system

Abstract

We provide the system. [Solution] A means for collecting user online behavior data, A means of analyzing collected user data to extract user interests and preferences, A means of generating personalized recommendations for each user, A means of notifying users of the generated recommendations, The means of accessing the hometown tax donation site by clicking a link from the information provided, A method for completing a donation based on the return gift information selected by the user, 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 method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] As the market scale of hometown tax payment expands, the competition for obtaining donations between local governments has intensified, and local governments are seeking means to effectively increase the amount of donations. On the other hand, since there are many options for users, it is difficult to efficiently find a return gift that suits their preferences. Therefore, there is a need to provide a mechanism that allows local governments to efficiently increase donations and users to easily find a return gift that suits them.

Means for Solving the Problems

[0005] This invention solves the above problem by providing a system for collecting and analyzing users' online behavior data. This system includes means for analyzing the collected user data to extract the user's preferences and interests. It also includes means for generating personalized recommendations for hometown tax donations for each user and notifying them of this information through a messaging service. The information thus generated provides a means for users to access the relevant return gift information page when they click on a link to a hometown tax donation site, allowing users to easily complete their donations. This enables local governments to efficiently increase donations, and users to easily find return gifts that suit them.

[0006] "Online behavioral data" refers to information about a user's actions on the internet, specifically data such as web pages viewed, search queries, click history, and time of day.

[0007] "Personalization" refers to providing customized suggestions and information tailored to the individual user's characteristics and preferences.

[0008] "Hometown tax donation information" refers to information related to hometown tax donations, specifically including donation amounts, the contents of return gifts, and information about local governments.

[0009] A "messaging service" refers to a means of communication that allows users to send and receive text, images, audio, video, and other content over the internet.

[0010] "Clicking a link" refers to the action of a user selecting and executing a hyperlink within a webpage or message.

[0011] A "hometown tax donation website" refers to a website where users can complete the procedures for making hometown tax donations, such as selecting return gifts and completing their donations.

[0012] A "return gift information page" refers to a webpage on a hometown tax donation website that displays detailed information about products offered as a reward for donations.

[0013] "Means of completing a donation" refers to the process by which a user can enter the necessary information and then confirm the completion of the payment or procedure. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13]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

[0015] 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.

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

[0017] 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 a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, 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.

[0019] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

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

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0031] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] As an embodiment of this invention, a system is described that collects and analyzes users' online behavior data to provide personalized information on hometown tax donations.

[0036] System Overview

[0037] This system operates by combining the user's device, a server, and a messaging service. The user's device collects online behavior data and sends it to the server. The server analyzes the received data and generates personalized information about hometown tax donations. The generated information is notified to the user via the messaging service, and the user clicks on a link in the notification to access the hometown tax donation website. Finally, the user confirms the information about the return gifts, completes the necessary procedures, and finishes the donation.

[0038] Collection and transmission of user data

[0039] Device: When a user browses a webpage, the device uses browser cookies to collect data about the user's online behavior. It also collects metadata for images and videos uploaded to Google Photos. The collected data is encrypted for privacy protection. The encrypted data is transmitted to the server using secure communication methods.

[0040] Data analysis and personalization

[0041] Server: Stores received user data in a database. The stored data is input into an AI model to analyze the user's behavior patterns and interests. For example, if a user frequently visits cooking recipe websites, the AI ​​model will determine that the user is interested in "cooking" and "gourmet food." The analysis results are recorded in the database as a personalized list of recommendations.

[0042] Specific example: If user A visits a cooking-related website, the server analyzes their behavioral data and recommends local specialties or gourmet products as thank-you gifts.

[0043] Generating and notifying recommendations

[0044] Server: Based on user preferences obtained through analysis, the server selects appropriate return gift information from the hometown tax donation return gift database. The selected information is then generated as a personalized notification message.

[0045] Terminal (messaging service): Sends personalized notification messages to users via LINE or other messaging services.

[0046] User actions and final donation procedures

[0047] User: Users who receive a notification can access the relevant page on the Furusato Nozei (hometown tax donation) website by clicking the link in the message.

[0048] Terminal: The user is redirected to a hometown tax donation website, where they can view details on the return gift information page. They add suitable return gifts to their cart, enter the necessary information, and complete the donation.

[0049] Specific example: When user A clicks on the link they receive in the notification, they are directed to a detailed page about the local specialty product and guided through the process of completing the donation.

[0050] This system allows users to easily receive information about return gifts that match their interests and preferences, and also enables local governments to efficiently acquire donations.

[0051] The following describes the processing flow.

[0052] Step 1:

[0053] Device: When a user browses a webpage, browser cookies are collected. Cookies include information such as the URL of the visited webpage, the date and time of the visit, and the duration of the visit.

[0054] Step 2:

[0055] Device: Collects metadata from images and videos uploaded by users to Google Photos. Metadata includes tag information and location information.

[0056] Step 3:

[0057] Device: Encrypts collected cookies and photo data and sends them to the server using secure communication methods (e.g., SSL / TLS).

[0058] Step 4:

[0059] Server: Stores received user data in the database. The data includes the user's ID, cookie information, and photo data.

[0060] Step 5:

[0061] Server: Inputs user data stored in the database into the AI ​​model. The AI ​​model analyzes the user's online behavior patterns and extracts their interests and preferences.

[0062] Step 6:

[0063] Server: Based on the analysis results of the AI ​​model, it generates personalized recommendations for hometown tax donations. For example, for a user interested in "cooking," it selects local specialty products and gourmet items as return gifts.

[0064] Step 7:

[0065] Server: Converts personalized recommendations into LINE message format and links them to the user's LINE ID.

[0066] Step 8:

[0067] Terminal (messaging service): Personalized hometown tax donation information is pushed to the user via LINE. The notification includes a link.

[0068] Step 9:

[0069] User: Receives a LINE notification and clicks on the link to the gift information that interests them.

[0070] Step 10:

[0071] Terminal: The clicked link redirects to the Furusato Nozei (hometown tax donation) website and displays the details page for the corresponding return gift.

[0072] Step 11:

[0073] User: Check the details on the gift information page and add it to your cart if you wish to purchase it.

[0074] Step 12:

[0075] User: Enter the required information (e.g., address, payment information) and complete the donation process.

[0076] By following these steps, users can easily find information on the most suitable return gifts for them and complete their donations. Furthermore, local governments can efficiently acquire donations.

[0077] (Example 1)

[0078] 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."

[0079] Conventional hometown tax donation systems lacked the functionality to effectively analyze users' diverse interests and online behavior and provide personalized return gift information based on that analysis. As a result, users found it difficult to find return gift information that matched their interests, and local governments were unable to effectively collect donations. This invention aims to solve these problems and promote the use of hometown tax donations by providing recommended information tailored to each user.

[0080] 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.

[0081] In this invention, the server includes means for collecting user online behavior data, means for encrypting the collected user data and transmitting it to the server, means for storing the received user data in a database, means for inputting the stored user data into a model for analysis and extracting the user's interests and preferences, means for generating personalized recommendations for each user, means for notifying the user of the generated recommendations using a messaging service, means for accessing a hometown tax donation site by clicking a link in the notified information, and means for completing the donation based on the return gift information selected by the user. This makes it possible to provide return gift information based on the user's interests and preferences, and to facilitate the donation process.

[0082] "User online behavior data" refers to information about a user's actions on the internet, such as web page browsing history and metadata.

[0083] "User data encryption" is a technique that uses specific algorithms to enhance security in order to prevent collected user data from being deciphered by third parties.

[0084] A "server" is a computer system that receives, analyzes, and stores users' online behavior data in a database.

[0085] A "database" is a data storage system that organizes and stores users' online behavior data and analysis results, allowing for quick access as needed.

[0086] A "model" refers to an algorithm or machine learning framework used for data analysis (for example, TENSORFLOW® or PyTorch), which is used to extract user behavior patterns and interests.

[0087] "Personalized recommendations" refer to reward information and recommendations that are identified based on each user's online behavior data and optimized to the user's interests and preferences.

[0088] A "messaging service" is a means of communication used to send personalized notification messages, and includes services like LINE and email.

[0089] A "hometown tax donation site" is a website that users access to actually make donations.

[0090] "Methods for completing a donation" refers to the process by which a user accesses a hometown tax donation website, selects a return gift, enters the necessary information, and completes the donation procedure.

[0091] This invention is a system that collects and analyzes users' online behavior data to provide personalized information about hometown tax donations. This system operates by combining the user's terminal, a server, and a messaging service.

[0092] Collection and transmission of user data

[0093] Device: When a user browses a webpage, the device uses browser cookies to collect data about the user's online behavior. It also collects metadata for images and videos uploaded by the user to Google Photos. The collected data is encrypted to protect user privacy. This encryption uses methods such as AES (Advanced Encryption Standard). The encrypted data is transmitted to the server using secure communication methods such as SSL (Secure Socket Layer) or TLS (Transport Layer Security).

[0094] Receiving and storing data

[0095] Server: The server decrypts the encrypted data received using SSL / TLS and stores it in the database. This database utilizes a common database management system (DBMS) such as MySQL® or PostgreSQL.

[0096] Data analysis and personalization

[0097] Server: Stored data is input into AI models using machine learning frameworks such as TensorFlow and PyTorch. The AI ​​models analyze user behavior patterns and interests. For example, if a user frequently visits cooking recipe websites, the server uses the AI ​​model to determine that the user is interested in "cooking" and "gourmet food." The analysis results are recorded in the database as a personalized list of recommendations.

[0098] Specific example: If user A frequently visits cooking-related websites, the server analyzes their behavioral data and recommends local specialties and gourmet products as thank-you gifts.

[0099] Generating and notifying recommendations

[0100] Server: Based on the analysis results, the server selects appropriate return gift information from the hometown tax return gift database. The selected information is then generated as a personalized notification message for the user. Email services (e.g., SendGrid) or messaging APIs (e.g., LINE Messaging API) are used to generate the notification message.

[0101] Terminal (Messaging Service): The generated notification message is sent to the user via LINE or other messaging services. The notification message includes a link to information about the reward item.

[0102] User actions and final donation procedures

[0103] User: Users who receive a notification can access the relevant page on the Furusato Nozei (hometown tax donation) website by clicking the link in the message.

[0104] Device: When you click the link, your device will automatically redirect to the Furusato Nozei (hometown tax donation) website. There, the user can check the details of the return gifts and add their favorite gifts to their cart. They then enter the necessary information to complete the donation. This process includes payment methods such as credit card and bank transfer.

[0105] Specific example: When user A clicks on the link they receive in the notification, they are taken to a page detailing the local specialty product and guided through the process of completing the donation. This allows user A to easily make a donation.

[0106] Example of a prompt

[0107] "Cookies and personal data protection"

[0108] "Introduction of AI models based on user behavior"

[0109] "Personalized notification system for hometown tax donations"

[0110] "A combination of secure data transmission and AI analysis"

[0111] This system allows users to easily receive information about return gifts that match their interests and preferences, and also enables local governments to efficiently acquire donations.

[0112] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0113] Step 1:

[0114] User data collection

[0115] Device: When a user browses a webpage, the device uses browser cookies to collect data about the user's online behavior. Furthermore, it collects metadata for images and videos uploaded to Google Photos. This collected data includes information such as the date and location where the image was taken.

[0116] Input: User's web page browsing history, image and video metadata

[0117] Output: Collected user online behavior data

[0118] Specific operation: The web browser uses cookies to save the URL and date / time of the visited web pages on the device. The Google Photos API is used to retrieve metadata for images and videos uploaded by the user.

[0119] Step 2:

[0120] Sending user data

[0121] Terminal: Collected data is encrypted using AES (Advanced Encryption Standard). Encrypted data is sent to the server using SSL (Secure Socket Layer) or TLS (Transport Layer Security).

[0122] Input: User's online behavior data before encryption

[0123] Output: Encrypted user data

[0124] Specific operation: The terminal encrypts the data using the AES algorithm, and then securely sends the encrypted data to the server using the SSL / TLS protocol.

[0125] Step 3:

[0126] Receiving and storing data

[0127] Server: The server receives and decrypts data encrypted with SSL / TLS. The decrypted data is stored in a database. This database uses a common DBMS such as MySQL or PostgreSQL.

[0128] Input: Encrypted user data

[0129] Output: User data stored in the database

[0130] Specific operation: The server receives data using the SSL / TLS protocol and decrypts it using the AES algorithm. The decrypted data is then stored in a MySQL database.

[0131] Step 4:

[0132] Data Analysis

[0133] Server: Data stored in the database is input into AI models using machine learning frameworks such as TensorFlow and PyTorch. The server uses the AI ​​models to analyze user behavior patterns and interests. For example, if a user frequently visits cooking recipe websites, the server will determine that the user is interested in "cooking" or "gourmet food."

[0134] Input: User data stored in the database

[0135] Output: Analyzed user interests and preferences

[0136] Specific operation: The server feeds data into the AI ​​model, executes machine learning algorithms, and analyzes user behavior patterns. The analysis results are recorded in a database.

[0137] Step 5:

[0138] Generating recommendations

[0139] Server: Based on the analysis results, the server selects appropriate return gift information from the hometown tax return gift database. The selected information is then generated as a personalized notification message for the user. Email services (e.g., SendGrid) or messaging APIs (e.g., LINE Messaging API) are used to generate the notification message.

[0140] Input: Analyzed user interests and preferences, and a database of return gifts.

[0141] Output: Personalized notification message

[0142] Specific operation: Based on the analysis results, the server extracts information on reward items that match the user's interests from the database and generates a notification message. This utilizes the SendGrid and LINE API interfaces.

[0143] Step 6:

[0144] Sending notifications

[0145] Terminal (messaging service): The generated notification message is sent to the user via LINE or other messaging services. The notification message includes a link to information about the reward item.

[0146] Input: Personalized notification message

[0147] Output: Notification messages received by the user

[0148] Specific operation: A notification message generated using the messaging API is sent to the user's LINE account.

[0149] Step 7:

[0150] Receiving notifications and clicking links

[0151] User: Users who receive a notification can access the relevant page on the Furusato Nozei (hometown tax donation) website by clicking the link in the message.

[0152] Input: Link included in the notification message

[0153] Output: The relevant page on the Furusato Tax Donation website

[0154] Specific actions: The user opens a LINE message, clicks a link to launch a web browser, and accesses a hometown tax donation website.

[0155] Step 8:

[0156] Completion of donation procedure

[0157] User: Check the details of the return gifts on the hometown tax donation website and add the desired gifts to the cart. Enter the necessary information to complete the donation. This process includes payment methods such as credit card and bank transfer.

[0158] Input: Information on return gifts from the hometown tax donation website, user payment information.

[0159] Output: Donation completion confirmation message

[0160] Specific steps: The user selects an item on the reward details page and adds it to their cart. Next, they enter the required personal and payment information to complete the donation process. Upon successful completion, a confirmation message is displayed.

[0161] (Application Example 1)

[0162] 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."

[0163] Traditional content distribution services often fail to adequately provide content tailored to users' interests and preferences, leading to increased exposure to irrelevant information and decreased satisfaction. Furthermore, the effort required for users to access diverse content results in low convenience.

[0164] 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.

[0165] In this invention, the server includes means for collecting user online behavior data, means for analyzing the collected user data to extract user interests and preferences, and means for generating personalized recommendations for each user. This makes it possible to automatically provide content that is most suitable for the user's interests and preferences.

[0166] "User online behavior data" refers to information generated when users browse, search, play, etc., on the internet.

[0167] "Analysis" is the process of examining collected data in detail and extracting users' interests and preferences.

[0168] "Personalized recommendations" refer to information that is selected and presented based on the user's interests and preferences.

[0169] A "notification" is an action that presents users with recommended information.

[0170] A "content distribution service" is a service that provides users with multimedia content such as movies, dramas, and music via the internet.

[0171] "Viewing or using" refers to the act of actually playing or consuming content selected by the user.

[0172] System Configuration

[0173] This invention describes a system that collects and analyzes users' online behavior data and provides personalized content to each user. This system operates by combining the user's terminal, a server, and a messaging service.

[0174] Collection and transmission of user data

[0175] The device collects online behavior data using browser cookies and activity logs when users browse web pages or use applications. This also includes in-app search history and viewing history. For privacy reasons, the collected data is encrypted and securely transmitted to the server using HTTPS.

[0176] Data analysis

[0177] The server stores the received user data in a database and analyzes the data using machine learning models (e.g., TensorFlow or PyTorch). The analysis process extracts interests and preferences based on the user's behavior patterns. For example, if a user frequently visits movie websites, they are determined to be interested in movies.

[0178] Generating and delivering personalized content

[0179] The server generates personalized content (e.g., recommendations for new movies or movie lists of specific genres) based on the analyzed user interests. The generated recommendations are then communicated to the user via a messaging service (e.g., Firebase Cloud Messaging).

[0180] User actions and content viewing

[0181] Users receive a notification and click a link to access the content distribution service. They then watch or use the content they selected. For example, clicking the notification might take them to a details page for a new movie, from which they can watch it directly.

[0182] Hardware and software used

[0183] Hardware: Smartphone (iOS or Android®)

[0184] Remote server: Cloud service (e.g., Amazon Web Services, Google Cloud Platform)

[0185] Software: Mobile applications (developed in Swift or Kotlin), backend servers (Node.js), databases (relational databases such as MySQL), messaging services (Firebase Cloud Messaging, Twilio, etc.)

[0186] Specific example

[0187] As a concrete example, consider the case of a movie-loving user searching for a new movie.

[0188] 1. The user browses a movie review website on their smartphone.

[0189] 2. A smartphone app collects that behavioral data and sends it to a server.

[0190] 3. The server analyzes the user's interests and identifies new releases and movies in genres of interest.

[0191] 4. Use Firebase Cloud Messaging to notify users with a personalized list of recommended movies.

[0192] 5. When a user clicks the notification, they are redirected to the app and can watch directly while viewing more details.

[0193] Example of a prompt

[0194] As an example of a prompt to input to a generative AI model,

[0195] The result is: "Please provide the URLs of movie review sites the user has recently visited. Also, please generate a list of new movies that the user might be interested in."

[0196] As described above, this system will allow users to quickly and accurately receive content that best suits their interests and preferences, resulting in a high level of satisfaction.

[0197] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0198] Step 1:

[0199] The device collects online behavioral data using browser cookies and activity logs when users browse, search, and play web pages. Search and viewing history within apps is also collected. Input data includes the user's browsing, search, and viewing history, while output data provides detailed information on these. Specifically, for example, the URL and viewing time when a user visits a movie review site are recorded.

[0200] Step 2:

[0201] The terminal encrypts the collected online behavioral data and securely transmits it to the server using HTTPS. The input data is the collected behavioral data, and the output data is the encrypted data. Specifically, the data is encrypted using the AES-256 encryption method and transmitted to the remote server.

[0202] Step 3:

[0203] The server decrypts the received encrypted data and stores it in the database. The input data is encrypted user data, and the output data is the decrypted data stored in the database. Specifically, data decrypted using AES-256 is stored in the MySQL database.

[0204] Step 4:

[0205] The server inputs the stored data into a machine learning model (such as TensorFlow or PyTorch) and executes the analysis process. The input data is user behavior data, and the output data is information about the user's interests and preferences. Specifically, the analysis includes the movie genres that users frequently view and the keywords they search for.

[0206] Step 5:

[0207] The server generates personalized content information for each user based on the analysis results. The input data consists of analysis results regarding the user's interests and preferences, while the output data is personalized recommended content information. Specifically, this includes recommendations for new movies and movie lists of specific genres.

[0208] Step 6:

[0209] The server notifies the user of the generated recommended content information via a messaging service (Firebase Cloud Messaging). The input data is personalized recommendations, and the output data is a notification message sent to the user's device. Specifically, a list of recommended movies is displayed as a pop-up notification on the user's smartphone.

[0210] Step 7:

[0211] The user receives a notification and clicks the link to access the content distribution service. The input data is the link in the notification message, and the output data is access to a specific page on the content distribution service. Specifically, tapping the link displayed in the notification opens the details page for a new movie within the app.

[0212] Step 8:

[0213] The user views or uses selected content. The input data is access to a specific page on the content delivery service, and the output data is the actual content the user views or uses. Specifically, the user can stream a new movie they selected on the spot.

[0214] By following these steps, this system can quickly provide users with the most suitable content and increase their satisfaction.

[0215] 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.

[0216] As an embodiment of this invention, a system is described that collects and analyzes users' online behavioral data and emotional data to provide personalized information on hometown tax donations.

[0217] System Overview

[0218] This system operates by combining the user's device, a server, an emotion engine, and a messaging service. The user's device collects online behavioral and emotion data and sends it to the server. The server analyzes the received data and generates personalized information about hometown tax donations. The generated information is notified to the user via the messaging service, and the user clicks on a link in the notification to access the hometown tax donation site. Finally, the user confirms the return gift information and completes the donation by following the necessary procedures.

[0219] Collection and transmission of user data

[0220] Device: When a user browses a webpage, the device collects browser cookies. These cookies include the URL of the visited webpage, the date and time of visit, and the duration of stay. It also collects metadata for images and videos uploaded by the user to Google Photos. In addition, the device has a built-in emotion engine that analyzes and collects emotion data from the user's voice and facial expressions. The collected data is encrypted for privacy protection and transmitted to the server using secure communication methods.

[0221] Data analysis and personalization

[0222] Server: Receives user data and stores it in a database. User behavior data, photo data, and emotion data are stored. This data is input into an AI model to analyze the user's behavior patterns, interests, and emotions. For example, if a user frequently visits cooking recipe websites, takes many food-related photos, and shows positive emotions while browsing, the AI ​​model will determine that the user is interested in "cooking" or "gourmet food." The analysis results are recorded in the database as a personalized list of recommendations.

[0223] Specific example: If user B visits a travel-related website, uploads many photos of their travel destinations, and shows a cheerful expression while considering travel plans, the server will determine that user B is interested in "travel" and recommend travel-related rewards.

[0224] Generating and notifying recommendations

[0225] Server: Based on user preferences and emotions obtained through analysis, the server selects appropriate return gift information from the hometown tax donation return gift database. The selected information is then generated as a personalized notification message.

[0226] Terminal (messaging service): Sends personalized notification messages to users via LINE or other messaging services.

[0227] User actions and final donation procedures

[0228] User: Users who receive a notification can access the relevant page on the Furusato Nozei (hometown tax donation) website by clicking the link in the message.

[0229] Terminal: The user is redirected to a hometown tax donation website, where they can view details on the return gift information page. They add suitable return gifts to their cart, enter the necessary information, and complete the donation.

[0230] Specific example: When user B clicks on the link they receive in the notification, they can access a detailed page for local specialties or accommodation coupons from their travel destination and proceed with the donation process.

[0231] This system allows users to easily receive information on return gifts that match their interests and preferences, and enables local governments to efficiently acquire donations. Furthermore, by utilizing an emotion engine, more accurate personalization can be achieved based on the user's psychological state.

[0232] The following describes the processing flow.

[0233] Step 1:

[0234] Device: When a user browses a webpage, browser cookies are collected. Cookies include information such as the URL of the visited webpage and the time spent on it.

[0235] Step 2:

[0236] Device: Collects metadata from images and videos uploaded by users to Google Photos. Metadata includes tag information and location information.

[0237] Step 3:

[0238] Device: The device's built-in emotion engine analyzes the user's voice and facial expressions to collect emotion data in real time. For example, it uses facial recognition and voice analysis while the user is using their smartphone.

[0239] Step 4:

[0240] Device: Encrypts collected cookies, photo data, and sentiment data. High-security encryption algorithms such as AES (Advanced Encryption Standard) are used for encryption.

[0241] Step 5:

[0242] Terminal: Sends encrypted data to the server via a secure communication method (e.g., SSL / TLS).

[0243] Step 6:

[0244] Server: Stores received user data in the database. It associates the data with the user's ID and stores behavioral data, photo data, and sentiment data.

[0245] Step 7:

[0246] Server: Inputs stored user data into an AI model to analyze user behavior patterns, interests, and emotions. For example, if a user visits many travel websites, takes many travel-related photos, and shows positive emotions while browsing, the AI ​​will determine that the user is interested in "travel."

[0247] Step 8:

[0248] Server: Based on the analysis results, it selects appropriate return gifts from the hometown tax donation return gift database. It generates personalized return gift recommendations for each user.

[0249] Step 9:

[0250] Server: Converts the generated recommended gift information into LINE message format. Creates a notification message linked to the user's LINE ID.

[0251] Step 10:

[0252] Terminal (messaging service): Personalized hometown tax donation information is pushed to the user via LINE. The notification includes a link to the hometown tax donation website.

[0253] Step 11:

[0254] User: Receives a LINE notification and checks its contents. Clicks the link in the notification to access the Furusato Nozei (hometown tax donation) website.

[0255] Step 12:

[0256] Terminal: The clicked link redirects to the Furusato Nozei (hometown tax donation) website and displays the details page for the corresponding return gift.

[0257] Step 13:

[0258] User: Check the details on the gift information page and add it to your cart if you wish to purchase it.

[0259] Step 14:

[0260] User: Enter the required information (e.g., address, payment information) and complete the donation process.

[0261] By following these steps, users can easily find information on the most suitable return gifts based on their interests and feelings, and complete their donations. Furthermore, local governments can use this system to efficiently acquire donations and support their communities.

[0262] (Example 2)

[0263] 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".

[0264] Traditional hometown tax donation websites have a problem in that they do not adequately suggest return gifts that match the user's interests and preferences, making it time-consuming for users to find a suitable gift. Furthermore, there was no means to analyze interests and preferences using user sentiment data to achieve highly accurate personalization.

[0265] 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 collecting the user's online behavior data, means for collecting the user's emotional data, means for encrypting the collected user data and transmitting it to the server, means for analyzing the collected user data and emotional data to extract the user's interests and preferences, means for generating personalized recommendation information for each user, means for notifying the user of the generated recommendation information, means for clicking a link from the notified information to access the hometown tax donation site, and means for completing the donation based on the return gift information selected by the user. As a result, users can easily receive return gift information that matches their interests and preferences, and highly accurate personalization is achieved.

[0266] "Online behavior data" refers to data about a user's activities on the internet, including information such as the URLs of visited web pages, the date and time of visit, the duration of stay, and the links clicked.

[0267] "Emotional data" refers to data about a user's emotional state obtained by analyzing their voice and facial expressions, and includes information indicating emotional states such as joy, sadness, surprise, and anger.

[0268] "Encryption" is a technology that converts data into a format that cannot be read by third parties, and is used to protect privacy and security.

[0269] A "server" is a computer system that receives, stores, and analyzes data sent by users.

[0270] An "emotion engine" refers to an algorithm or software that analyzes a user's voice and image data to extract their emotional state.

[0271] "Personalized recommendations" refer to individual suggestions generated based on each user's unique interests and preferences.

[0272] "Notification" refers to the act of sending messages or alerts to users, primarily through email or messaging services.

[0273] A "hometown tax donation site" is an online platform for making donations to local governments and a website that provides information on various return gifts.

[0274] This invention is a system that collects and analyzes users' online behavioral data and emotional data to provide users with personalized information about hometown tax donations. This system mainly consists of the user's terminal, a server, an emotional engine, and a messaging service.

[0275] Collection and transmission of user data

[0276] First, the device collects browser cookies when the user browses a webpage. Cookies include the URL of the visited webpage, the date and time of visit, and the duration of stay. It also uses image analysis software to collect metadata of images and videos uploaded by the user. Furthermore, the device has an emotion engine built in that analyzes and collects emotion data from the user's voice and facial expressions. The collected data is encrypted to protect privacy and sent to the server using secure communication methods (e.g., SSL / TLS).

[0277] Data analysis

[0278] The server stores the received user data in a database. Suitable databases include MySQL or PostgreSQL. Next, a Python®-based AI model (e.g., TensorFlow or PyTorch) is used to analyze the user's behavior patterns, interests, and emotions. The user's interests and preferences obtained through the analysis are recorded in the database.

[0279] Generating recommendations

[0280] Based on the user's preferences and emotions obtained through analysis, the server selects appropriate gift return information from the hometown tax payment gift return database. The selected information is generated as a personalized notification message.

[0281] Notification and User Actions

[0282] The terminal (messaging service) sends the generated notification message to the user through LINE or other messaging services. After receiving the notification, the user can access the hometown tax payment site by clicking the link in the message.

[0283] Completion of the Donation Procedure

[0284] The terminal redirects the user to the hometown tax payment site, and the user checks the details on the gift return information page. The user enters the necessary information to complete the donation procedure.

[0285] Specific Example

[0286] For example, if user B visits a travel-related website, uploads many photos of the travel destination, and shows a happy expression during the travel plan, the server analyzes that user B is interested in "travel". Then, travel-related gift returns (such as hotel coupons or local specialties) are recommended.

[0287] Example of Prompt Sentence

[0288] "Based on the user's online behavior data and emotion data, please extract the hometown tax payment gift returns that the user is likely to be interested in. For example, if the user browses many travel-related sites, uploads many travel photos, and shows a happy expression during the browsing, it is content that recommends gift returns related to travel and tourism."

[0289] The flow of specific processing in Example 2 will be described using FIG. 13.

[0290] Step 1: Collecting User Data

[0291] The device collects browser cookies when the user browses web pages. These cookies include the URL of the visited web page, the date and time of visit, and the duration of the visit. It also retrieves metadata for images and videos uploaded by the user. The device's built-in emotion engine analyzes the user's voice and facial expressions to obtain emotion data. The input is the user's online behavior data and emotion data, and the output is the collected cookie information and emotion data. Specifically, if the user is browsing a cooking recipe website, the URL of the page and the duration of the visit are saved in a cookie, and the user's facial expressions and voice are captured using the camera and microphone.

[0292] Step 2: Encrypt and transmit data

[0293] The device encrypts the collected data using AES encryption and sends it to the server using a secure communication method (e.g., SSL / TLS). The input consists of collected cookies and sentiment data, and the output is encrypted data. Specifically, encryption automatically begins when the collected data reaches a certain size, and then the data is sent to the server.

[0294] Step 3: Data storage

[0295] The server decrypts the received encrypted data and stores it in a database. MySQL and PostgreSQL are suitable databases. The input is encrypted data, and the output is user behavior and sentiment data stored in the database. Specifically, the server automatically stores the received data in the database and verifies the success of the save.

[0296] Step 4: Data Analysis

[0297] The server inputs stored data into a Python-based AI model (e.g., TensorFlow or PyTorch) to analyze user behavior patterns and emotions. This extracts user interests and preferences. The input is user data stored in a database, and the output is information about user interests and preferences obtained through analysis. Specifically, the server periodically performs batch processing to input new data into the model and update the analysis results.

[0298] Step 5: Generating recommendations

[0299] The server selects appropriate return gift information from the Furusato Nozei (hometown tax donation) return gift database based on the user's interests and preferences, and generates a personalized notification message. The input is the analysis results and information from the return gift database, and the output is the personalized notification message. Specifically, the server adds a specific return gift to the recommendation list based on the analysis results of the AI ​​model, and converts that information into a message for the messaging service.

[0300] Step 6: Sending Notifications

[0301] The terminal (messaging service) sends the generated notification message to the user. Suitable messaging services include LINE and email. The input is the personalized notification message, and the output is the successful sending of the notification message. Specifically, the notification message is displayed on the user's terminal.

[0302] Step 7: User Actions

[0303] The user receives a notification and clicks the link in the message to access the Furusato Nozei (hometown tax donation) website. The input is the notification message, and the output is access to the Furusato Nozei website. Specifically, the user clicks the link for the recommended return gift, and the browser opens the corresponding page on the Furusato Nozei website.

[0304] Step 8: Completion of the donation procedure

[0305] The terminal redirects to the hometown tax payment site, where the user checks the details on the page of the return gift information, enters the necessary information, and completes the donation. The input is the return gift page selected by the user, and the output is the confirmation of the completion of the donation. As a specific operation, the user enters the necessary information in the form and clicks the donation button to complete the procedure.

[0306] (Application Example 2)

[0307] Next, Application Example 2 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart device 14 is referred to as a "terminal".

[0308] Shopping on the Internet lacks personalization that reflects the individual interests and feelings of users, and there is a problem that users may miss the products and services they really want. In addition, due to the immaturity of data collection and its utilization method for precisely analyzing users' interests and preferences, it is difficult to make optimal product recommendations. It is required to provide a method for solving these problems and providing a more satisfactory shopping experience.

[0309] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0310] In this invention, the server includes means for collecting the user's online behavior data, means for analyzing the collected user data and emotional data to extract the user's interests and preferences, means for generating personalized recommended information for each user, means for notifying the generated recommended information to the user, means for accessing the target site by clicking a link from the notified information, and means for completing the purchase procedure based on the product information selected by the user. Thereby, it becomes possible to make an optimal product recommendation based on the user's emotions and behavior data.

[0311] "User online behavior data" refers to data about various actions taken by users on the internet, and specifically includes browsing history, URLs of visited web pages, date and time of visit, duration of stay, and links clicked.

[0312] "Emotional data" refers to data that indicates the user's psychological state, and includes emotional information analyzed from facial expressions, voice, and other sources.

[0313] "Means of extracting user interests and preferences" refers to algorithms and methods that analyze collected online behavioral and emotional data to identify what users are interested in and what kinds of things they like.

[0314] "Personalized recommendations" refer to product and service suggestions optimized for each individual user, based on analyzed user interests, preferences, and emotional data.

[0315] "Means of notification" refers to means of conveying generated personalized recommendations to users, specifically including messaging services and notification systems.

[0316] "A means of accessing a target site by clicking a link" refers to a function that allows a user to select the appropriate link from the information provided and click it to be redirected to a specific website.

[0317] "Means of completing the purchase process" refers to the procedures and systems used to complete the online purchase process based on the product information selected by the user.

[0318] As an embodiment of this invention, a specific implementation method of a "personalized shopping assistant" system is shown below. This system utilizes the user's online behavior data and emotional data to provide personalized product information.

[0319] System Overview

[0320] Hardware:

[0321] Smartphone (equipped with camera and microphone)

[0322] software:

[0323] EmotionEngine (an engine for analyzing emotional data)

[0324] Messaging Service

[0325] Request library (a library for making HTTP requests)

[0326] Data collection steps

[0327] 1. The device (the user's smartphone) collects online behavior data. This data includes browsing history, URLs of visited web pages, date and time of visit, duration of stay, and links clicked.

[0328] 2. Simultaneously, the device's camera and microphone are used to collect user emotion data. EmotionEngine analyzes this data in real time, estimating the user's psychological state from their facial expressions and voice.

[0329] 3. The collected data is encrypted and transmitted to the server using secure communication methods.

[0330] Data analysis and personalization

[0331] 4. The server stores the received user data and sentiment data in a database.

[0332] 5. The server uses an AI model to analyze user behavior and emotional data to identify the user's interests and preferences. For example, if a user frequently visits recipe websites, posts many photos of food, and shows positive emotions, the AI ​​model will determine that the user is interested in cooking and gourmet food.

[0333] 6. The analysis results are generated as a personalized product list and stored in the database.

[0334] Recommended information notifications

[0335] 7. The server notifies the user of the generated personalized product information via the MessagingService.

[0336] 8. The user receives a notification and clicks the link in the message to access the relevant page on the target site (e.g., an online shopping site).

[0337] User actions and purchase procedures

[0338] 9. The device (smartphone) is redirected to the target site upon clicking the link, and the user checks the product information on the details page.

[0339] 10. The user completes the purchase process by following the specified procedure.

[0340] Specific example

[0341] User A is online shopping on their smartphone. At this time, the smartphone's camera and microphone collect the user's facial expressions and voice, and EmotionEngine analyzes their emotions. This data, along with past browsing and purchase history, is sent to the server. Based on this data, the server identifies "products that the user has recently been interested in," generates a personalized list of recommended products, and notifies User A via a messaging service.

[0342] Examples of input prompts for a generative AI model

[0343] "Generate appropriate product lists based on user sentiment and online behavior data. For example, if a user frequently visits recipe websites, posts many photos of their cooking, and displays positive emotions, recommend kitchenware and cookbooks."

[0344] In this way, it becomes possible to provide a shopping experience tailored to the individual preferences of each user.

[0345] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0346] Step 1:

[0347] The device collects online behavioral data when users shop online. This online behavioral data includes browsing history, URLs of visited web pages, visit date and time, duration of visit, and clicked links. This data is temporarily stored on the device.

[0348] Step 2:

[0349] The device's camera and microphone are used to collect the user's facial expressions and voice in real time. EmotionEngine analyzes this data to obtain the user's emotional data from their facial expressions and voice. This emotional data indicates a psychological state such as positive, negative, or neutral, and this data is also temporarily stored on the device.

[0350] Step 3:

[0351] The device encrypts the collected online behavioral data and emotional data and transmits it to the server using a secure communication method. The input data consists of online behavioral data and emotional data, and the encrypted data is output and transmitted to the server.

[0352] Step 4:

[0353] The server stores the received online behavioral and emotional data in a database. The stored data includes information about the user's behavioral history and psychological state, and this data serves as input for subsequent analysis.

[0354] Step 5:

[0355] The server uses an AI model to analyze online behavioral and emotional data to identify user interests and preferences. Specifically, the AI ​​model analyzes the data to identify websites frequently visited by the user and activities that indicate positive emotions. This analysis result then serves as input for generating personalized content.

[0356] Step 6:

[0357] The server generates personalized product recommendation lists for each user based on the analysis results. This generation process selects appropriate products from the database based on the user's interests and preferences, and compiles them into a list. This list becomes the output data.

[0358] Step 7:

[0359] The server uses MessagingService to notify the user of the generated personalized list of recommended products. Specifically, it creates a notification message and sends it to the user's smartphone. This notification is displayed as a text message with a link.

[0360] Step 8:

[0361] The user receives a notification and clicks the link in the message. This takes the user to the relevant page on the target site (e.g., an online shopping site). This link click is recorded as an interface event.

[0362] Step 9:

[0363] The device redirects the user to the target site upon clicking a link, displaying a detailed product information page. This page displays personalized products based on the user's interests.

[0364] Step 10:

[0365] The user reviews product information on the details page and completes the purchase process according to the specified procedure. The input data is information about the selected product, and the output is the verification result of the completed purchase process.

[0366] 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.

[0367] 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.

[0368] 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.

[0369] [Second Embodiment]

[0370] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0371] 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.

[0372] 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).

[0373] 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.

[0374] 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.

[0375] 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).

[0376] 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.

[0377] 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.

[0378] 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.

[0379] 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.

[0380] 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.

[0381] 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".

[0382] As an embodiment of this invention, a system is described that collects and analyzes users' online behavior data to provide personalized information on hometown tax donations.

[0383] System Overview

[0384] This system operates by combining the user's device, a server, and a messaging service. The user's device collects online behavior data and sends it to the server. The server analyzes the received data and generates personalized information about hometown tax donations. The generated information is notified to the user via the messaging service, and the user clicks on a link in the notification to access the hometown tax donation website. Finally, the user confirms the information about the return gifts, completes the necessary procedures, and finishes the donation.

[0385] Collection and transmission of user data

[0386] Device: When a user browses a webpage, the device uses browser cookies to collect data about the user's online behavior. It also collects metadata for images and videos uploaded to Google Photos. The collected data is encrypted for privacy protection. The encrypted data is transmitted to the server using secure communication methods.

[0387] Data analysis and personalization

[0388] Server: Stores received user data in a database. The stored data is input into an AI model to analyze the user's behavior patterns and interests. For example, if a user frequently visits cooking recipe websites, the AI ​​model will determine that the user is interested in "cooking" and "gourmet food." The analysis results are recorded in the database as a personalized list of recommendations.

[0389] Specific example: If user A visits a cooking-related website, the server analyzes their behavioral data and recommends local specialties or gourmet products as thank-you gifts.

[0390] Generating and notifying recommendations

[0391] Server: Based on user preferences obtained through analysis, the server selects appropriate return gift information from the hometown tax donation return gift database. The selected information is then generated as a personalized notification message.

[0392] Terminal (messaging service): Sends personalized notification messages to users via LINE or other messaging services.

[0393] User actions and final donation procedures

[0394] User: Users who receive a notification can access the relevant page on the Furusato Nozei (hometown tax donation) website by clicking the link in the message.

[0395] Terminal: The user is redirected to a hometown tax donation website, where they can view details on the return gift information page. They add suitable return gifts to their cart, enter the necessary information, and complete the donation.

[0396] Specific example: When user A clicks on the link they receive in the notification, they are directed to a detailed page about the local specialty product and guided through the process of completing the donation.

[0397] This system allows users to easily receive information about return gifts that match their interests and preferences, and also enables local governments to efficiently acquire donations.

[0398] The following describes the processing flow.

[0399] Step 1:

[0400] Device: When a user browses a webpage, browser cookies are collected. Cookies include information such as the URL of the visited webpage, the date and time of the visit, and the duration of the visit.

[0401] Step 2:

[0402] Device: Collects metadata from images and videos uploaded by users to Google Photos. Metadata includes tag information and location information.

[0403] Step 3:

[0404] Device: Encrypts collected cookies and photo data and sends them to the server using secure communication methods (e.g., SSL / TLS).

[0405] Step 4:

[0406] Server: Stores received user data in the database. The data includes the user's ID, cookie information, and photo data.

[0407] Step 5:

[0408] Server: Inputs user data stored in the database into the AI ​​model. The AI ​​model analyzes the user's online behavior patterns and extracts their interests and preferences.

[0409] Step 6:

[0410] Server: Based on the analysis results of the AI ​​model, it generates personalized recommendations for hometown tax donations. For example, for a user interested in "cooking," it selects local specialty products and gourmet items as return gifts.

[0411] Step 7:

[0412] Server: Converts personalized recommendations into LINE message format and links them to the user's LINE ID.

[0413] Step 8:

[0414] Terminal (messaging service): Personalized hometown tax donation information is pushed to the user via LINE. The notification includes a link.

[0415] Step 9:

[0416] User: Receives a LINE notification and clicks on the link to the gift information that interests them.

[0417] Step 10:

[0418] Terminal: The clicked link redirects to the Furusato Nozei (hometown tax donation) website and displays the details page for the corresponding return gift.

[0419] Step 11:

[0420] User: Check the details on the gift information page and add it to your cart if you wish to purchase it.

[0421] Step 12:

[0422] User: Enter the required information (e.g., address, payment information) and complete the donation process.

[0423] By following these steps, users can easily find information on the most suitable return gifts for them and complete their donations. Furthermore, local governments can efficiently acquire donations.

[0424] (Example 1)

[0425] 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."

[0426] Conventional hometown tax donation systems lacked the functionality to effectively analyze users' diverse interests and online behavior and provide personalized return gift information based on that analysis. As a result, users found it difficult to find return gift information that matched their interests, and local governments were unable to effectively collect donations. This invention aims to solve these problems and promote the use of hometown tax donations by providing recommended information tailored to each user.

[0427] 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.

[0428] In this invention, the server includes means for collecting user online behavior data, means for encrypting the collected user data and transmitting it to the server, means for storing the received user data in a database, means for inputting the stored user data into a model for analysis and extracting the user's interests and preferences, means for generating personalized recommendations for each user, means for notifying the user of the generated recommendations using a messaging service, means for accessing a hometown tax donation site by clicking a link in the notified information, and means for completing the donation based on the return gift information selected by the user. This makes it possible to provide return gift information based on the user's interests and preferences, and to facilitate the donation process.

[0429] "User online behavior data" refers to information about a user's actions on the internet, such as web page browsing history and metadata.

[0430] "User data encryption" is a technique that uses specific algorithms to enhance security in order to prevent collected user data from being deciphered by third parties.

[0431] A "server" is a computer system that receives, analyzes, and stores users' online behavior data in a database.

[0432] A "database" is a data storage system that organizes and stores users' online behavior data and analysis results, allowing for quick access as needed.

[0433] A "model" refers to an algorithm or machine learning framework (such as TensorFlow or PyTorch) used for data analysis, and is utilized to extract user behavior patterns and interests.

[0434] "Personalized recommendations" refer to reward information and recommendations that are identified based on each user's online behavior data and optimized to the user's interests and preferences.

[0435] A "messaging service" is a means of communication used to send personalized notification messages, and includes services like LINE and email.

[0436] A "hometown tax donation site" is a website that users access to actually make donations.

[0437] "Methods for completing a donation" refers to the process by which a user accesses a hometown tax donation website, selects a return gift, enters the necessary information, and completes the donation procedure.

[0438] This invention is a system that collects and analyzes users' online behavior data to provide personalized information about hometown tax donations. This system operates by combining the user's terminal, a server, and a messaging service.

[0439] Collection and transmission of user data

[0440] Device: When a user browses a webpage, the device uses browser cookies to collect data about the user's online behavior. It also collects metadata for images and videos uploaded by the user to Google Photos. The collected data is encrypted to protect user privacy. This encryption uses methods such as AES (Advanced Encryption Standard). The encrypted data is transmitted to the server using secure communication methods such as SSL (Secure Socket Layer) or TLS (Transport Layer Security).

[0441] Receiving and storing data

[0442] Server: The server decrypts the encrypted data received using SSL / TLS and stores it in the database. This database uses a common database management system (DBMS) such as MySQL or PostgreSQL.

[0443] Data analysis and personalization

[0444] Server: Stored data is input into AI models using machine learning frameworks such as TensorFlow and PyTorch. The AI ​​models analyze user behavior patterns and interests. For example, if a user frequently visits cooking recipe websites, the server uses the AI ​​model to determine that the user is interested in "cooking" and "gourmet food." The analysis results are recorded in the database as a personalized list of recommendations.

[0445] Specific example: If user A frequently visits cooking-related websites, the server analyzes their behavioral data and recommends local specialties and gourmet products as thank-you gifts.

[0446] Generating and notifying recommendations

[0447] Server: Based on the analysis results, the server selects appropriate return gift information from the hometown tax return gift database. The selected information is then generated as a personalized notification message for the user. Email services (e.g., SendGrid) or messaging APIs (e.g., LINE Messaging API) are used to generate the notification message.

[0448] Terminal (Messaging Service): The generated notification message is sent to the user via LINE or other messaging services. The notification message includes a link to information about the reward item.

[0449] User actions and final donation procedures

[0450] User: Users who receive a notification can access the relevant page on the Furusato Nozei (hometown tax donation) website by clicking the link in the message.

[0451] Device: When you click the link, your device will automatically redirect to the Furusato Nozei (hometown tax donation) website. There, the user can check the details of the return gifts and add their favorite gifts to their cart. They then enter the necessary information to complete the donation. This process includes payment methods such as credit card and bank transfer.

[0452] Specific example: When user A clicks on the link they receive in the notification, they are taken to a page detailing the local specialty product and guided through the process of completing the donation. This allows user A to easily make a donation.

[0453] Example of a prompt

[0454] "Cookies and personal data protection"

[0455] "Introduction of AI models based on user behavior"

[0456] "Personalized notification system for hometown tax donations"

[0457] "A combination of secure data transmission and AI analysis"

[0458] This system allows users to easily receive information about return gifts that match their interests and preferences, and also enables local governments to efficiently acquire donations.

[0459] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0460] Step 1:

[0461] User data collection

[0462] Device: When a user browses a webpage, the device uses browser cookies to collect data about the user's online behavior. Furthermore, it collects metadata for images and videos uploaded to Google Photos. This collected data includes information such as the date and location where the image was taken.

[0463] Input: User's web page browsing history, image and video metadata

[0464] Output: Collected user online behavior data

[0465] Specific operation: The web browser uses cookies to save the URL and date / time of the visited web pages on the device. The Google Photos API is used to retrieve metadata for images and videos uploaded by the user.

[0466] Step 2:

[0467] Sending user data

[0468] Terminal: Collected data is encrypted using AES (Advanced Encryption Standard). Encrypted data is sent to the server using SSL (Secure Socket Layer) or TLS (Transport Layer Security).

[0469] Input: User's online behavior data before encryption

[0470] Output: Encrypted user data

[0471] Specific operation: The terminal encrypts the data using the AES algorithm, and then securely sends the encrypted data to the server using the SSL / TLS protocol.

[0472] Step 3:

[0473] Receiving and storing data

[0474] Server: The server receives and decrypts data encrypted with SSL / TLS. The decrypted data is stored in a database. This database uses a common DBMS such as MySQL or PostgreSQL.

[0475] Input: Encrypted user data

[0476] Output: User data stored in the database

[0477] Specific operation: The server receives data using the SSL / TLS protocol and decrypts it using the AES algorithm. The decrypted data is then stored in a MySQL database.

[0478] Step 4:

[0479] Data Analysis

[0480] Server: Data stored in the database is input into AI models using machine learning frameworks such as TensorFlow and PyTorch. The server uses the AI ​​models to analyze user behavior patterns and interests. For example, if a user frequently visits cooking recipe websites, the server will determine that the user is interested in "cooking" or "gourmet food."

[0481] Input: User data stored in the database

[0482] Output: Analyzed user interests and preferences

[0483] Specific operation: The server feeds data into the AI ​​model, executes machine learning algorithms, and analyzes user behavior patterns. The analysis results are recorded in a database.

[0484] Step 5:

[0485] Generating recommendations

[0486] Server: Based on the analysis results, the server selects appropriate return gift information from the hometown tax return gift database. The selected information is then generated as a personalized notification message for the user. Email services (e.g., SendGrid) or messaging APIs (e.g., LINE Messaging API) are used to generate the notification message.

[0487] Input: Analyzed user interests and preferences, and a database of return gifts.

[0488] Output: Personalized notification message

[0489] Specific operation: Based on the analysis results, the server extracts information on reward items that match the user's interests from the database and generates a notification message. This utilizes the SendGrid and LINE API interfaces.

[0490] Step 6:

[0491] Sending notifications

[0492] Terminal (messaging service): The generated notification message is sent to the user via LINE or other messaging services. The notification message includes a link to information about the reward item.

[0493] Input: Personalized notification message

[0494] Output: Notification messages received by the user

[0495] Specific operation: A notification message generated using the messaging API is sent to the user's LINE account.

[0496] Step 7:

[0497] Receiving notifications and clicking links

[0498] User: Users who receive a notification can access the relevant page on the Furusato Nozei (hometown tax donation) website by clicking the link in the message.

[0499] Input: Link included in the notification message

[0500] Output: The relevant page on the Furusato Tax Donation website

[0501] Specific actions: The user opens a LINE message, clicks a link to launch a web browser, and accesses a hometown tax donation website.

[0502] Step 8:

[0503] Completion of donation procedure

[0504] User: Check the details of the return gifts on the hometown tax donation website and add the desired gifts to the cart. Enter the necessary information to complete the donation. This process includes payment methods such as credit card and bank transfer.

[0505] Input: Information on return gifts from the hometown tax donation website, user payment information.

[0506] Output: Donation completion confirmation message

[0507] Specific steps: The user selects an item on the reward details page and adds it to their cart. Next, they enter the required personal and payment information to complete the donation process. Upon successful completion, a confirmation message is displayed.

[0508] (Application Example 1)

[0509] 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."

[0510] Traditional content distribution services often fail to adequately provide content tailored to users' interests and preferences, leading to increased exposure to irrelevant information and decreased satisfaction. Furthermore, the effort required for users to access diverse content results in low convenience.

[0511] 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.

[0512] In this invention, the server includes means for collecting user online behavior data, means for analyzing the collected user data to extract user interests and preferences, and means for generating personalized recommendations for each user. This makes it possible to automatically provide content that is most suitable for the user's interests and preferences.

[0513] "User online behavior data" refers to information generated when users browse, search, play, etc., on the internet.

[0514] "Analysis" is the process of examining collected data in detail and extracting users' interests and preferences.

[0515] "Personalized recommendations" refer to information that is selected and presented based on the user's interests and preferences.

[0516] A "notification" is an action that presents users with recommended information.

[0517] A "content distribution service" is a service that provides users with multimedia content such as movies, dramas, and music via the internet.

[0518] "Viewing or using" refers to the act of actually playing or consuming content selected by the user.

[0519] System Configuration

[0520] This invention describes a system that collects and analyzes users' online behavior data and provides personalized content to each user. This system operates by combining the user's terminal, a server, and a messaging service.

[0521] Collection and transmission of user data

[0522] The device collects online behavior data using browser cookies and activity logs when users browse web pages or use applications. This also includes in-app search history and viewing history. For privacy reasons, the collected data is encrypted and securely transmitted to the server using HTTPS.

[0523] Data analysis

[0524] The server stores the received user data in a database and analyzes the data using machine learning models (e.g., TensorFlow or PyTorch). The analysis process extracts interests and preferences based on the user's behavior patterns. For example, if a user frequently visits movie websites, they are determined to be interested in movies.

[0525] Generating and delivering personalized content

[0526] The server generates personalized content (e.g., recommendations for new movies or movie lists of specific genres) based on the analyzed user interests. The generated recommendations are then communicated to the user via a messaging service (e.g., Firebase Cloud Messaging).

[0527] User actions and content viewing

[0528] Users receive a notification and click a link to access the content distribution service. They then watch or use the content they selected. For example, clicking the notification might take them to a details page for a new movie, from which they can watch it directly.

[0529] Hardware and software used

[0530] Hardware: Smartphone (iOS or Android)

[0531] Remote server: Cloud service (e.g., Amazon Web Services, Google Cloud Platform)

[0532] Software: Mobile applications (developed in Swift or Kotlin), backend servers (Node.js), databases (relational databases such as MySQL), messaging services (Firebase Cloud Messaging, Twilio, etc.)

[0533] Specific example

[0534] As a concrete example, consider the case of a movie-loving user searching for a new movie.

[0535] 1. The user browses a movie review website on their smartphone.

[0536] 2. A smartphone app collects that behavioral data and sends it to a server.

[0537] 3. The server analyzes the user's interests and identifies new releases and movies in genres of interest.

[0538] 4. Use Firebase Cloud Messaging to notify users with a personalized list of recommended movies.

[0539] 5. When a user clicks the notification, they are redirected to the app and can watch directly while viewing more details.

[0540] Example of a prompt

[0541] As an example of a prompt to input to a generative AI model,

[0542] The result is: "Please provide the URLs of movie review sites the user has recently visited. Also, please generate a list of new movies that the user might be interested in."

[0543] As described above, this system will allow users to quickly and accurately receive content that best suits their interests and preferences, resulting in a high level of satisfaction.

[0544] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0545] Step 1:

[0546] The device collects online behavioral data using browser cookies and activity logs when users browse, search, and play web pages. Search and viewing history within apps is also collected. Input data includes the user's browsing, search, and viewing history, while output data provides detailed information on these. Specifically, for example, the URL and viewing time when a user visits a movie review site are recorded.

[0547] Step 2:

[0548] The terminal encrypts the collected online behavioral data and securely transmits it to the server using HTTPS. The input data is the collected behavioral data, and the output data is the encrypted data. Specifically, the data is encrypted using the AES-256 encryption method and transmitted to the remote server.

[0549] Step 3:

[0550] The server decrypts the received encrypted data and stores it in the database. The input data is encrypted user data, and the output data is the decrypted data stored in the database. Specifically, data decrypted using AES-256 is stored in the MySQL database.

[0551] Step 4:

[0552] The server inputs the stored data into a machine learning model (such as TensorFlow or PyTorch) and executes the analysis process. The input data is user behavior data, and the output data is information about the user's interests and preferences. Specifically, the analysis includes the movie genres that users frequently view and the keywords they search for.

[0553] Step 5:

[0554] The server generates personalized content information for each user based on the analysis results. The input data consists of analysis results regarding the user's interests and preferences, while the output data is personalized recommended content information. Specifically, this includes recommendations for new movies and movie lists of specific genres.

[0555] Step 6:

[0556] The server notifies the user of the generated recommended content information via a messaging service (Firebase Cloud Messaging). The input data is personalized recommendations, and the output data is a notification message sent to the user's device. Specifically, a list of recommended movies is displayed as a pop-up notification on the user's smartphone.

[0557] Step 7:

[0558] The user receives a notification and clicks the link to access the content distribution service. The input data is the link in the notification message, and the output data is access to a specific page on the content distribution service. Specifically, tapping the link displayed in the notification opens the details page for a new movie within the app.

[0559] Step 8:

[0560] The user views or uses selected content. The input data is access to a specific page on the content delivery service, and the output data is the actual content the user views or uses. Specifically, the user can stream a new movie they selected on the spot.

[0561] By following these steps, this system can quickly provide users with the most suitable content and increase their satisfaction.

[0562] 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.

[0563] As an embodiment of this invention, a system is described that collects and analyzes users' online behavioral data and emotional data to provide personalized information on hometown tax donations.

[0564] System Overview

[0565] This system operates by combining the user's device, a server, an emotion engine, and a messaging service. The user's device collects online behavioral and emotion data and sends it to the server. The server analyzes the received data and generates personalized information about hometown tax donations. The generated information is notified to the user via the messaging service, and the user clicks on a link in the notification to access the hometown tax donation site. Finally, the user confirms the return gift information and completes the donation by following the necessary procedures.

[0566] Collection and transmission of user data

[0567] Device: When a user browses a webpage, the device collects browser cookies. These cookies include the URL of the visited webpage, the date and time of visit, and the duration of stay. It also collects metadata for images and videos uploaded by the user to Google Photos. In addition, the device has a built-in emotion engine that analyzes and collects emotion data from the user's voice and facial expressions. The collected data is encrypted for privacy protection and transmitted to the server using secure communication methods.

[0568] Data analysis and personalization

[0569] Server: Receives user data and stores it in a database. User behavior data, photo data, and emotion data are stored. This data is input into an AI model to analyze the user's behavior patterns, interests, and emotions. For example, if a user frequently visits cooking recipe websites, takes many food-related photos, and shows positive emotions while browsing, the AI ​​model will determine that the user is interested in "cooking" or "gourmet food." The analysis results are recorded in the database as a personalized list of recommendations.

[0570] Specific example: If user B visits a travel-related website, uploads many photos of their travel destinations, and shows a cheerful expression while considering travel plans, the server will determine that user B is interested in "travel" and recommend travel-related rewards.

[0571] Generating and notifying recommendations

[0572] Server: Based on user preferences and emotions obtained through analysis, the server selects appropriate return gift information from the hometown tax donation return gift database. The selected information is then generated as a personalized notification message.

[0573] Terminal (messaging service): Sends personalized notification messages to users via LINE or other messaging services.

[0574] User actions and final donation procedures

[0575] User: Users who receive a notification can access the relevant page on the Furusato Nozei (hometown tax donation) website by clicking the link in the message.

[0576] Terminal: The user is redirected to a hometown tax donation website, where they can view details on the return gift information page. They add suitable return gifts to their cart, enter the necessary information, and complete the donation.

[0577] Specific example: When user B clicks on the link they receive in the notification, they can access a detailed page for local specialties or accommodation coupons from their travel destination and proceed with the donation process.

[0578] This system allows users to easily receive information on return gifts that match their interests and preferences, and enables local governments to efficiently acquire donations. Furthermore, by utilizing an emotion engine, more accurate personalization can be achieved based on the user's psychological state.

[0579] The following describes the processing flow.

[0580] Step 1:

[0581] Device: When a user browses a webpage, browser cookies are collected. Cookies include information such as the URL of the visited webpage and the time spent on it.

[0582] Step 2:

[0583] Device: Collects metadata from images and videos uploaded by users to Google Photos. Metadata includes tag information and location information.

[0584] Step 3:

[0585] Device: The device's built-in emotion engine analyzes the user's voice and facial expressions to collect emotion data in real time. For example, it uses facial recognition and voice analysis while the user is using their smartphone.

[0586] Step 4:

[0587] Device: Encrypts collected cookies, photo data, and sentiment data. High-security encryption algorithms such as AES (Advanced Encryption Standard) are used for encryption.

[0588] Step 5:

[0589] Terminal: Sends encrypted data to the server via a secure communication method (e.g., SSL / TLS).

[0590] Step 6:

[0591] Server: Stores received user data in the database. It associates the data with the user's ID and stores behavioral data, photo data, and sentiment data.

[0592] Step 7:

[0593] Server: Inputs stored user data into an AI model to analyze user behavior patterns, interests, and emotions. For example, if a user visits many travel websites, takes many travel-related photos, and shows positive emotions while browsing, the AI ​​will determine that the user is interested in "travel."

[0594] Step 8:

[0595] Server: Based on the analysis results, it selects appropriate return gifts from the hometown tax donation return gift database. It generates personalized return gift recommendations for each user.

[0596] Step 9:

[0597] Server: Converts the generated recommended gift information into LINE message format. Creates a notification message linked to the user's LINE ID.

[0598] Step 10:

[0599] Terminal (messaging service): Personalized hometown tax donation information is pushed to the user via LINE. The notification includes a link to the hometown tax donation website.

[0600] Step 11:

[0601] User: Receives a LINE notification and checks its contents. Clicks the link in the notification to access the Furusato Nozei (hometown tax donation) website.

[0602] Step 12:

[0603] Terminal: The clicked link redirects to the Furusato Nozei (hometown tax donation) website and displays the details page for the corresponding return gift.

[0604] Step 13:

[0605] User: Check the details on the gift information page and add it to your cart if you wish to purchase it.

[0606] Step 14:

[0607] User: Enter the required information (e.g., address, payment information) and complete the donation process.

[0608] By following these steps, users can easily find information on the most suitable return gifts based on their interests and feelings, and complete their donations. Furthermore, local governments can use this system to efficiently acquire donations and support their communities.

[0609] (Example 2)

[0610] 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".

[0611] Traditional hometown tax donation websites have a problem in that they do not adequately suggest return gifts that match the user's interests and preferences, making it time-consuming for users to find a suitable gift. Furthermore, there was no means to analyze interests and preferences using user sentiment data to achieve highly accurate personalization.

[0612] 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 collecting the user's online behavior data, means for collecting the user's emotional data, means for encrypting the collected user data and transmitting it to the server, means for analyzing the collected user data and emotional data to extract the user's interests and preferences, means for generating personalized recommendation information for each user, means for notifying the user of the generated recommendation information, means for clicking a link from the notified information to access the hometown tax donation site, and means for completing the donation based on the return gift information selected by the user. As a result, users can easily receive return gift information that matches their interests and preferences, and highly accurate personalization is achieved.

[0613] "Online behavior data" refers to data about a user's activities on the internet, including information such as the URLs of visited web pages, the date and time of visit, the duration of stay, and the links clicked.

[0614] "Emotional data" refers to data about a user's emotional state obtained by analyzing their voice and facial expressions, and includes information indicating emotional states such as joy, sadness, surprise, and anger.

[0615] "Encryption" is a technology that converts data into a format that cannot be read by third parties, and is used to protect privacy and security.

[0616] A "server" is a computer system that receives, stores, and analyzes data sent by users.

[0617] An "emotion engine" refers to an algorithm or software that analyzes a user's voice and image data to extract their emotional state.

[0618] "Personalized recommendations" refer to individual suggestions generated based on each user's unique interests and preferences.

[0619] "Notification" refers to the act of sending messages or alerts to users, primarily through email or messaging services.

[0620] A "hometown tax donation site" is an online platform for making donations to local governments and a website that provides information on various return gifts.

[0621] This invention is a system that collects and analyzes users' online behavioral data and emotional data to provide users with personalized information about hometown tax donations. This system mainly consists of the user's terminal, a server, an emotional engine, and a messaging service.

[0622] Collection and transmission of user data

[0623] First, the device collects browser cookies when the user browses a webpage. Cookies include the URL of the visited webpage, the date and time of visit, and the duration of stay. It also uses image analysis software to collect metadata of images and videos uploaded by the user. Furthermore, the device has an emotion engine built in that analyzes and collects emotion data from the user's voice and facial expressions. The collected data is encrypted to protect privacy and sent to the server using secure communication methods (e.g., SSL / TLS).

[0624] Data analysis

[0625] The server stores the received user data in a database. Suitable databases include MySQL or PostgreSQL. Next, a Python-based AI model (e.g., TensorFlow or PyTorch) is used to analyze the user's behavior patterns, interests, and emotions. The user's interests and preferences obtained through the analysis are recorded in the database.

[0626] Generating recommendations

[0627] Based on the user's preferences and emotions obtained through analysis, the server selects appropriate return gift information from the hometown tax donation return gift database. The selected information is then generated as a personalized notification message.

[0628] Notifications and user actions

[0629] The device (messaging service) sends the generated notification message to the user via LINE or other messaging services. After receiving the notification, the user can access the hometown tax donation website by clicking the link in the message.

[0630] Completion of donation procedure

[0631] The device redirects the user to the hometown tax donation website, where the user checks the details on the page with information about the return gifts. The user then enters the necessary information and completes the donation process.

[0632] Specific example

[0633] For example, if user B visits a travel-related website, uploads many photos of their travel destinations, and shows an enthusiastic expression while planning their trip, the server will analyze that user B is interested in "travel." Then, travel-related rewards (such as accommodation coupons or local specialty products) will be recommended.

[0634] Example of a prompt

[0635] "Based on the user's online behavior and emotional data, please extract hometown tax return gifts that they are likely to be interested in. For example, if a user frequently visits travel-related websites, uploads many travel photos, and displays an enjoyable expression while browsing, then the recommendations should be for return gifts related to travel and tourism."

[0636] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0637] Step 1: Collecting User Data

[0638] The device collects browser cookies when the user browses web pages. These cookies include the URL of the visited web page, the date and time of visit, and the duration of the visit. It also retrieves metadata for images and videos uploaded by the user. The device's built-in emotion engine analyzes the user's voice and facial expressions to obtain emotion data. The input is the user's online behavior data and emotion data, and the output is the collected cookie information and emotion data. Specifically, if the user is browsing a cooking recipe website, the URL of the page and the duration of the visit are saved in a cookie, and the user's facial expressions and voice are captured using the camera and microphone.

[0639] Step 2: Encrypt and transmit data

[0640] The device encrypts the collected data using AES encryption and sends it to the server using a secure communication method (e.g., SSL / TLS). The input consists of collected cookies and sentiment data, and the output is encrypted data. Specifically, encryption automatically begins when the collected data reaches a certain size, and then the data is sent to the server.

[0641] Step 3: Data storage

[0642] The server decrypts the received encrypted data and stores it in a database. MySQL and PostgreSQL are suitable databases. The input is encrypted data, and the output is user behavior and sentiment data stored in the database. Specifically, the server automatically stores the received data in the database and verifies the success of the save.

[0643] Step 4: Data Analysis

[0644] The server inputs stored data into a Python-based AI model (e.g., TensorFlow or PyTorch) to analyze user behavior patterns and emotions. This extracts user interests and preferences. The input is user data stored in a database, and the output is information about user interests and preferences obtained through analysis. Specifically, the server periodically performs batch processing to input new data into the model and update the analysis results.

[0645] Step 5: Generating recommendations

[0646] The server selects appropriate return gift information from the Furusato Nozei (hometown tax donation) return gift database based on the user's interests and preferences, and generates a personalized notification message. The input is the analysis results and information from the return gift database, and the output is the personalized notification message. Specifically, the server adds a specific return gift to the recommendation list based on the analysis results of the AI ​​model, and converts that information into a message for the messaging service.

[0647] Step 6: Sending Notifications

[0648] The terminal (messaging service) sends the generated notification message to the user. Suitable messaging services include LINE and email. The input is the personalized notification message, and the output is the successful sending of the notification message. Specifically, the notification message is displayed on the user's terminal.

[0649] Step 7: User Actions

[0650] The user receives a notification and clicks the link in the message to access the Furusato Nozei (hometown tax donation) website. The input is the notification message, and the output is access to the Furusato Nozei website. Specifically, the user clicks the link for the recommended return gift, and the browser opens the corresponding page on the Furusato Nozei website.

[0651] Step 8: Completion of the donation process

[0652] The device redirects to a hometown tax donation website, where the user checks the details on the return gift information page, enters the necessary information, and completes the donation. The input is the return gift page selected by the user, and the output is a confirmation of the donation completion. Specifically, the user enters the required information in the form and clicks the donate button to complete the procedure.

[0653] (Application Example 2)

[0654] 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."

[0655] Online shopping suffers from a lack of personalization that reflects individual user interests and emotions, leading to users missing out on products and services they truly want. Furthermore, the insufficient methods for collecting and utilizing data to precisely analyze user interests and preferences make it difficult to recommend optimal products. There is a need to address these challenges and provide a more satisfying shopping experience.

[0656] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0657] In this invention, the server includes means for collecting user online behavior data, means for analyzing the collected user data and sentiment data to extract user interests and preferences, means for generating personalized recommendations for each user, means for notifying the user of the generated recommendations, means for accessing the target site by clicking a link from the notified information, and means for completing the purchase procedure based on the product information selected by the user. This makes it possible to provide optimal product suggestions based on the user's sentiment and behavior data.

[0658] "User online behavior data" refers to data about various actions taken by users on the internet, and specifically includes browsing history, URLs of visited web pages, date and time of visit, duration of stay, and links clicked.

[0659] "Emotional data" refers to data that indicates the user's psychological state, and includes emotional information analyzed from facial expressions, voice, and other sources.

[0660] "Means of extracting user interests and preferences" refers to algorithms and methods that analyze collected online behavioral and emotional data to identify what users are interested in and what kinds of things they like.

[0661] "Personalized recommendations" refer to product and service suggestions optimized for each individual user, based on analyzed user interests, preferences, and emotional data.

[0662] "Means of notification" refers to means of conveying generated personalized recommendations to users, specifically including messaging services and notification systems.

[0663] "A means of accessing a target site by clicking a link" refers to a function that allows a user to select the appropriate link from the information provided and click it to be redirected to a specific website.

[0664] "Means of completing the purchase process" refers to the procedures and systems used to complete the online purchase process based on the product information selected by the user.

[0665] As an embodiment of this invention, a specific implementation method of a "personalized shopping assistant" system is shown below. This system utilizes the user's online behavior data and emotional data to provide personalized product information.

[0666] System Overview

[0667] Hardware:

[0668] Smartphone (equipped with camera and microphone)

[0669] software:

[0670] EmotionEngine (an engine for analyzing emotional data)

[0671] Messaging Service

[0672] Request library (a library for making HTTP requests)

[0673] Data collection steps

[0674] 1. The device (the user's smartphone) collects online behavior data. This data includes browsing history, URLs of visited web pages, date and time of visit, duration of stay, and links clicked.

[0675] 2. Simultaneously, the device's camera and microphone are used to collect user emotion data. EmotionEngine analyzes this data in real time, estimating the user's psychological state from their facial expressions and voice.

[0676] 3. The collected data is encrypted and transmitted to the server using secure communication methods.

[0677] Data analysis and personalization

[0678] 4. The server stores the received user data and sentiment data in a database.

[0679] 5. The server uses an AI model to analyze user behavior and emotional data to identify the user's interests and preferences. For example, if a user frequently visits recipe websites, posts many photos of food, and shows positive emotions, the AI ​​model will determine that the user is interested in cooking and gourmet food.

[0680] 6. The analysis results are generated as a personalized product list and stored in the database.

[0681] Recommended information notifications

[0682] 7. The server notifies the user of the generated personalized product information via the MessagingService.

[0683] 8. The user receives a notification and clicks the link in the message to access the relevant page on the target site (e.g., an online shopping site).

[0684] User actions and purchase procedures

[0685] 9. The device (smartphone) is redirected to the target site upon clicking the link, and the user checks the product information on the details page.

[0686] 10. The user completes the purchase process by following the specified procedure.

[0687] Specific example

[0688] User A is online shopping on their smartphone. At this time, the smartphone's camera and microphone collect the user's facial expressions and voice, and EmotionEngine analyzes their emotions. This data, along with past browsing and purchase history, is sent to the server. Based on this data, the server identifies "products that the user has recently been interested in," generates a personalized list of recommended products, and notifies User A via a messaging service.

[0689] Examples of input prompts for a generative AI model

[0690] "Generate appropriate product lists based on user sentiment and online behavior data. For example, if a user frequently visits recipe websites, posts many photos of their cooking, and displays positive emotions, recommend kitchenware and cookbooks."

[0691] In this way, it becomes possible to provide a shopping experience tailored to the individual preferences of each user.

[0692] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0693] Step 1:

[0694] The device collects online behavioral data when users shop online. This online behavioral data includes browsing history, URLs of visited web pages, visit date and time, duration of visit, and clicked links. This data is temporarily stored on the device.

[0695] Step 2:

[0696] The device's camera and microphone are used to collect the user's facial expressions and voice in real time. EmotionEngine analyzes this data to obtain the user's emotional data from their facial expressions and voice. This emotional data indicates a psychological state such as positive, negative, or neutral, and this data is also temporarily stored on the device.

[0697] Step 3:

[0698] The device encrypts the collected online behavioral data and emotional data and transmits it to the server using a secure communication method. The input data consists of online behavioral data and emotional data, and the encrypted data is output and transmitted to the server.

[0699] Step 4:

[0700] The server stores the received online behavioral and emotional data in a database. The stored data includes information about the user's behavioral history and psychological state, and this data serves as input for subsequent analysis.

[0701] Step 5:

[0702] The server uses an AI model to analyze online behavioral and emotional data to identify user interests and preferences. Specifically, the AI ​​model analyzes the data to identify websites frequently visited by the user and activities that indicate positive emotions. This analysis result then serves as input for generating personalized content.

[0703] Step 6:

[0704] The server generates personalized product recommendation lists for each user based on the analysis results. This generation process selects appropriate products from the database based on the user's interests and preferences, and compiles them into a list. This list becomes the output data.

[0705] Step 7:

[0706] The server uses MessagingService to notify the user of the generated personalized list of recommended products. Specifically, it creates a notification message and sends it to the user's smartphone. This notification is displayed as a text message with a link.

[0707] Step 8:

[0708] The user receives a notification and clicks the link in the message. This takes the user to the relevant page on the target site (e.g., an online shopping site). This link click is recorded as an interface event.

[0709] Step 9:

[0710] The device redirects the user to the target site upon clicking a link, displaying a detailed product information page. This page displays personalized products based on the user's interests.

[0711] Step 10:

[0712] The user reviews product information on the details page and completes the purchase process according to the specified procedure. The input data is information about the selected product, and the output is the verification result of the completed purchase process.

[0713] 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.

[0714] 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.

[0715] 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.

[0716] [Third Embodiment]

[0717] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0718] 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.

[0719] 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).

[0720] 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.

[0721] 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.

[0722] 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).

[0723] 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.

[0724] 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.

[0725] 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.

[0726] 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.

[0727] 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.

[0728] 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".

[0729] As an embodiment of this invention, a system is described that collects and analyzes users' online behavior data to provide personalized information on hometown tax donations.

[0730] System Overview

[0731] This system operates by combining the user's device, a server, and a messaging service. The user's device collects online behavior data and sends it to the server. The server analyzes the received data and generates personalized information about hometown tax donations. The generated information is notified to the user via the messaging service, and the user clicks on a link in the notification to access the hometown tax donation website. Finally, the user confirms the information about the return gifts, completes the necessary procedures, and finishes the donation.

[0732] Collection and transmission of user data

[0733] Device: When a user browses a webpage, the device uses browser cookies to collect data about the user's online behavior. It also collects metadata for images and videos uploaded to Google Photos. The collected data is encrypted for privacy protection. The encrypted data is transmitted to the server using secure communication methods.

[0734] Data analysis and personalization

[0735] Server: Stores received user data in a database. The stored data is input into an AI model to analyze the user's behavior patterns and interests. For example, if a user frequently visits cooking recipe websites, the AI ​​model will determine that the user is interested in "cooking" and "gourmet food." The analysis results are recorded in the database as a personalized list of recommendations.

[0736] Specific example: If user A visits a cooking-related website, the server analyzes their behavioral data and recommends local specialties or gourmet products as thank-you gifts.

[0737] Generating and notifying recommendations

[0738] Server: Based on user preferences obtained through analysis, the server selects appropriate return gift information from the hometown tax donation return gift database. The selected information is then generated as a personalized notification message.

[0739] Terminal (messaging service): Sends personalized notification messages to users via LINE or other messaging services.

[0740] User actions and final donation procedures

[0741] User: Users who receive a notification can access the relevant page on the Furusato Nozei (hometown tax donation) website by clicking the link in the message.

[0742] Terminal: The user is redirected to a hometown tax donation website, where they can view details on the return gift information page. They add suitable return gifts to their cart, enter the necessary information, and complete the donation.

[0743] Specific example: When user A clicks on the link they receive in the notification, they are directed to a detailed page about the local specialty product and guided through the process of completing the donation.

[0744] This system allows users to easily receive information about return gifts that match their interests and preferences, and also enables local governments to efficiently acquire donations.

[0745] The following describes the processing flow.

[0746] Step 1:

[0747] Device: When a user browses a webpage, browser cookies are collected. Cookies include information such as the URL of the visited webpage, the date and time of the visit, and the duration of the visit.

[0748] Step 2:

[0749] Device: Collects metadata from images and videos uploaded by users to Google Photos. Metadata includes tag information and location information.

[0750] Step 3:

[0751] Device: Encrypts collected cookies and photo data and sends them to the server using secure communication methods (e.g., SSL / TLS).

[0752] Step 4:

[0753] Server: Stores received user data in the database. The data includes the user's ID, cookie information, and photo data.

[0754] Step 5:

[0755] Server: Inputs user data stored in the database into the AI ​​model. The AI ​​model analyzes the user's online behavior patterns and extracts their interests and preferences.

[0756] Step 6:

[0757] Server: Based on the analysis results of the AI ​​model, it generates personalized recommendations for hometown tax donations. For example, for a user interested in "cooking," it selects local specialty products and gourmet items as return gifts.

[0758] Step 7:

[0759] Server: Converts personalized recommendations into LINE message format and links them to the user's LINE ID.

[0760] Step 8:

[0761] Terminal (messaging service): Personalized hometown tax donation information is pushed to the user via LINE. The notification includes a link.

[0762] Step 9:

[0763] User: Receives a LINE notification and clicks on the link to the gift information that interests them.

[0764] Step 10:

[0765] Terminal: The clicked link redirects to the Furusato Nozei (hometown tax donation) website and displays the details page for the corresponding return gift.

[0766] Step 11:

[0767] User: Check the details on the gift information page and add it to your cart if you wish to purchase it.

[0768] Step 12:

[0769] User: Enter the required information (e.g., address, payment information) and complete the donation process.

[0770] By following these steps, users can easily find information on the most suitable return gifts for them and complete their donations. Furthermore, local governments can efficiently acquire donations.

[0771] (Example 1)

[0772] 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."

[0773] Conventional hometown tax donation systems lacked the functionality to effectively analyze users' diverse interests and online behavior and provide personalized return gift information based on that analysis. As a result, users found it difficult to find return gift information that matched their interests, and local governments were unable to effectively collect donations. This invention aims to solve these problems and promote the use of hometown tax donations by providing recommended information tailored to each user.

[0774] 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.

[0775] In this invention, the server includes means for collecting user online behavior data, means for encrypting the collected user data and transmitting it to the server, means for storing the received user data in a database, means for inputting the stored user data into a model for analysis and extracting the user's interests and preferences, means for generating personalized recommendations for each user, means for notifying the user of the generated recommendations using a messaging service, means for accessing a hometown tax donation site by clicking a link in the notified information, and means for completing the donation based on the return gift information selected by the user. This makes it possible to provide return gift information based on the user's interests and preferences, and to facilitate the donation process.

[0776] "User online behavior data" refers to information about a user's actions on the internet, such as web page browsing history and metadata.

[0777] "User data encryption" is a technique that uses specific algorithms to enhance security in order to prevent collected user data from being deciphered by third parties.

[0778] A "server" is a computer system that receives, analyzes, and stores users' online behavior data in a database.

[0779] A "database" is a data storage system that organizes and stores users' online behavior data and analysis results, allowing for quick access as needed.

[0780] A "model" refers to an algorithm or machine learning framework (such as TensorFlow or PyTorch) used for data analysis, and is utilized to extract user behavior patterns and interests.

[0781] "Personalized recommendations" refer to reward information and recommendations that are identified based on each user's online behavior data and optimized to the user's interests and preferences.

[0782] A "messaging service" is a means of communication used to send personalized notification messages, and includes services like LINE and email.

[0783] A "hometown tax donation site" is a website that users access to actually make donations.

[0784] "Methods for completing a donation" refers to the process by which a user accesses a hometown tax donation website, selects a return gift, enters the necessary information, and completes the donation procedure.

[0785] This invention is a system that collects and analyzes users' online behavior data to provide personalized information about hometown tax donations. This system operates by combining the user's terminal, a server, and a messaging service.

[0786] Collection and transmission of user data

[0787] Device: When a user browses a webpage, the device uses browser cookies to collect data about the user's online behavior. It also collects metadata for images and videos uploaded by the user to Google Photos. The collected data is encrypted to protect user privacy. This encryption uses methods such as AES (Advanced Encryption Standard). The encrypted data is transmitted to the server using secure communication methods such as SSL (Secure Socket Layer) or TLS (Transport Layer Security).

[0788] Receiving and storing data

[0789] Server: The server decrypts the encrypted data received using SSL / TLS and stores it in the database. This database uses a common database management system (DBMS) such as MySQL or PostgreSQL.

[0790] Data analysis and personalization

[0791] Server: Stored data is input into AI models using machine learning frameworks such as TensorFlow and PyTorch. The AI ​​models analyze user behavior patterns and interests. For example, if a user frequently visits cooking recipe websites, the server uses the AI ​​model to determine that the user is interested in "cooking" and "gourmet food." The analysis results are recorded in the database as a personalized list of recommendations.

[0792] Specific example: If user A frequently visits cooking-related websites, the server analyzes their behavioral data and recommends local specialties and gourmet products as thank-you gifts.

[0793] Generating and notifying recommendations

[0794] Server: Based on the analysis results, the server selects appropriate return gift information from the hometown tax return gift database. The selected information is then generated as a personalized notification message for the user. Email services (e.g., SendGrid) or messaging APIs (e.g., LINE Messaging API) are used to generate the notification message.

[0795] Terminal (Messaging Service): The generated notification message is sent to the user via LINE or other messaging services. The notification message includes a link to information about the reward item.

[0796] User actions and final donation procedures

[0797] User: Users who receive a notification can access the relevant page on the Furusato Nozei (hometown tax donation) website by clicking the link in the message.

[0798] Device: When you click the link, your device will automatically redirect to the Furusato Nozei (hometown tax donation) website. There, the user can check the details of the return gifts and add their favorite gifts to their cart. They then enter the necessary information to complete the donation. This process includes payment methods such as credit card and bank transfer.

[0799] Specific example: When user A clicks on the link they receive in the notification, they are taken to a page detailing the local specialty product and guided through the process of completing the donation. This allows user A to easily make a donation.

[0800] Example of a prompt

[0801] "Cookies and personal data protection"

[0802] "Introduction of AI models based on user behavior"

[0803] "Personalized notification system for hometown tax donations"

[0804] "A combination of secure data transmission and AI analysis"

[0805] This system allows users to easily receive information about return gifts that match their interests and preferences, and also enables local governments to efficiently acquire donations.

[0806] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0807] Step 1:

[0808] User data collection

[0809] Device: When a user browses a webpage, the device uses browser cookies to collect data about the user's online behavior. Furthermore, it collects metadata for images and videos uploaded to Google Photos. This collected data includes information such as the date and location where the image was taken.

[0810] Input: User's web page browsing history, image and video metadata

[0811] Output: Collected user online behavior data

[0812] Specific operation: The web browser uses cookies to save the URL and date / time of the visited web pages on the device. The Google Photos API is used to retrieve metadata for images and videos uploaded by the user.

[0813] Step 2:

[0814] Sending user data

[0815] Terminal: Collected data is encrypted using AES (Advanced Encryption Standard). Encrypted data is sent to the server using SSL (Secure Socket Layer) or TLS (Transport Layer Security).

[0816] Input: User's online behavior data before encryption

[0817] Output: Encrypted user data

[0818] Specific operation: The terminal encrypts the data using the AES algorithm, and then securely sends the encrypted data to the server using the SSL / TLS protocol.

[0819] Step 3:

[0820] Receiving and storing data

[0821] Server: The server receives and decrypts data encrypted with SSL / TLS. The decrypted data is stored in a database. This database uses a common DBMS such as MySQL or PostgreSQL.

[0822] Input: Encrypted user data

[0823] Output: User data stored in the database

[0824] Specific operation: The server receives data using the SSL / TLS protocol and decrypts it using the AES algorithm. The decrypted data is then stored in a MySQL database.

[0825] Step 4:

[0826] Data Analysis

[0827] Server: Data stored in the database is input into AI models using machine learning frameworks such as TensorFlow and PyTorch. The server uses the AI ​​models to analyze user behavior patterns and interests. For example, if a user frequently visits cooking recipe websites, the server will determine that the user is interested in "cooking" or "gourmet food."

[0828] Input: User data stored in the database

[0829] Output: Analyzed user interests and preferences

[0830] Specific operation: The server feeds data into the AI ​​model, executes machine learning algorithms, and analyzes user behavior patterns. The analysis results are recorded in a database.

[0831] Step 5:

[0832] Generating recommendations

[0833] Server: Based on the analysis results, the server selects appropriate return gift information from the hometown tax return gift database. The selected information is then generated as a personalized notification message for the user. Email services (e.g., SendGrid) or messaging APIs (e.g., LINE Messaging API) are used to generate the notification message.

[0834] Input: Analyzed user interests and preferences, and a database of return gifts.

[0835] Output: Personalized notification message

[0836] Specific operation: Based on the analysis results, the server extracts information on reward items that match the user's interests from the database and generates a notification message. This utilizes the SendGrid and LINE API interfaces.

[0837] Step 6:

[0838] Sending notifications

[0839] Terminal (messaging service): The generated notification message is sent to the user via LINE or other messaging services. The notification message includes a link to information about the reward item.

[0840] Input: Personalized notification message

[0841] Output: Notification messages received by the user

[0842] Specific operation: A notification message generated using the messaging API is sent to the user's LINE account.

[0843] Step 7:

[0844] Receiving notifications and clicking links

[0845] User: Users who receive a notification can access the relevant page on the Furusato Nozei (hometown tax donation) website by clicking the link in the message.

[0846] Input: Link included in the notification message

[0847] Output: The relevant page on the Furusato Tax Donation website

[0848] Specific actions: The user opens a LINE message, clicks a link to launch a web browser, and accesses a hometown tax donation website.

[0849] Step 8:

[0850] Completion of donation procedure

[0851] User: Check the details of the return gifts on the hometown tax donation website and add the desired gifts to the cart. Enter the necessary information to complete the donation. This process includes payment methods such as credit card and bank transfer.

[0852] Input: Information on return gifts from the hometown tax donation website, user payment information.

[0853] Output: Donation completion confirmation message

[0854] Specific steps: The user selects an item on the reward details page and adds it to their cart. Next, they enter the required personal and payment information to complete the donation process. Upon successful completion, a confirmation message is displayed.

[0855] (Application Example 1)

[0856] 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."

[0857] Traditional content distribution services often fail to adequately provide content tailored to users' interests and preferences, leading to increased exposure to irrelevant information and decreased satisfaction. Furthermore, the effort required for users to access diverse content results in low convenience.

[0858] 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.

[0859] In this invention, the server includes means for collecting user online behavior data, means for analyzing the collected user data to extract user interests and preferences, and means for generating personalized recommendations for each user. This makes it possible to automatically provide content that is most suitable for the user's interests and preferences.

[0860] "User online behavior data" refers to information generated when users browse, search, play, etc., on the internet.

[0861] "Analysis" is the process of examining collected data in detail and extracting users' interests and preferences.

[0862] "Personalized recommendations" refer to information that is selected and presented based on the user's interests and preferences.

[0863] A "notification" is an action that presents users with recommended information.

[0864] A "content distribution service" is a service that provides users with multimedia content such as movies, dramas, and music via the internet.

[0865] "Viewing or using" refers to the act of actually playing or consuming content selected by the user.

[0866] System Configuration

[0867] This invention describes a system that collects and analyzes users' online behavior data and provides personalized content to each user. This system operates by combining the user's terminal, a server, and a messaging service.

[0868] Collection and transmission of user data

[0869] The device collects online behavior data using browser cookies and activity logs when users browse web pages or use applications. This also includes in-app search history and viewing history. For privacy reasons, the collected data is encrypted and securely transmitted to the server using HTTPS.

[0870] Data analysis

[0871] The server stores the received user data in a database and analyzes the data using machine learning models (e.g., TensorFlow or PyTorch). The analysis process extracts interests and preferences based on the user's behavior patterns. For example, if a user frequently visits movie websites, they are determined to be interested in movies.

[0872] Generating and delivering personalized content

[0873] The server generates personalized content (e.g., recommendations for new movies or movie lists of specific genres) based on the analyzed user interests. The generated recommendations are then communicated to the user via a messaging service (e.g., Firebase Cloud Messaging).

[0874] User actions and content viewing

[0875] Users receive a notification and click a link to access the content distribution service. They then watch or use the content they selected. For example, clicking the notification might take them to a details page for a new movie, from which they can watch it directly.

[0876] Hardware and software used

[0877] Hardware: Smartphone (iOS or Android)

[0878] Remote server: Cloud service (e.g., Amazon Web Services, Google Cloud Platform)

[0879] Software: Mobile applications (developed in Swift or Kotlin), backend servers (Node.js), databases (relational databases such as MySQL), messaging services (Firebase Cloud Messaging, Twilio, etc.)

[0880] Specific example

[0881] As a concrete example, consider the case of a movie-loving user searching for a new movie.

[0882] 1. The user browses a movie review website on their smartphone.

[0883] 2. A smartphone app collects that behavioral data and sends it to a server.

[0884] 3. The server analyzes the user's interests and identifies new releases and movies in genres of interest.

[0885] 4. Use Firebase Cloud Messaging to notify users with a personalized list of recommended movies.

[0886] 5. When a user clicks the notification, they are redirected to the app and can watch directly while viewing more details.

[0887] Example of a prompt

[0888] As an example of a prompt to input to a generative AI model,

[0889] The result is: "Please provide the URLs of movie review sites the user has recently visited. Also, please generate a list of new movies that the user might be interested in."

[0890] As described above, this system will allow users to quickly and accurately receive content that best suits their interests and preferences, resulting in a high level of satisfaction.

[0891] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0892] Step 1:

[0893] The device collects online behavioral data using browser cookies and activity logs when users browse, search, and play web pages. Search and viewing history within apps is also collected. Input data includes the user's browsing, search, and viewing history, while output data provides detailed information on these. Specifically, for example, the URL and viewing time when a user visits a movie review site are recorded.

[0894] Step 2:

[0895] The terminal encrypts the collected online behavioral data and securely transmits it to the server using HTTPS. The input data is the collected behavioral data, and the output data is the encrypted data. Specifically, the data is encrypted using the AES-256 encryption method and transmitted to the remote server.

[0896] Step 3:

[0897] The server decrypts the received encrypted data and stores it in the database. The input data is encrypted user data, and the output data is the decrypted data stored in the database. Specifically, data decrypted using AES-256 is stored in the MySQL database.

[0898] Step 4:

[0899] The server inputs the stored data into a machine learning model (such as TensorFlow or PyTorch) and executes the analysis process. The input data is user behavior data, and the output data is information about the user's interests and preferences. Specifically, the analysis includes the movie genres that users frequently view and the keywords they search for.

[0900] Step 5:

[0901] The server generates personalized content information for each user based on the analysis results. The input data consists of analysis results regarding the user's interests and preferences, while the output data is personalized recommended content information. Specifically, this includes recommendations for new movies and movie lists of specific genres.

[0902] Step 6:

[0903] The server notifies the user of the generated recommended content information via a messaging service (Firebase Cloud Messaging). The input data is personalized recommendations, and the output data is a notification message sent to the user's device. Specifically, a list of recommended movies is displayed as a pop-up notification on the user's smartphone.

[0904] Step 7:

[0905] The user receives a notification and clicks the link to access the content distribution service. The input data is the link in the notification message, and the output data is access to a specific page on the content distribution service. Specifically, tapping the link displayed in the notification opens the details page for a new movie within the app.

[0906] Step 8:

[0907] The user views or uses selected content. The input data is access to a specific page on the content delivery service, and the output data is the actual content the user views or uses. Specifically, the user can stream a new movie they selected on the spot.

[0908] By following these steps, this system can quickly provide users with the most suitable content and increase their satisfaction.

[0909] 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.

[0910] As an embodiment of this invention, a system is described that collects and analyzes users' online behavioral data and emotional data to provide personalized information on hometown tax donations.

[0911] System Overview

[0912] This system operates by combining the user's device, a server, an emotion engine, and a messaging service. The user's device collects online behavioral and emotion data and sends it to the server. The server analyzes the received data and generates personalized information about hometown tax donations. The generated information is notified to the user via the messaging service, and the user clicks on a link in the notification to access the hometown tax donation site. Finally, the user confirms the return gift information and completes the donation by following the necessary procedures.

[0913] Collection and transmission of user data

[0914] Device: When a user browses a webpage, the device collects browser cookies. These cookies include the URL of the visited webpage, the date and time of visit, and the duration of stay. It also collects metadata for images and videos uploaded by the user to Google Photos. In addition, the device has a built-in emotion engine that analyzes and collects emotion data from the user's voice and facial expressions. The collected data is encrypted for privacy protection and transmitted to the server using secure communication methods.

[0915] Data analysis and personalization

[0916] Server: Receives user data and stores it in a database. User behavior data, photo data, and emotion data are stored. This data is input into an AI model to analyze the user's behavior patterns, interests, and emotions. For example, if a user frequently visits cooking recipe websites, takes many food-related photos, and shows positive emotions while browsing, the AI ​​model will determine that the user is interested in "cooking" or "gourmet food." The analysis results are recorded in the database as a personalized list of recommendations.

[0917] Specific example: If user B visits a travel-related website, uploads many photos of their travel destinations, and shows a cheerful expression while considering travel plans, the server will determine that user B is interested in "travel" and recommend travel-related rewards.

[0918] Generating and notifying recommendations

[0919] Server: Based on user preferences and emotions obtained through analysis, the server selects appropriate return gift information from the hometown tax donation return gift database. The selected information is then generated as a personalized notification message.

[0920] Terminal (messaging service): Sends personalized notification messages to users via LINE or other messaging services.

[0921] User actions and final donation procedures

[0922] User: Users who receive a notification can access the relevant page on the Furusato Nozei (hometown tax donation) website by clicking the link in the message.

[0923] Terminal: The user is redirected to a hometown tax donation website, where they can view details on the return gift information page. They add suitable return gifts to their cart, enter the necessary information, and complete the donation.

[0924] Specific example: When user B clicks on the link they receive in the notification, they can access a detailed page for local specialties or accommodation coupons from their travel destination and proceed with the donation process.

[0925] This system allows users to easily receive information on return gifts that match their interests and preferences, and enables local governments to efficiently acquire donations. Furthermore, by utilizing an emotion engine, more accurate personalization can be achieved based on the user's psychological state.

[0926] The following describes the processing flow.

[0927] Step 1:

[0928] Device: When a user browses a webpage, browser cookies are collected. Cookies include information such as the URL of the visited webpage and the time spent on it.

[0929] Step 2:

[0930] Device: Collects metadata from images and videos uploaded by users to Google Photos. Metadata includes tag information and location information.

[0931] Step 3:

[0932] Device: The device's built-in emotion engine analyzes the user's voice and facial expressions to collect emotion data in real time. For example, it uses facial recognition and voice analysis while the user is using their smartphone.

[0933] Step 4:

[0934] Device: Encrypts collected cookies, photo data, and sentiment data. High-security encryption algorithms such as AES (Advanced Encryption Standard) are used for encryption.

[0935] Step 5:

[0936] Terminal: Sends encrypted data to the server via a secure communication method (e.g., SSL / TLS).

[0937] Step 6:

[0938] Server: Stores received user data in the database. It associates the data with the user's ID and stores behavioral data, photo data, and sentiment data.

[0939] Step 7:

[0940] Server: Inputs stored user data into an AI model to analyze user behavior patterns, interests, and emotions. For example, if a user visits many travel websites, takes many travel-related photos, and shows positive emotions while browsing, the AI ​​will determine that the user is interested in "travel."

[0941] Step 8:

[0942] Server: Based on the analysis results, it selects appropriate return gifts from the hometown tax donation return gift database. It generates personalized return gift recommendations for each user.

[0943] Step 9:

[0944] Server: Converts the generated recommended gift information into LINE message format. Creates a notification message linked to the user's LINE ID.

[0945] Step 10:

[0946] Terminal (messaging service): Personalized hometown tax donation information is pushed to the user via LINE. The notification includes a link to the hometown tax donation website.

[0947] Step 11:

[0948] User: Receives a LINE notification and checks its contents. Clicks the link in the notification to access the Furusato Nozei (hometown tax donation) website.

[0949] Step 12:

[0950] Terminal: The clicked link redirects to the Furusato Nozei (hometown tax donation) website and displays the details page for the corresponding return gift.

[0951] Step 13:

[0952] User: Check the details on the gift information page and add it to your cart if you wish to purchase it.

[0953] Step 14:

[0954] User: Enter the required information (e.g., address, payment information) and complete the donation process.

[0955] By following these steps, users can easily find information on the most suitable return gifts based on their interests and feelings, and complete their donations. Furthermore, local governments can use this system to efficiently acquire donations and support their communities.

[0956] (Example 2)

[0957] 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."

[0958] Traditional hometown tax donation websites have a problem in that they do not adequately suggest return gifts that match the user's interests and preferences, making it time-consuming for users to find a suitable gift. Furthermore, there was no means to analyze interests and preferences using user sentiment data to achieve highly accurate personalization.

[0959] 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 collecting the user's online behavior data, means for collecting the user's emotional data, means for encrypting the collected user data and transmitting it to the server, means for analyzing the collected user data and emotional data to extract the user's interests and preferences, means for generating personalized recommendation information for each user, means for notifying the user of the generated recommendation information, means for clicking a link from the notified information to access the hometown tax donation site, and means for completing the donation based on the return gift information selected by the user. As a result, users can easily receive return gift information that matches their interests and preferences, and highly accurate personalization is achieved.

[0960] "Online behavior data" refers to data about a user's activities on the internet, including information such as the URLs of visited web pages, the date and time of visit, the duration of stay, and the links clicked.

[0961] "Emotional data" refers to data about a user's emotional state obtained by analyzing their voice and facial expressions, and includes information indicating emotional states such as joy, sadness, surprise, and anger.

[0962] "Encryption" is a technology that converts data into a format that cannot be read by third parties, and is used to protect privacy and security.

[0963] A "server" is a computer system that receives, stores, and analyzes data sent by users.

[0964] An "emotion engine" refers to an algorithm or software that analyzes a user's voice and image data to extract their emotional state.

[0965] "Personalized recommendations" refer to individual suggestions generated based on each user's unique interests and preferences.

[0966] "Notification" refers to the act of sending messages or alerts to users, primarily through email or messaging services.

[0967] A "hometown tax donation site" is an online platform for making donations to local governments and a website that provides information on various return gifts.

[0968] This invention is a system that collects and analyzes users' online behavioral data and emotional data to provide users with personalized information about hometown tax donations. This system mainly consists of the user's terminal, a server, an emotional engine, and a messaging service.

[0969] Collection and transmission of user data

[0970] First, the device collects browser cookies when the user browses a webpage. Cookies include the URL of the visited webpage, the date and time of visit, and the duration of stay. It also uses image analysis software to collect metadata of images and videos uploaded by the user. Furthermore, the device has an emotion engine built in that analyzes and collects emotion data from the user's voice and facial expressions. The collected data is encrypted to protect privacy and sent to the server using secure communication methods (e.g., SSL / TLS).

[0971] Data analysis

[0972] The server stores the received user data in a database. Suitable databases include MySQL or PostgreSQL. Next, a Python-based AI model (e.g., TensorFlow or PyTorch) is used to analyze the user's behavior patterns, interests, and emotions. The user's interests and preferences obtained through the analysis are recorded in the database.

[0973] Generating recommendations

[0974] Based on the user's preferences and emotions obtained through analysis, the server selects appropriate return gift information from the hometown tax donation return gift database. The selected information is then generated as a personalized notification message.

[0975] Notifications and user actions

[0976] The device (messaging service) sends the generated notification message to the user via LINE or other messaging services. After receiving the notification, the user can access the hometown tax donation website by clicking the link in the message.

[0977] Completion of donation procedure

[0978] The device redirects the user to the hometown tax donation website, where the user checks the details on the page with information about the return gifts. The user then enters the necessary information and completes the donation process.

[0979] Specific example

[0980] For example, if user B visits a travel-related website, uploads many photos of their travel destinations, and shows an enthusiastic expression while planning their trip, the server will analyze that user B is interested in "travel." Then, travel-related rewards (such as accommodation coupons or local specialty products) will be recommended.

[0981] Example of a prompt

[0982] "Based on the user's online behavior and emotional data, please extract hometown tax return gifts that they are likely to be interested in. For example, if a user frequently visits travel-related websites, uploads many travel photos, and displays an enjoyable expression while browsing, then the recommendations should be for return gifts related to travel and tourism."

[0983] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0984] Step 1: Collecting User Data

[0985] The device collects browser cookies when the user browses web pages. These cookies include the URL of the visited web page, the date and time of visit, and the duration of the visit. It also retrieves metadata for images and videos uploaded by the user. The device's built-in emotion engine analyzes the user's voice and facial expressions to obtain emotion data. The input is the user's online behavior data and emotion data, and the output is the collected cookie information and emotion data. Specifically, if the user is browsing a cooking recipe website, the URL of the page and the duration of the visit are saved in a cookie, and the user's facial expressions and voice are captured using the camera and microphone.

[0986] Step 2: Encrypt and transmit data

[0987] The device encrypts the collected data using AES encryption and sends it to the server using a secure communication method (e.g., SSL / TLS). The input consists of collected cookies and sentiment data, and the output is encrypted data. Specifically, encryption automatically begins when the collected data reaches a certain size, and then the data is sent to the server.

[0988] Step 3: Data storage

[0989] The server decrypts the received encrypted data and stores it in a database. MySQL and PostgreSQL are suitable databases. The input is encrypted data, and the output is user behavior and sentiment data stored in the database. Specifically, the server automatically stores the received data in the database and verifies the success of the save.

[0990] Step 4: Data Analysis

[0991] The server inputs stored data into a Python-based AI model (e.g., TensorFlow or PyTorch) to analyze user behavior patterns and emotions. This extracts user interests and preferences. The input is user data stored in a database, and the output is information about user interests and preferences obtained through analysis. Specifically, the server periodically performs batch processing to input new data into the model and update the analysis results.

[0992] Step 5: Generating recommendations

[0993] The server selects appropriate return gift information from the Furusato Nozei (hometown tax donation) return gift database based on the user's interests and preferences, and generates a personalized notification message. The input is the analysis results and information from the return gift database, and the output is the personalized notification message. Specifically, the server adds a specific return gift to the recommendation list based on the analysis results of the AI ​​model, and converts that information into a message for the messaging service.

[0994] Step 6: Sending Notifications

[0995] The terminal (messaging service) sends the generated notification message to the user. Suitable messaging services include LINE and email. The input is the personalized notification message, and the output is the successful sending of the notification message. Specifically, the notification message is displayed on the user's terminal.

[0996] Step 7: User Actions

[0997] The user receives a notification and clicks the link in the message to access the Furusato Nozei (hometown tax donation) website. The input is the notification message, and the output is access to the Furusato Nozei website. Specifically, the user clicks the link for the recommended return gift, and the browser opens the corresponding page on the Furusato Nozei website.

[0998] Step 8: Completion of the donation process

[0999] The device redirects to a hometown tax donation website, where the user checks the details on the return gift information page, enters the necessary information, and completes the donation. The input is the return gift page selected by the user, and the output is a confirmation of the donation completion. Specifically, the user enters the required information in the form and clicks the donate button to complete the procedure.

[1000] (Application Example 2)

[1001] 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."

[1002] Online shopping suffers from a lack of personalization that reflects individual user interests and emotions, leading to users missing out on products and services they truly want. Furthermore, the insufficient methods for collecting and utilizing data to precisely analyze user interests and preferences make it difficult to recommend optimal products. There is a need to address these challenges and provide a more satisfying shopping experience.

[1003] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1004] In this invention, the server includes means for collecting user online behavior data, means for analyzing the collected user data and sentiment data to extract user interests and preferences, means for generating personalized recommendations for each user, means for notifying the user of the generated recommendations, means for accessing the target site by clicking a link from the notified information, and means for completing the purchase procedure based on the product information selected by the user. This makes it possible to provide optimal product suggestions based on the user's sentiment and behavior data.

[1005] "User online behavior data" refers to data about various actions taken by users on the internet, and specifically includes browsing history, URLs of visited web pages, date and time of visit, duration of stay, and links clicked.

[1006] "Emotional data" refers to data that indicates the user's psychological state, and includes emotional information analyzed from facial expressions, voice, and other sources.

[1007] "Means of extracting user interests and preferences" refers to algorithms and methods that analyze collected online behavioral and emotional data to identify what users are interested in and what kinds of things they like.

[1008] "Personalized recommendations" refer to product and service suggestions optimized for each individual user, based on analyzed user interests, preferences, and emotional data.

[1009] "Means of notification" refers to means of conveying generated personalized recommendations to users, specifically including messaging services and notification systems.

[1010] "A means of accessing a target site by clicking a link" refers to a function that allows a user to select the appropriate link from the information provided and click it to be redirected to a specific website.

[1011] "Means of completing the purchase process" refers to the procedures and systems used to complete the online purchase process based on the product information selected by the user.

[1012] As an embodiment of this invention, a specific implementation method of a "personalized shopping assistant" system is shown below. This system utilizes the user's online behavior data and emotional data to provide personalized product information.

[1013] System Overview

[1014] Hardware:

[1015] Smartphone (equipped with camera and microphone)

[1016] software:

[1017] EmotionEngine (an engine for analyzing emotional data)

[1018] Messaging Service

[1019] Request library (a library for making HTTP requests)

[1020] Data collection steps

[1021] 1. The device (the user's smartphone) collects online behavior data. This data includes browsing history, URLs of visited web pages, date and time of visit, duration of stay, and links clicked.

[1022] 2. Simultaneously, the device's camera and microphone are used to collect user emotion data. EmotionEngine analyzes this data in real time, estimating the user's psychological state from their facial expressions and voice.

[1023] 3. The collected data is encrypted and transmitted to the server using secure communication methods.

[1024] Data analysis and personalization

[1025] 4. The server stores the received user data and sentiment data in a database.

[1026] 5. The server uses an AI model to analyze user behavior and emotional data to identify the user's interests and preferences. For example, if a user frequently visits recipe websites, posts many photos of food, and shows positive emotions, the AI ​​model will determine that the user is interested in cooking and gourmet food.

[1027] 6. The analysis results are generated as a personalized product list and stored in the database.

[1028] Recommended information notifications

[1029] 7. The server notifies the user of the generated personalized product information via the MessagingService.

[1030] 8. The user receives a notification and clicks the link in the message to access the relevant page on the target site (e.g., an online shopping site).

[1031] User actions and purchase procedures

[1032] 9. The device (smartphone) is redirected to the target site upon clicking the link, and the user checks the product information on the details page.

[1033] 10. The user completes the purchase process by following the specified procedure.

[1034] Specific example

[1035] User A is online shopping on their smartphone. At this time, the smartphone's camera and microphone collect the user's facial expressions and voice, and EmotionEngine analyzes their emotions. This data, along with past browsing and purchase history, is sent to the server. Based on this data, the server identifies "products that the user has recently been interested in," generates a personalized list of recommended products, and notifies User A via a messaging service.

[1036] Examples of input prompts for a generative AI model

[1037] "Generate appropriate product lists based on user sentiment and online behavior data. For example, if a user frequently visits recipe websites, posts many photos of their cooking, and displays positive emotions, recommend kitchenware and cookbooks."

[1038] In this way, it becomes possible to provide a shopping experience tailored to the individual preferences of each user.

[1039] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1040] Step 1:

[1041] The device collects online behavioral data when users shop online. This online behavioral data includes browsing history, URLs of visited web pages, visit date and time, duration of visit, and clicked links. This data is temporarily stored on the device.

[1042] Step 2:

[1043] The device's camera and microphone are used to collect the user's facial expressions and voice in real time. EmotionEngine analyzes this data to obtain the user's emotional data from their facial expressions and voice. This emotional data indicates a psychological state such as positive, negative, or neutral, and this data is also temporarily stored on the device.

[1044] Step 3:

[1045] The device encrypts the collected online behavioral data and emotional data and transmits it to the server using a secure communication method. The input data consists of online behavioral data and emotional data, and the encrypted data is output and transmitted to the server.

[1046] Step 4:

[1047] The server stores the received online behavioral and emotional data in a database. The stored data includes information about the user's behavioral history and psychological state, and this data serves as input for subsequent analysis.

[1048] Step 5:

[1049] The server uses an AI model to analyze online behavioral and emotional data to identify user interests and preferences. Specifically, the AI ​​model analyzes the data to identify websites frequently visited by the user and activities that indicate positive emotions. This analysis result then serves as input for generating personalized content.

[1050] Step 6:

[1051] The server generates personalized product recommendation lists for each user based on the analysis results. This generation process selects appropriate products from the database based on the user's interests and preferences, and compiles them into a list. This list becomes the output data.

[1052] Step 7:

[1053] The server uses MessagingService to notify the user of the generated personalized list of recommended products. Specifically, it creates a notification message and sends it to the user's smartphone. This notification is displayed as a text message with a link.

[1054] Step 8:

[1055] The user receives a notification and clicks the link in the message. This takes the user to the relevant page on the target site (e.g., an online shopping site). This link click is recorded as an interface event.

[1056] Step 9:

[1057] The device redirects the user to the target site upon clicking a link, displaying a detailed product information page. This page displays personalized products based on the user's interests.

[1058] Step 10:

[1059] The user reviews product information on the details page and completes the purchase process according to the specified procedure. The input data is information about the selected product, and the output is the verification result of the completed purchase process.

[1060] 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.

[1061] 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.

[1062] 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.

[1063] [Fourth Embodiment]

[1064] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1065] 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.

[1066] 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).

[1067] 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.

[1068] 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.

[1069] 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).

[1070] 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.

[1071] 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.

[1072] 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.

[1073] 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.

[1074] 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.

[1075] 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.

[1076] 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".

[1077] As an embodiment of this invention, a system is described that collects and analyzes users' online behavior data to provide personalized information on hometown tax donations.

[1078] System Overview

[1079] This system operates by combining the user's device, a server, and a messaging service. The user's device collects online behavior data and sends it to the server. The server analyzes the received data and generates personalized information about hometown tax donations. The generated information is notified to the user via the messaging service, and the user clicks on a link in the notification to access the hometown tax donation website. Finally, the user confirms the information about the return gifts, completes the necessary procedures, and finishes the donation.

[1080] Collection and transmission of user data

[1081] Device: When a user browses a webpage, the device uses browser cookies to collect data about the user's online behavior. It also collects metadata for images and videos uploaded to Google Photos. The collected data is encrypted for privacy protection. The encrypted data is transmitted to the server using secure communication methods.

[1082] Data analysis and personalization

[1083] Server: Stores received user data in a database. The stored data is input into an AI model to analyze the user's behavior patterns and interests. For example, if a user frequently visits cooking recipe websites, the AI ​​model will determine that the user is interested in "cooking" and "gourmet food." The analysis results are recorded in the database as a personalized list of recommendations.

[1084] Specific example: If user A visits a cooking-related website, the server analyzes their behavioral data and recommends local specialties or gourmet products as thank-you gifts.

[1085] Generating and notifying recommendations

[1086] Server: Based on user preferences obtained through analysis, the server selects appropriate return gift information from the hometown tax donation return gift database. The selected information is then generated as a personalized notification message.

[1087] Terminal (messaging service): Sends personalized notification messages to users via LINE or other messaging services.

[1088] User actions and final donation procedures

[1089] User: Users who receive a notification can access the relevant page on the Furusato Nozei (hometown tax donation) website by clicking the link in the message.

[1090] Terminal: The user is redirected to a hometown tax donation website, where they can view details on the return gift information page. They add suitable return gifts to their cart, enter the necessary information, and complete the donation.

[1091] Specific example: When user A clicks on the link they receive in the notification, they are directed to a detailed page about the local specialty product and guided through the process of completing the donation.

[1092] This system allows users to easily receive information about return gifts that match their interests and preferences, and also enables local governments to efficiently acquire donations.

[1093] The following describes the processing flow.

[1094] Step 1:

[1095] Device: When a user browses a webpage, browser cookies are collected. Cookies include information such as the URL of the visited webpage, the date and time of the visit, and the duration of the visit.

[1096] Step 2:

[1097] Device: Collects metadata from images and videos uploaded by users to Google Photos. Metadata includes tag information and location information.

[1098] Step 3:

[1099] Device: Encrypts collected cookies and photo data and sends them to the server using secure communication methods (e.g., SSL / TLS).

[1100] Step 4:

[1101] Server: Stores received user data in the database. The data includes the user's ID, cookie information, and photo data.

[1102] Step 5:

[1103] Server: Inputs user data stored in the database into the AI ​​model. The AI ​​model analyzes the user's online behavior patterns and extracts their interests and preferences.

[1104] Step 6:

[1105] Server: Based on the analysis results of the AI ​​model, it generates personalized recommendations for hometown tax donations. For example, for a user interested in "cooking," it selects local specialty products and gourmet items as return gifts.

[1106] Step 7:

[1107] Server: Converts personalized recommendations into LINE message format and links them to the user's LINE ID.

[1108] Step 8:

[1109] Terminal (messaging service): Personalized hometown tax donation information is pushed to the user via LINE. The notification includes a link.

[1110] Step 9:

[1111] User: Receives a LINE notification and clicks on the link to the gift information that interests them.

[1112] Step 10:

[1113] Terminal: The clicked link redirects to the Furusato Nozei (hometown tax donation) website and displays the details page for the corresponding return gift.

[1114] Step 11:

[1115] User: Check the details on the gift information page and add it to your cart if you wish to purchase it.

[1116] Step 12:

[1117] User: Enter the required information (e.g., address, payment information) and complete the donation process.

[1118] By following these steps, users can easily find information on the most suitable return gifts for them and complete their donations. Furthermore, local governments can efficiently acquire donations.

[1119] (Example 1)

[1120] 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".

[1121] Conventional hometown tax donation systems lacked the functionality to effectively analyze users' diverse interests and online behavior and provide personalized return gift information based on that analysis. As a result, users found it difficult to find return gift information that matched their interests, and local governments were unable to effectively collect donations. This invention aims to solve these problems and promote the use of hometown tax donations by providing recommended information tailored to each user.

[1122] 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.

[1123] In this invention, the server includes means for collecting user online behavior data, means for encrypting the collected user data and transmitting it to the server, means for storing the received user data in a database, means for inputting the stored user data into a model for analysis and extracting the user's interests and preferences, means for generating personalized recommendations for each user, means for notifying the user of the generated recommendations using a messaging service, means for accessing a hometown tax donation site by clicking a link in the notified information, and means for completing the donation based on the return gift information selected by the user. This makes it possible to provide return gift information based on the user's interests and preferences, and to facilitate the donation process.

[1124] "User online behavior data" refers to information about a user's actions on the internet, such as web page browsing history and metadata.

[1125] "User data encryption" is a technique that uses specific algorithms to enhance security in order to prevent collected user data from being deciphered by third parties.

[1126] A "server" is a computer system that receives, analyzes, and stores users' online behavior data in a database.

[1127] A "database" is a data storage system that organizes and stores users' online behavior data and analysis results, allowing for quick access as needed.

[1128] A "model" refers to an algorithm or machine learning framework (such as TensorFlow or PyTorch) used for data analysis, and is utilized to extract user behavior patterns and interests.

[1129] "Personalized recommendations" refer to reward information and recommendations that are identified based on each user's online behavior data and optimized to the user's interests and preferences.

[1130] A "messaging service" is a means of communication used to send personalized notification messages, and includes services like LINE and email.

[1131] A "hometown tax donation site" is a website that users access to actually make donations.

[1132] "Methods for completing a donation" refers to the process by which a user accesses a hometown tax donation website, selects a return gift, enters the necessary information, and completes the donation procedure.

[1133] This invention is a system that collects and analyzes users' online behavior data to provide personalized information about hometown tax donations. This system operates by combining the user's terminal, a server, and a messaging service.

[1134] Collection and transmission of user data

[1135] Device: When a user browses a webpage, the device uses browser cookies to collect data about the user's online behavior. It also collects metadata for images and videos uploaded by the user to Google Photos. The collected data is encrypted to protect user privacy. This encryption uses methods such as AES (Advanced Encryption Standard). The encrypted data is transmitted to the server using secure communication methods such as SSL (Secure Socket Layer) or TLS (Transport Layer Security).

[1136] Receiving and storing data

[1137] Server: The server decrypts the encrypted data received using SSL / TLS and stores it in the database. This database uses a common database management system (DBMS) such as MySQL or PostgreSQL.

[1138] Data analysis and personalization

[1139] Server: Stored data is input into AI models using machine learning frameworks such as TensorFlow and PyTorch. The AI ​​models analyze user behavior patterns and interests. For example, if a user frequently visits cooking recipe websites, the server uses the AI ​​model to determine that the user is interested in "cooking" and "gourmet food." The analysis results are recorded in the database as a personalized list of recommendations.

[1140] Specific example: If user A frequently visits cooking-related websites, the server analyzes their behavioral data and recommends local specialties and gourmet products as thank-you gifts.

[1141] Generating and notifying recommendations

[1142] Server: Based on the analysis results, the server selects appropriate return gift information from the hometown tax return gift database. The selected information is then generated as a personalized notification message for the user. Email services (e.g., SendGrid) or messaging APIs (e.g., LINE Messaging API) are used to generate the notification message.

[1143] Terminal (Messaging Service): The generated notification message is sent to the user via LINE or other messaging services. The notification message includes a link to information about the reward item.

[1144] User actions and final donation procedures

[1145] User: Users who receive a notification can access the relevant page on the Furusato Nozei (hometown tax donation) website by clicking the link in the message.

[1146] Device: When you click the link, your device will automatically redirect to the Furusato Nozei (hometown tax donation) website. There, the user can check the details of the return gifts and add their favorite gifts to their cart. They then enter the necessary information to complete the donation. This process includes payment methods such as credit card and bank transfer.

[1147] Specific example: When user A clicks on the link they receive in the notification, they are taken to a page detailing the local specialty product and guided through the process of completing the donation. This allows user A to easily make a donation.

[1148] Example of a prompt

[1149] "Cookies and personal data protection"

[1150] "Introduction of AI models based on user behavior"

[1151] "Personalized notification system for hometown tax donations"

[1152] "A combination of secure data transmission and AI analysis"

[1153] This system allows users to easily receive information about return gifts that match their interests and preferences, and also enables local governments to efficiently acquire donations.

[1154] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1155] Step 1:

[1156] User data collection

[1157] Device: When a user browses a webpage, the device uses browser cookies to collect data about the user's online behavior. Furthermore, it collects metadata for images and videos uploaded to Google Photos. This collected data includes information such as the date and location where the image was taken.

[1158] Input: User's web page browsing history, image and video metadata

[1159] Output: Collected user online behavior data

[1160] Specific operation: The web browser uses cookies to save the URL and date / time of the visited web pages on the device. The Google Photos API is used to retrieve metadata for images and videos uploaded by the user.

[1161] Step 2:

[1162] Sending user data

[1163] Terminal: Collected data is encrypted using AES (Advanced Encryption Standard). Encrypted data is sent to the server using SSL (Secure Socket Layer) or TLS (Transport Layer Security).

[1164] Input: User's online behavior data before encryption

[1165] Output: Encrypted user data

[1166] Specific operation: The terminal encrypts the data using the AES algorithm, and then securely sends the encrypted data to the server using the SSL / TLS protocol.

[1167] Step 3:

[1168] Receiving and storing data

[1169] Server: The server receives and decrypts data encrypted with SSL / TLS. The decrypted data is stored in a database. This database uses a common DBMS such as MySQL or PostgreSQL.

[1170] Input: Encrypted user data

[1171] Output: User data stored in the database

[1172] Specific operation: The server receives data using the SSL / TLS protocol and decrypts it using the AES algorithm. The decrypted data is then stored in a MySQL database.

[1173] Step 4:

[1174] Data Analysis

[1175] Server: Data stored in the database is input into AI models using machine learning frameworks such as TensorFlow and PyTorch. The server uses the AI ​​models to analyze user behavior patterns and interests. For example, if a user frequently visits cooking recipe websites, the server will determine that the user is interested in "cooking" or "gourmet food."

[1176] Input: User data stored in the database

[1177] Output: Analyzed user interests and preferences

[1178] Specific operation: The server feeds data into the AI ​​model, executes machine learning algorithms, and analyzes user behavior patterns. The analysis results are recorded in a database.

[1179] Step 5:

[1180] Generating recommendations

[1181] Server: Based on the analysis results, the server selects appropriate return gift information from the hometown tax return gift database. The selected information is then generated as a personalized notification message for the user. Email services (e.g., SendGrid) or messaging APIs (e.g., LINE Messaging API) are used to generate the notification message.

[1182] Input: Analyzed user interests and preferences, and a database of return gifts.

[1183] Output: Personalized notification message

[1184] Specific operation: Based on the analysis results, the server extracts information on reward items that match the user's interests from the database and generates a notification message. This utilizes the SendGrid and LINE API interfaces.

[1185] Step 6:

[1186] Sending notifications

[1187] Terminal (messaging service): The generated notification message is sent to the user via LINE or other messaging services. The notification message includes a link to information about the reward item.

[1188] Input: Personalized notification message

[1189] Output: Notification messages received by the user

[1190] Specific operation: A notification message generated using the messaging API is sent to the user's LINE account.

[1191] Step 7:

[1192] Receiving notifications and clicking links

[1193] User: Users who receive a notification can access the relevant page on the Furusato Nozei (hometown tax donation) website by clicking the link in the message.

[1194] Input: Link included in the notification message

[1195] Output: The relevant page on the Furusato Tax Donation website

[1196] Specific actions: The user opens a LINE message, clicks a link to launch a web browser, and accesses a hometown tax donation website.

[1197] Step 8:

[1198] Completion of donation procedure

[1199] User: Check the details of the return gifts on the hometown tax donation website and add the desired gifts to the cart. Enter the necessary information to complete the donation. This process includes payment methods such as credit card and bank transfer.

[1200] Input: Information on return gifts from the hometown tax donation website, user payment information.

[1201] Output: Donation completion confirmation message

[1202] Specific steps: The user selects an item on the reward details page and adds it to their cart. Next, they enter the required personal and payment information to complete the donation process. Upon successful completion, a confirmation message is displayed.

[1203] (Application Example 1)

[1204] 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".

[1205] Traditional content distribution services often fail to adequately provide content tailored to users' interests and preferences, leading to increased exposure to irrelevant information and decreased satisfaction. Furthermore, the effort required for users to access diverse content results in low convenience.

[1206] 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.

[1207] In this invention, the server includes means for collecting user online behavior data, means for analyzing the collected user data to extract user interests and preferences, and means for generating personalized recommendations for each user. This makes it possible to automatically provide content that is most suitable for the user's interests and preferences.

[1208] "User online behavior data" refers to information generated when users browse, search, play, etc., on the internet.

[1209] "Analysis" is the process of examining collected data in detail and extracting users' interests and preferences.

[1210] "Personalized recommendations" refer to information that is selected and presented based on the user's interests and preferences.

[1211] A "notification" is an action that presents users with recommended information.

[1212] A "content distribution service" is a service that provides users with multimedia content such as movies, dramas, and music via the internet.

[1213] "Viewing or using" refers to the act of actually playing or consuming content selected by the user.

[1214] System Configuration

[1215] This invention describes a system that collects and analyzes users' online behavior data and provides personalized content to each user. This system operates by combining the user's terminal, a server, and a messaging service.

[1216] Collection and transmission of user data

[1217] The device collects online behavior data using browser cookies and activity logs when users browse web pages or use applications. This also includes in-app search history and viewing history. For privacy reasons, the collected data is encrypted and securely transmitted to the server using HTTPS.

[1218] Data analysis

[1219] The server stores the received user data in a database and analyzes the data using machine learning models (e.g., TensorFlow or PyTorch). The analysis process extracts interests and preferences based on the user's behavior patterns. For example, if a user frequently visits movie websites, they are determined to be interested in movies.

[1220] Generating and delivering personalized content

[1221] The server generates personalized content (e.g., recommendations for new movies or movie lists of specific genres) based on the analyzed user interests. The generated recommendations are then communicated to the user via a messaging service (e.g., Firebase Cloud Messaging).

[1222] User actions and content viewing

[1223] Users receive a notification and click a link to access the content distribution service. They then watch or use the content they selected. For example, clicking the notification might take them to a details page for a new movie, from which they can watch it directly.

[1224] Hardware and software used

[1225] Hardware: Smartphone (iOS or Android)

[1226] Remote server: Cloud service (e.g., Amazon Web Services, Google Cloud Platform)

[1227] Software: Mobile applications (developed in Swift or Kotlin), backend servers (Node.js), databases (relational databases such as MySQL), messaging services (Firebase Cloud Messaging, Twilio, etc.)

[1228] Specific example

[1229] As a concrete example, consider the case of a movie-loving user searching for a new movie.

[1230] 1. The user browses a movie review website on their smartphone.

[1231] 2. A smartphone app collects that behavioral data and sends it to a server.

[1232] 3. The server analyzes the user's interests and identifies new releases and movies in genres of interest.

[1233] 4. Use Firebase Cloud Messaging to notify users with a personalized list of recommended movies.

[1234] 5. When a user clicks the notification, they are redirected to the app and can watch directly while viewing more details.

[1235] Example of a prompt

[1236] As an example of a prompt to input to a generative AI model,

[1237] The result is: "Please provide the URLs of movie review sites the user has recently visited. Also, please generate a list of new movies that the user might be interested in."

[1238] As described above, this system will allow users to quickly and accurately receive content that best suits their interests and preferences, resulting in a high level of satisfaction.

[1239] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1240] Step 1:

[1241] The device collects online behavioral data using browser cookies and activity logs when users browse, search, and play web pages. Search and viewing history within apps is also collected. Input data includes the user's browsing, search, and viewing history, while output data provides detailed information on these. Specifically, for example, the URL and viewing time when a user visits a movie review site are recorded.

[1242] Step 2:

[1243] The terminal encrypts the collected online behavioral data and securely transmits it to the server using HTTPS. The input data is the collected behavioral data, and the output data is the encrypted data. Specifically, the data is encrypted using the AES-256 encryption method and transmitted to the remote server.

[1244] Step 3:

[1245] The server decrypts the received encrypted data and stores it in the database. The input data is encrypted user data, and the output data is the decrypted data stored in the database. Specifically, data decrypted using AES-256 is stored in the MySQL database.

[1246] Step 4:

[1247] The server inputs the stored data into a machine learning model (such as TensorFlow or PyTorch) and executes the analysis process. The input data is user behavior data, and the output data is information about the user's interests and preferences. Specifically, the analysis includes the movie genres that users frequently view and the keywords they search for.

[1248] Step 5:

[1249] The server generates personalized content information for each user based on the analysis results. The input data consists of analysis results regarding the user's interests and preferences, while the output data is personalized recommended content information. Specifically, this includes recommendations for new movies and movie lists of specific genres.

[1250] Step 6:

[1251] The server notifies the user of the generated recommended content information via a messaging service (Firebase Cloud Messaging). The input data is personalized recommendations, and the output data is a notification message sent to the user's device. Specifically, a list of recommended movies is displayed as a pop-up notification on the user's smartphone.

[1252] Step 7:

[1253] The user receives a notification and clicks the link to access the content distribution service. The input data is the link in the notification message, and the output data is access to a specific page on the content distribution service. Specifically, tapping the link displayed in the notification opens the details page for a new movie within the app.

[1254] Step 8:

[1255] The user views or uses selected content. The input data is access to a specific page on the content delivery service, and the output data is the actual content the user views or uses. Specifically, the user can stream a new movie they selected on the spot.

[1256] By following these steps, this system can quickly provide users with the most suitable content and increase their satisfaction.

[1257] 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.

[1258] As an embodiment of this invention, a system is described that collects and analyzes users' online behavioral data and emotional data to provide personalized information on hometown tax donations.

[1259] System Overview

[1260] This system operates by combining the user's device, a server, an emotion engine, and a messaging service. The user's device collects online behavioral and emotion data and sends it to the server. The server analyzes the received data and generates personalized information about hometown tax donations. The generated information is notified to the user via the messaging service, and the user clicks on a link in the notification to access the hometown tax donation site. Finally, the user confirms the return gift information and completes the donation by following the necessary procedures.

[1261] Collection and transmission of user data

[1262] Device: When a user browses a webpage, the device collects browser cookies. These cookies include the URL of the visited webpage, the date and time of visit, and the duration of stay. It also collects metadata for images and videos uploaded by the user to Google Photos. In addition, the device has a built-in emotion engine that analyzes and collects emotion data from the user's voice and facial expressions. The collected data is encrypted for privacy protection and transmitted to the server using secure communication methods.

[1263] Data analysis and personalization

[1264] Server: Receives user data and stores it in a database. User behavior data, photo data, and emotion data are stored. This data is input into an AI model to analyze the user's behavior patterns, interests, and emotions. For example, if a user frequently visits cooking recipe websites, takes many food-related photos, and shows positive emotions while browsing, the AI ​​model will determine that the user is interested in "cooking" or "gourmet food." The analysis results are recorded in the database as a personalized list of recommendations.

[1265] Specific example: If user B visits a travel-related website, uploads many photos of their travel destinations, and shows a cheerful expression while considering travel plans, the server will determine that user B is interested in "travel" and recommend travel-related rewards.

[1266] Generating and notifying recommendations

[1267] Server: Based on user preferences and emotions obtained through analysis, the server selects appropriate return gift information from the hometown tax donation return gift database. The selected information is then generated as a personalized notification message.

[1268] Terminal (messaging service): Sends personalized notification messages to users via LINE or other messaging services.

[1269] User actions and final donation procedures

[1270] User: Users who receive a notification can access the relevant page on the Furusato Nozei (hometown tax donation) website by clicking the link in the message.

[1271] Terminal: The user is redirected to a hometown tax donation website, where they can view details on the return gift information page. They add suitable return gifts to their cart, enter the necessary information, and complete the donation.

[1272] Specific example: When user B clicks on the link they receive in the notification, they can access a detailed page for local specialties or accommodation coupons from their travel destination and proceed with the donation process.

[1273] This system allows users to easily receive information on return gifts that match their interests and preferences, and enables local governments to efficiently acquire donations. Furthermore, by utilizing an emotion engine, more accurate personalization can be achieved based on the user's psychological state.

[1274] The following describes the processing flow.

[1275] Step 1:

[1276] Device: When a user browses a webpage, browser cookies are collected. Cookies include information such as the URL of the visited webpage and the time spent on it.

[1277] Step 2:

[1278] Device: Collects metadata from images and videos uploaded by users to Google Photos. Metadata includes tag information and location information.

[1279] Step 3:

[1280] Device: The device's built-in emotion engine analyzes the user's voice and facial expressions to collect emotion data in real time. For example, it uses facial recognition and voice analysis while the user is using their smartphone.

[1281] Step 4:

[1282] Device: Encrypts collected cookies, photo data, and sentiment data. High-security encryption algorithms such as AES (Advanced Encryption Standard) are used for encryption.

[1283] Step 5:

[1284] Terminal: Sends encrypted data to the server via a secure communication method (e.g., SSL / TLS).

[1285] Step 6:

[1286] Server: Stores received user data in the database. It associates the data with the user's ID and stores behavioral data, photo data, and sentiment data.

[1287] Step 7:

[1288] Server: Inputs stored user data into an AI model to analyze user behavior patterns, interests, and emotions. For example, if a user visits many travel websites, takes many travel-related photos, and shows positive emotions while browsing, the AI ​​will determine that the user is interested in "travel."

[1289] Step 8:

[1290] Server: Based on the analysis results, it selects appropriate return gifts from the hometown tax donation return gift database. It generates personalized return gift recommendations for each user.

[1291] Step 9:

[1292] Server: Converts the generated recommended gift information into LINE message format. Creates a notification message linked to the user's LINE ID.

[1293] Step 10:

[1294] Terminal (messaging service): Personalized hometown tax donation information is pushed to the user via LINE. The notification includes a link to the hometown tax donation website.

[1295] Step 11:

[1296] User: Receives a LINE notification and checks its contents. Clicks the link in the notification to access the Furusato Nozei (hometown tax donation) website.

[1297] Step 12:

[1298] Terminal: The clicked link redirects to the Furusato Nozei (hometown tax donation) website and displays the details page for the corresponding return gift.

[1299] Step 13:

[1300] User: Check the details on the gift information page and add it to your cart if you wish to purchase it.

[1301] Step 14:

[1302] User: Enter the required information (e.g., address, payment information) and complete the donation process.

[1303] By following these steps, users can easily find information on the most suitable return gifts based on their interests and feelings, and complete their donations. Furthermore, local governments can use this system to efficiently acquire donations and support their communities.

[1304] (Example 2)

[1305] 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".

[1306] Traditional hometown tax donation websites have a problem in that they do not adequately suggest return gifts that match the user's interests and preferences, making it time-consuming for users to find a suitable gift. Furthermore, there was no means to analyze interests and preferences using user sentiment data to achieve highly accurate personalization.

[1307] 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 collecting the user's online behavior data, means for collecting the user's emotional data, means for encrypting the collected user data and transmitting it to the server, means for analyzing the collected user data and emotional data to extract the user's interests and preferences, means for generating personalized recommendation information for each user, means for notifying the user of the generated recommendation information, means for clicking a link from the notified information to access the hometown tax donation site, and means for completing the donation based on the return gift information selected by the user. As a result, users can easily receive return gift information that matches their interests and preferences, and highly accurate personalization is achieved.

[1308] "Online behavior data" refers to data about a user's activities on the internet, including information such as the URLs of visited web pages, the date and time of visit, the duration of stay, and the links clicked.

[1309] "Emotional data" refers to data about a user's emotional state obtained by analyzing their voice and facial expressions, and includes information indicating emotional states such as joy, sadness, surprise, and anger.

[1310] "Encryption" is a technology that converts data into a format that cannot be read by third parties, and is used to protect privacy and security.

[1311] A "server" is a computer system that receives, stores, and analyzes data sent by users.

[1312] An "emotion engine" refers to an algorithm or software that analyzes a user's voice and image data to extract their emotional state.

[1313] "Personalized recommendations" refer to individual suggestions generated based on each user's unique interests and preferences.

[1314] "Notification" refers to the act of sending messages or alerts to users, primarily through email or messaging services.

[1315] A "hometown tax donation site" is an online platform for making donations to local governments and a website that provides information on various return gifts.

[1316] This invention is a system that collects and analyzes users' online behavioral data and emotional data to provide users with personalized information about hometown tax donations. This system mainly consists of the user's terminal, a server, an emotional engine, and a messaging service.

[1317] Collection and transmission of user data

[1318] First, the device collects browser cookies when the user browses a webpage. Cookies include the URL of the visited webpage, the date and time of visit, and the duration of stay. It also uses image analysis software to collect metadata of images and videos uploaded by the user. Furthermore, the device has an emotion engine built in that analyzes and collects emotion data from the user's voice and facial expressions. The collected data is encrypted to protect privacy and sent to the server using secure communication methods (e.g., SSL / TLS).

[1319] Data analysis

[1320] The server stores the received user data in a database. Suitable databases include MySQL or PostgreSQL. Next, a Python-based AI model (e.g., TensorFlow or PyTorch) is used to analyze the user's behavior patterns, interests, and emotions. The user's interests and preferences obtained through the analysis are recorded in the database.

[1321] Generating recommendations

[1322] Based on the user's preferences and emotions obtained through analysis, the server selects appropriate return gift information from the hometown tax donation return gift database. The selected information is then generated as a personalized notification message.

[1323] Notifications and user actions

[1324] The device (messaging service) sends the generated notification message to the user via LINE or other messaging services. After receiving the notification, the user can access the hometown tax donation website by clicking the link in the message.

[1325] Completion of donation procedure

[1326] The device redirects the user to the hometown tax donation website, where the user checks the details on the page with information about the return gifts. The user then enters the necessary information and completes the donation process.

[1327] Specific example

[1328] For example, if user B visits a travel-related website, uploads many photos of their travel destinations, and shows an enthusiastic expression while planning their trip, the server will analyze that user B is interested in "travel." Then, travel-related rewards (such as accommodation coupons or local specialty products) will be recommended.

[1329] Example of a prompt

[1330] "Based on the user's online behavior and emotional data, please extract hometown tax return gifts that they are likely to be interested in. For example, if a user frequently visits travel-related websites, uploads many travel photos, and displays an enjoyable expression while browsing, then the recommendations should be for return gifts related to travel and tourism."

[1331] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1332] Step 1: Collecting User Data

[1333] The device collects browser cookies when the user browses web pages. These cookies include the URL of the visited web page, the date and time of visit, and the duration of the visit. It also retrieves metadata for images and videos uploaded by the user. The device's built-in emotion engine analyzes the user's voice and facial expressions to obtain emotion data. The input is the user's online behavior data and emotion data, and the output is the collected cookie information and emotion data. Specifically, if the user is browsing a cooking recipe website, the URL of the page and the duration of the visit are saved in a cookie, and the user's facial expressions and voice are captured using the camera and microphone.

[1334] Step 2: Encrypt and transmit data

[1335] The device encrypts the collected data using AES encryption and sends it to the server using a secure communication method (e.g., SSL / TLS). The input consists of collected cookies and sentiment data, and the output is encrypted data. Specifically, encryption automatically begins when the collected data reaches a certain size, and then the data is sent to the server.

[1336] Step 3: Data storage

[1337] The server decrypts the received encrypted data and stores it in a database. MySQL and PostgreSQL are suitable databases. The input is encrypted data, and the output is user behavior and sentiment data stored in the database. Specifically, the server automatically stores the received data in the database and verifies the success of the save.

[1338] Step 4: Data Analysis

[1339] The server inputs stored data into a Python-based AI model (e.g., TensorFlow or PyTorch) to analyze user behavior patterns and emotions. This extracts user interests and preferences. The input is user data stored in a database, and the output is information about user interests and preferences obtained through analysis. Specifically, the server periodically performs batch processing to input new data into the model and update the analysis results.

[1340] Step 5: Generating recommendations

[1341] The server selects appropriate return gift information from the Furusato Nozei (hometown tax donation) return gift database based on the user's interests and preferences, and generates a personalized notification message. The input is the analysis results and information from the return gift database, and the output is the personalized notification message. Specifically, the server adds a specific return gift to the recommendation list based on the analysis results of the AI ​​model, and converts that information into a message for the messaging service.

[1342] Step 6: Sending Notifications

[1343] The terminal (messaging service) sends the generated notification message to the user. Suitable messaging services include LINE and email. The input is the personalized notification message, and the output is the successful sending of the notification message. Specifically, the notification message is displayed on the user's terminal.

[1344] Step 7: User Actions

[1345] The user receives a notification and clicks the link in the message to access the Furusato Nozei (hometown tax donation) website. The input is the notification message, and the output is access to the Furusato Nozei website. Specifically, the user clicks the link for the recommended return gift, and the browser opens the corresponding page on the Furusato Nozei website.

[1346] Step 8: Completion of the donation process

[1347] The device redirects to a hometown tax donation website, where the user checks the details on the return gift information page, enters the necessary information, and completes the donation. The input is the return gift page selected by the user, and the output is a confirmation of the donation completion. Specifically, the user enters the required information in the form and clicks the donate button to complete the procedure.

[1348] (Application Example 2)

[1349] 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".

[1350] Online shopping suffers from a lack of personalization that reflects individual user interests and emotions, leading to users missing out on products and services they truly want. Furthermore, the insufficient methods for collecting and utilizing data to precisely analyze user interests and preferences make it difficult to recommend optimal products. There is a need to address these challenges and provide a more satisfying shopping experience.

[1351] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1352] In this invention, the server includes means for collecting user online behavior data, means for analyzing the collected user data and sentiment data to extract user interests and preferences, means for generating personalized recommendations for each user, means for notifying the user of the generated recommendations, means for accessing the target site by clicking a link from the notified information, and means for completing the purchase procedure based on the product information selected by the user. This makes it possible to provide optimal product suggestions based on the user's sentiment and behavior data.

[1353] "User online behavior data" refers to data about various actions taken by users on the internet, and specifically includes browsing history, URLs of visited web pages, date and time of visit, duration of stay, and links clicked.

[1354] "Emotional data" refers to data that indicates the user's psychological state, and includes emotional information analyzed from facial expressions, voice, and other sources.

[1355] "Means of extracting user interests and preferences" refers to algorithms and methods that analyze collected online behavioral and emotional data to identify what users are interested in and what kinds of things they like.

[1356] "Personalized recommendations" refer to product and service suggestions optimized for each individual user, based on analyzed user interests, preferences, and emotional data.

[1357] "Means of notification" refers to means of conveying generated personalized recommendations to users, specifically including messaging services and notification systems.

[1358] "A means of accessing a target site by clicking a link" refers to a function that allows a user to select the appropriate link from the information provided and click it to be redirected to a specific website.

[1359] "Means of completing the purchase process" refers to the procedures and systems used to complete the online purchase process based on the product information selected by the user.

[1360] As an embodiment of this invention, a specific implementation method of a "personalized shopping assistant" system is shown below. This system utilizes the user's online behavior data and emotional data to provide personalized product information.

[1361] System Overview

[1362] Hardware:

[1363] Smartphone (equipped with camera and microphone)

[1364] software:

[1365] EmotionEngine (an engine for analyzing emotional data)

[1366] Messaging Service

[1367] Request library (a library for making HTTP requests)

[1368] Data collection steps

[1369] 1. The device (the user's smartphone) collects online behavior data. This data includes browsing history, URLs of visited web pages, date and time of visit, duration of stay, and links clicked.

[1370] 2. Simultaneously, the device's camera and microphone are used to collect user emotion data. EmotionEngine analyzes this data in real time, estimating the user's psychological state from their facial expressions and voice.

[1371] 3. The collected data is encrypted and transmitted to the server using secure communication methods.

[1372] Data analysis and personalization

[1373] 4. The server stores the received user data and sentiment data in a database.

[1374] 5. The server uses an AI model to analyze user behavior and emotional data to identify the user's interests and preferences. For example, if a user frequently visits recipe websites, posts many photos of food, and shows positive emotions, the AI ​​model will determine that the user is interested in cooking and gourmet food.

[1375] 6. The analysis results are generated as a personalized product list and stored in the database.

[1376] Recommended information notifications

[1377] 7. The server notifies the user of the generated personalized product information via the MessagingService.

[1378] 8. The user receives a notification and clicks the link in the message to access the relevant page on the target site (e.g., an online shopping site).

[1379] User actions and purchase procedures

[1380] 9. The device (smartphone) is redirected to the target site upon clicking the link, and the user checks the product information on the details page.

[1381] 10. The user completes the purchase process by following the specified procedure.

[1382] Specific example

[1383] User A is online shopping on their smartphone. At this time, the smartphone's camera and microphone collect the user's facial expressions and voice, and EmotionEngine analyzes their emotions. This data, along with past browsing and purchase history, is sent to the server. Based on this data, the server identifies "products that the user has recently been interested in," generates a personalized list of recommended products, and notifies User A via a messaging service.

[1384] Examples of input prompts for a generative AI model

[1385] "Generate appropriate product lists based on user sentiment and online behavior data. For example, if a user frequently visits recipe websites, posts many photos of their cooking, and displays positive emotions, recommend kitchenware and cookbooks."

[1386] In this way, it becomes possible to provide a shopping experience tailored to the individual preferences of each user.

[1387] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1388] Step 1:

[1389] The device collects online behavioral data when users shop online. This online behavioral data includes browsing history, URLs of visited web pages, visit date and time, duration of visit, and clicked links. This data is temporarily stored on the device.

[1390] Step 2:

[1391] The device's camera and microphone are used to collect the user's facial expressions and voice in real time. EmotionEngine analyzes this data to obtain the user's emotional data from their facial expressions and voice. This emotional data indicates a psychological state such as positive, negative, or neutral, and this data is also temporarily stored on the device.

[1392] Step 3:

[1393] The device encrypts the collected online behavioral data and emotional data and transmits it to the server using a secure communication method. The input data consists of online behavioral data and emotional data, and the encrypted data is output and transmitted to the server.

[1394] Step 4:

[1395] The server stores the received online behavioral and emotional data in a database. The stored data includes information about the user's behavioral history and psychological state, and this data serves as input for subsequent analysis.

[1396] Step 5:

[1397] The server uses an AI model to analyze online behavioral and emotional data to identify user interests and preferences. Specifically, the AI ​​model analyzes the data to identify websites frequently visited by the user and activities that indicate positive emotions. This analysis result then serves as input for generating personalized content.

[1398] Step 6:

[1399] The server generates personalized product recommendation lists for each user based on the analysis results. This generation process selects appropriate products from the database based on the user's interests and preferences, and compiles them into a list. This list becomes the output data.

[1400] Step 7:

[1401] The server uses MessagingService to notify the user of the generated personalized list of recommended products. Specifically, it creates a notification message and sends it to the user's smartphone. This notification is displayed as a text message with a link.

[1402] Step 8:

[1403] The user receives a notification and clicks the link in the message. This takes the user to the relevant page on the target site (e.g., an online shopping site). This link click is recorded as an interface event.

[1404] Step 9:

[1405] The device redirects the user to the target site upon clicking a link, displaying a detailed product information page. This page displays personalized products based on the user's interests.

[1406] Step 10:

[1407] The user reviews product information on the details page and completes the purchase process according to the specified procedure. The input data is information about the selected product, and the output is the verification result of the completed purchase process.

[1408] 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.

[1409] 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.

[1410] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1411] 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.

[1412] 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.

[1413] 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.

[1414] 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.

[1415] 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.

[1416] 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."

[1417] 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.

[1418] 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.

[1419] 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.

[1420] 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.

[1421] 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.

[1422] 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.

[1423] 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.

[1424] 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.

[1425] 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.

[1426] 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.

[1427] 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.

[1428] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[1429] The following is further disclosed regarding the embodiments described above.

[1430] (Claim 1)

[1431] Means for collecting user online behavior data,

[1432] A means of analyzing collected user data to extract user interests and preferences,

[1433] A means of generating personalized recommendations for each user,

[1434] A means of notifying users of the generated recommendations,

[1435] The means of accessing the hometown tax donation site by clicking a link from the information provided,

[1436] A method for completing a donation based on the return gift information selected by the user,

[1437] A system that includes this.

[1438] (Claim 2)

[1439] The system according to claim 1, characterized in that it includes means for collecting user behavior data for advertising and marketing purposes.

[1440] (Claim 3)

[1441] The system according to claim 1, characterized in that it includes means for encrypting the collected user data and transmitting it to a server.

[1442] (Claim 4)

[1443] The system according to claim 1, characterized by using artificial intelligence to analyze the user's interests and preferences.

[1444] (Claim 5)

[1445] The system according to claim 1, characterized in that it includes means for notifying the generated recommendation information through a messaging service.

[1446] "Example 1"

[1447] (Claim 1)

[1448] Means for collecting user online behavior data,

[1449] A means of encrypting the collected user data and sending it to the server,

[1450] A means of storing received user data in a database,

[1451] A method for inputting stored user data into a model for analysis and extracting user interests and preferences,

[1452] A means of generating personalized recommendations for each user,

[1453] A means of notifying users of generated recommendation information through a messaging service,

[1454] The means of accessing the hometown tax donation site by clicking on the link in the notified information,

[1455] A method for completing a donation based on the return gift information selected by the user,

[1456] A system that includes this.

[1457] (Claim 2)

[1458] The system according to claim 1, characterized in that it includes means for collecting user behavior data for advertising and marketing purposes.

[1459] (Claim 3)

[1460] The system according to claim 1, characterized in that it includes means for using a messaging service when sending a notification message.

[1461] "Application Example 1"

[1462] (Claim 1)

[1463] Means for collecting user online behavior data,

[1464] A means of analyzing collected user data to extract user interests and preferences,

[1465] A means of generating personalized recommendations for each user,

[1466] A means of notifying users of the generated recommendations,

[1467] A means of accessing the content distribution service by clicking a link from the notified information,

[1468] The means by which the user views or uses the content selected by the user,

[1469] A system that includes this.

[1470] (Claim 2)

[1471] The system according to claim 1, characterized in that it includes means for collecting user behavior data for advertising and marketing purposes.

[1472] (Claim 3)

[1473] The system according to claim 1, characterized in that it includes means for encrypting the collected user data and transmitting it to a server.

[1474] "Example 2 of combining an emotion engine"

[1475] (Claim 1)

[1476] Means for collecting user online behavior data,

[1477] Means for collecting user sentiment data,

[1478] A means of encrypting the collected user data and sending it to the server,

[1479] A method for extracting user interests and preferences by analyzing collected user data and sentiment data,

[1480] A means of generating personalized recommendations for each user,

[1481] A means of notifying users of the generated recommendations,

[1482] The means of accessing the hometown tax donation site by clicking a link from the information provided,

[1483] A method for completing a donation based on the return gift information selected by the user,

[1484] A system that includes this.

[1485] (Claim 2)

[1486] The system according to claim 1, characterized in that it includes means for collecting user behavior data for advertising and marketing purposes.

[1487] (Claim 3)

[1488] The system according to claim 1, characterized in that it includes means for analyzing user emotional data using an emotion engine.

[1489] "Application example 2 when combining with an emotional engine"

[1490] (Claim 1)

[1491] Means for collecting user online behavior data,

[1492] A means of analyzing collected user data and sentiment data to extract user interests and preferences,

[1493] A means of generating personalized recommendations for each user,

[1494] A means of notifying users of the generated recommendations,

[1495] The means of accessing the target site by clicking a link from the notified information,

[1496] A means of completing the purchase process based on the product information selected by the user,

[1497] A system that includes this.

[1498] (Claim 2)

[1499] The system according to claim 1, characterized in that it includes means for collecting user behavior data for advertising and marketing purposes.

[1500] (Claim 3)

[1501] The system according to claim 1, characterized in that it includes means for encrypting the collected user data and transmitting it to a server. [Explanation of Symbols]

[1502] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means for collecting user online behavior data, A means of analyzing collected user data to extract user interests and preferences, A means of generating personalized recommendations for each user, A means of notifying users of the generated recommendations, The means of accessing the hometown tax donation site by clicking a link from the information provided, A method for completing a donation based on the return gift information selected by the user, A system that includes this.

2. The system according to claim 1, characterized in that it includes means for collecting user behavior data for advertising and marketing purposes.

3. The system according to claim 1, characterized in that it includes means for encrypting the collected user data and transmitting it to a server.

4. The system according to claim 1, characterized by using artificial intelligence to analyze the user's interests and preferences.

5. The system according to claim 1, characterized in that it includes means for notifying the generated recommendation information through a messaging service.

Images