[1279] When a user interacts with a generative AI application on their device, the application collects user behavior data (text input, clicks, browsing time, etc.) and stores it in a local database. Simultaneously, the emotion engine analyzes the user's text input and voice data in real time and extracts emotion data. The input consists of user behavior and voice / text data, and the output consists of behavior data and emotion data stored in the local database.

[1280] Step 3:

[1281] Data preparation and transmission

[1282] The terminal prepares the collected behavioral and sentimental data in batch processing, compressing and encrypting the data. It then sends the data to the server using a secure communication protocol (e.g., HTTPS). The input consists of behavioral and sentimental data in a local database, and the output is securely encrypted data sent to the server.

[1283] Step 4:

[1284] Data storage and formatting

[1285] The server stores the received data in an appropriate database (e.g., SQL database, NoSQL database) and performs an ETL (Extract, Transform, Load) process to format and clean the data. The input is encrypted data, and the output is clean data converted to a unified format, which is then stored in the database.

[1286] Step 5:

[1287] Analysis of integrated data

[1288] The server analyzes user behavior data and sentiment data integrated with multiple pieces of informational data. This analysis utilizes AI and machine learning algorithms to reveal user interests, behavioral patterns, and emotional states. The input consists of integrated user data and informational data, and the output is the analysis results.

[1289] Step 6:

[1290] Recommendation information generation

[1291] The server generates optimal recommendation information for the user based on the analysis results. For example, if the user is feeling stressed, it suggests relaxation content; if they are excited, it suggests active content. The input is the analysis results, and the output is the recommendation information suggested to the user.

[1292] Step 7:

[1293] Recommendation information distribution

[1294] The generated recommendation information is sent to the device as a push notification. The user receives this information in real time. The input is the recommendation information, and the output is the push notification displayed on the user's device.

[1295] Step 8:

[1296] Executing ad targeting

[1297] The server provides analysis results to multiple information providers for use in advertising targeting. This allows service providers to display personalized ads and promotions. The input is the analysis results, and the output is targeted ads delivered to the user.

[1298] (Application Example 2)

[1299] 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".

[1300] Traditional e-commerce sites have struggled to effectively utilize user behavioral and emotional data to provide personalized product recommendations in real time. Furthermore, improving the accuracy of advertising targeting based on collected data has also been challenging. This invention aims to solve these problems and provide a system that enables more appropriate and effective product recommendations and advertising to users.

[1301] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting user behavior data and emotional data, means for encrypting the collected data and transmitting it to the server, means for analyzing user behavior data and emotional data integrated with multiple service data, means for generating personalized product recommendation information based on the analysis results, means for pushing the generated recommendation information to the terminal in real time, and means for providing the analysis results to multiple services and using them for advertising targeting. This makes it possible to accurately capture user behavior and emotions and provide personalized product recommendations and advertisements at the appropriate time.

[1302] A "device" is an electronic device designed for use by users, and includes smartphones, tablets, and other similar devices.

[1303] A "generative AI application" is a software application that uses artificial intelligence technology to provide diverse services to users, and has the ability to generate objects, generate content, or provide assistant functions.

[1304] "User behavior data" refers to data that shows a user's operation history and behavioral patterns, and includes text input, clicks, biometric information, and browsing time.

[1305] "Emotional data" refers to data that indicates a user's emotional state, and is information extracted from voice tone and text content.

[1306] A "server" is a computer system that stores, processes, and distributes data over a network.

[1307] "Data encryption" refers to the technology of converting data into a format that cannot be deciphered by third parties, thereby ensuring the secure transmission of data.

[1308] "Multiple service data" refers to a collection of data gathered from different services, and involves centrally managing the data provided by each service.

[1309] "Recommendation information" refers to information about products and content that is suggested to users based on their behavior and emotions.

[1310] "Push notifications" are a notification function that sends information from a server to a device in real time to alert the user.

[1311] "Ad targeting" is a method of displaying individually optimized advertisements based on user characteristics and behavioral analysis.

[1312] The system of the present invention pre-installs generative AI applications through user operation, collects user behavior data and emotional data, analyzes integrated data, generates and delivers recommendation information, and performs advertising targeting. The details are described below.

[1313] Device reset and application pre-installation

[1314] The device comes pre-installed with generative AI applications during initial setup. This allows users to immediately use these applications from the moment they first use the device. These applications include, for example, AI assistants and content generation tools. Furthermore, an emotion engine is integrated into the device, enabling the collection of user emotion data.

[1315] Collection of user behavior data and emotional data

[1316] When a user uses a generative AI application on their device, the application collects user behavioral and emotional data. This behavioral data includes text input, clicks, and browsing time. Furthermore, the emotion engine analyzes the user's text input and voice data to collect emotional data. This also results in data based on the user's emotional state.

[1317] Data transmission and storage

[1318] The device encrypts the collected behavioral and emotional data and sends it to the server. The data is encrypted during transmission and transmitted through a secure communication channel. The server stores the received data in an appropriate database and performs data formatting and cleaning. This converts the data into a unified format.

[1319] Analysis of integrated data

[1320] The server analyzes user behavior and sentiment data integrated with multiple service data sets. This analysis is performed using AI and machine learning algorithms designed by data scientists and engineers. The goal of the analysis is to reveal users' interests, behavioral patterns, and real-time emotional states, and to generate optimal recommendation information based on this information.

[1321] Generation and distribution of recommendation information

[1322] Based on the analysis results, the server generates optimal product recommendations for the user. For example, if the user is feeling stressed, it can suggest relaxation products; if they are excited, it can suggest active products. The generated recommendations are sent to the device as real-time push notifications and displayed immediately to attract the user's attention.

[1323] Ad targeting

[1324] The server provides analysis results to multiple services (e.g., advertising networks and electronic payment services). This allows service providers to display personalized ads and promotions to each user. Improved ad targeting accuracy enables ad delivery that better fits user interests.

[1325] User usage examples

[1326] For example, consider a scenario where a user is browsing an online shopping site using an AI shopping assistant app. The user types, "I'm looking into product A." The device records this input and sends it to the server. The emotion engine identifies the user's emotions from the text and tone of voice used in their input, and also sends the results to the server. The server integrates and analyzes the user's emotion data with other behavioral data to generate recommendations for their next purchase. It then pushes the latest product information and links to related promotions to the device, suggesting them to the user. If the user is excited, information on active products is also provided simultaneously.

[1327] Examples of prompt statements

[1328] Here are some specific examples of prompt statements to input into a generative AI model:

[1329] If a user shows interest in product A, analyze and recommend the following products:

[1330] User input: I am researching product A.

[1331] User's emotion: Excitement

[1332] Product Catalog: ["Product A", "Product B", "Product C"]

[1333] The above describes a specific embodiment of the system of the present invention. Through this system, users can receive personalized services and content, and the accuracy of advertising targeting can also be improved. By introducing an emotion engine, it is possible to provide more appropriate recommendations according to the user's emotional state.

[1334] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1335] Step 1:

[1336] The device comes pre-installed with a generative AI application. The installed application automatically launches during the user's initial setup, ensuring it's ready when the user begins using the device. Here, the input is the device's initial setup, and the output is the state in which the AI ​​application is available for use.

[1337] Step 2:

[1338] When a user begins using a generative AI application on their device, the application collects user behavioral and emotional data. This collection includes behavioral data such as text input, clicks, and browsing time, as well as emotional data derived from voice tone and keyboard typing speed. Here, input is the user's actions, and output is the collected data.

[1339] Step 3:

[1340] The device encrypts the collected behavioral and emotional data and transmits it to the server via a secure communication channel. A data encryption algorithm is used in this process. The input here is the collected data, and the output is the encrypted data.

[1341] Step 4:

[1342] The server stores the received data in the appropriate database and performs data formatting and cleaning. This process includes standardizing the data format and handling missing data values. The input here is encrypted data, and the output is formatted and cleaned data.

[1343] Step 5:

[1344] The server analyzes user behavior and sentiment data integrated with multiple service data sets. AI and machine learning algorithms are used for the analysis to reveal user interests, behavioral patterns, and real-time emotional states. The input here consists of formatted and cleaned data and existing service data, while the output is the analysis results.

[1345] Step 6:

[1346] The server generates personalized product recommendations based on the analysis results. For example, if the user is stressed, it suggests relaxation-related products; if they are agitated, it suggests active products. A generative AI model is used in this process. The input here is the analysis results, and the output is personalized recommendations.

[1347] Step 7:

[1348] The server pushes the generated recommendation information to the device in real time. A push notification protocol is used to ensure that the information reaches the user immediately. The input here is the recommendation information, and the output is the notification to the device.

[1349] Step 8:

[1350] The device displays received push notifications to the user. These notifications contain relevant product links and promotional information, designed for easy user access. Here, the input is the push notification, and the output is the display on the user interface.

[1351] Step 9:

[1352] The server provides analysis results to multiple services (ad networks, electronic payment services, etc.) for use in ad targeting. This allows each service provider to implement personalized ads and promotions for each user. The input here is the analysis results, and the output is personalized ads.

[1353] 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.

[1354] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1355] 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.

[1356] 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.

[1357] 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.

[1358] 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.

[1359] 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.

[1360] 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.

[1361] 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."

[1362] 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.

[1363] 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.

[1364] 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.

[1365] 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.

[1366] 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.

[1367] 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.

[1368] 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.

[1369] 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.

[1370] 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.

[1371] 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.

[1372] 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.

[1373] 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.

[1374] The following is further disclosed regarding the embodiments described above.

[1375] (Claim 1)

[1376] Methods for pre-installing generative AI applications on terminals,

[1377] means for collecting user behavior data on the aforementioned terminal,

[1378] Means for transmitting the collected data to a server,

[1379] The server includes means for analyzing user behavior data integrated with multiple service data,

[1380] A means for generating recommendation information for users based on analysis results,

[1381] A means for transmitting the generated recommendation information to the terminal,

[1382] A means of providing the aforementioned analysis results to multiple services and using them for advertising targeting,

[1383] A system that includes this.

[1384] (Claim 2)

[1385] The system according to claim 1, further comprising means for push notification of the aforementioned recommendation information to a terminal.

[1386] (Claim 3)

[1387] The system according to claim 1, wherein the generative AI application collects behavioral data based on the user's text input and click history.

[1388] "Example 1"

[1389] (Claim 1)

[1390] Methods for pre-installing generative AI applications on terminals,

[1391] means for collecting user behavior data on the terminal,

[1392] Means for transmitting the collected data to a server,

[1393] The server includes means for analyzing user behavior data integrated with multiple service data,

[1394] A means for generating recommendation information for users based on analysis results,

[1395] A means for transmitting the generated recommendation information to the terminal,

[1396] A means of providing the aforementioned analysis results to multiple services and using them for advertising targeting,

[1397] A means for transmitting the data collected by the terminal to a server via a secure channel and storing it in an encrypted state,

[1398] A system that includes this.

[1399] (Claim 2)

[1400] The system according to claim 1, further comprising means for push notification of the aforementioned recommendation information to a terminal.

[1401] (Claim 3)

[1402] The system according to claim 1, wherein the generative AI application collects behavioral data based on the user's text input, clicks, and browsing time.

[1403] "Application Example 1"

[1404] (Claim 1)

[1405] Methods for pre-installing generative AI applications on terminals,

[1406] means for collecting user behavior data on the aforementioned terminal,

[1407] Means for transmitting the collected data to a server,

[1408] The server includes means for analyzing user behavior data integrated with multiple service data,

[1409] A means for generating recommendation information for users based on analysis results,

[1410] A means for transmitting the generated recommendation information to the terminal,

[1411] A means of providing the aforementioned analysis results to multiple services and using them for advertising targeting,

[1412] The e-commerce site application installed on the aforementioned terminal includes means for generating recommendation information based on the user's purchase history and browsing history,

[1413] A means for sending the generated recommendation information as a push notification in real time,

[1414] A system that includes this.

[1415] (Claim 2)

[1416] The system according to claim 1, further comprising means for push notification of the aforementioned recommendation information to a terminal.

[1417] (Claim 3)

[1418] The system according to claim 1, wherein the generative AI application collects behavioral data based on the user's text input and click history.

[1419] "Example 2 of combining an emotion engine"

[1420] (Claim 1)

[1421] Methods for pre-installing generative AI applications on terminals,

[1422] Means for collecting user behavior data and emotional data on the terminal,

[1423] Means for transmitting the collected data to a server,

[1424] The server includes means for analyzing user behavior data and sentiment data integrated with multiple pieces of information data,

[1425] A means for generating recommendation information for users based on analysis results,

[1426] A means for transmitting the generated recommendation information to the terminal,

[1427] A means of providing the aforementioned analysis results to multiple information provision services and using them for advertising targeting,

[1428] A system that includes this.

[1429] (Claim 2)

[1430] The system according to claim 1, further comprising means for push notification of the aforementioned recommendation information to a terminal.

[1431] (Claim 3)

[1432] The system according to claim 1, wherein the generative AI application collects behavioral data based on the user's text input, clicks, and browsing time, and further collects the user's emotional data using an emotion engine.

[1433] "Application example 2 when combining with an emotional engine"

[1434] (Claim 1)

[1435] Methods for pre-installing generative AI applications on terminals,

[1436] Means for collecting user behavior data and emotional data on the terminal,

[1437] A means for encrypting the collected data and sending it to a server,

[1438] The server includes means for analyzing user behavior data and sentiment data integrated with multiple service data,

[1439] A means for generating personalized product recommendation information based on analysis results,

[1440] A means for sending the generated recommendation information to the terminal in real time via push notification,

[1441] A means of providing the aforementioned analysis results to multiple services and using them for advertising targeting,

[1442] A system that includes this.

[1443] (Claim 2)

[1444] The system according to claim 1, further comprising means for push notification of the real-time generated recommendation information to a terminal.

[1445] (Claim 3)

[1446] The system according to claim 1, wherein the generative AI application collects behavioral data and emotional data based on the user's text input and click history. [Explanation of Symbols]

[1447] 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. Methods for pre-installing generative AI applications on terminals, means for collecting user behavior data on the aforementioned terminal, Means for transmitting the collected data to a server, The server includes means for analyzing user behavior data integrated with multiple service data, A means for generating recommendation information for users based on analysis results, A means for transmitting the generated recommendation information to the terminal, A means of providing the aforementioned analysis results to multiple services and using them for advertising targeting, A system that includes this.

2. The system according to claim 1, further comprising means for push notification of the aforementioned recommendation information to a terminal.

3. The system according to claim 1, wherein the generative AI application collects behavioral data based on the user's text input and click history.

Images